feat: Common result dataclasses and refactoring several methods. (#50)

* chore: Rename scripts to tools folder and unify argument parser

* refactor: Centralize dataclasses in types.py and add __call__ to all models

- Move Face and result dataclasses to uniface/types.py
- Add GazeResult, SpoofingResult, EmotionResult (frozen=True)
- Add __call__ to BaseDetector, BaseRecognizer, BaseLandmarker
- Add __repr__ to all dataclasses
- Replace print() with Logger in onnx_utils.py
- Update tools and docs to use new dataclass return types
- Add test_types.py with comprehensive dataclass testschore: Rename files under tools folder and unitify argument parser for them

.github/workflows/ci.yml

@@ -10,14 +10,31 @@ on:
       - main
       - develop
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
-  test:
+  lint:
     runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+      - uses: pre-commit/action@v3.0.1
+
+  test:
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 15
+    needs: lint
 
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10", "3.11", "3.12", "3.13"]
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.11", "3.13"]
 
     steps:
       - name: Checkout code
@@ -27,7 +44,7 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache: 'pip'
+          cache: "pip"
 
       - name: Install dependencies
         run: |
@@ -38,21 +55,15 @@ jobs:
         run: |
           python -c "import onnxruntime as ort; print('Available providers:', ort.get_available_providers())"
 
-      - name: Lint with ruff (if available)
-        run: |
-          pip install ruff || true
-          ruff check . --exit-zero || true
-        continue-on-error: true
-
       - name: Run tests
         run: pytest -v --tb=short
 
       - name: Test package imports
-        run: |
-          python -c "from uniface import RetinaFace, ArcFace, Landmark106, AgeGender; print('All imports successful')"
+        run: python -c "import uniface; print(f'uniface {uniface.__version__} loaded with {len(uniface.__all__)} exports')"
 
   build:
     runs-on: ubuntu-latest
+    timeout-minutes: 10
     needs: test
 
     steps:
@@ -62,8 +73,8 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
-          cache: 'pip'
+          python-version: "3.11"
+          cache: "pip"
 
       - name: Install build tools
         run: |
@@ -84,4 +95,3 @@ jobs:
           name: dist-python-${{ github.sha }}
           path: dist/
           retention-days: 7
-

.github/workflows/publish.yml

@@ -5,9 +5,14 @@ on:
     tags:
       - "v*.*.*"  # Trigger only on version tags like v0.1.9
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
   validate:
     runs-on: ubuntu-latest
+    timeout-minutes: 5
     outputs:
       version: ${{ steps.get_version.outputs.version }}
       tag_version: ${{ steps.get_version.outputs.tag_version }}
@@ -16,13 +21,18 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
       - name: Get version from tag and pyproject.toml
         id: get_version
         run: |
           TAG_VERSION=${GITHUB_REF#refs/tags/v}
           echo "tag_version=$TAG_VERSION" >> $GITHUB_OUTPUT
 
-          PYPROJECT_VERSION=$(grep -Po '(?<=^version = ")[^"]*' pyproject.toml)
+          PYPROJECT_VERSION=$(python -c "import tomllib; print(tomllib.load(open('pyproject.toml','rb'))['project']['version'])")
           echo "version=$PYPROJECT_VERSION" >> $GITHUB_OUTPUT
 
           echo "Tag version: v$TAG_VERSION"
@@ -38,12 +48,13 @@ jobs:
 
   test:
     runs-on: ubuntu-latest
+    timeout-minutes: 15
     needs: validate
 
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.11", "3.13"]
 
     steps:
       - name: Checkout code
@@ -65,6 +76,7 @@ jobs:
 
   publish:
     runs-on: ubuntu-latest
+    timeout-minutes: 10
     needs: [validate, test]
     permissions:
       contents: write
@@ -105,4 +117,3 @@ jobs:
         with:
           files: dist/*
           generate_release_notes: true
-

.pre-commit-config.yaml

@@ -0,0 +1,40 @@
+# Pre-commit configuration for UniFace
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+
+repos:
+  # General file checks
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-toml
+      - id: check-added-large-files
+        args: ['--maxkb=1000']
+      - id: check-merge-conflict
+      - id: debug-statements
+      - id: check-ast
+
+  # Ruff - Fast Python linter and formatter
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.14.10
+    hooks:
+      - id: ruff
+        args: [--fix, --unsafe-fixes, --exit-non-zero-on-fix]
+      - id: ruff-format
+
+  # Security checks
+  - repo: https://github.com/PyCQA/bandit
+    rev: 1.9.2
+    hooks:
+      - id: bandit
+        args: [-c, pyproject.toml]
+        additional_dependencies: ['bandit[toml]']
+        exclude: ^tests/
+
+# Configuration
+ci:
+  autofix_commit_msg: 'style: auto-fix by pre-commit hooks'
+  autoupdate_commit_msg: 'chore: update pre-commit hooks'

CONTRIBUTING.md

@@ -0,0 +1,190 @@
+# Contributing to UniFace
+
+Thank you for considering contributing to UniFace! We welcome contributions of all kinds.
+
+## How to Contribute
+
+### Reporting Issues
+
+- Use GitHub Issues to report bugs or suggest features
+- Include clear descriptions and reproducible examples
+- Check existing issues before creating new ones
+
+### Pull Requests
+
+1. Fork the repository
+2. Create a new branch for your feature
+3. Write clear, documented code with type hints
+4. Add tests for new functionality
+5. Ensure all tests pass and pre-commit hooks are satisfied
+6. Submit a pull request with a clear description
+
+## Development Setup
+
+```bash
+git clone https://github.com/yakhyo/uniface.git
+cd uniface
+pip install -e ".[dev]"
+```
+
+### Setting Up Pre-commit Hooks
+
+We use [pre-commit](https://pre-commit.com/) to ensure code quality and consistency. Install and configure it:
+
+```bash
+# Install pre-commit
+pip install pre-commit
+
+# Install the git hooks
+pre-commit install
+
+# (Optional) Run against all files
+pre-commit run --all-files
+```
+
+Once installed, pre-commit will automatically run on every commit to check:
+
+- Code formatting and linting (Ruff)
+- Security issues (Bandit)
+- General file hygiene (trailing whitespace, YAML/TOML validity, etc.)
+
+**Note:** All PRs are automatically checked by CI. The merge button will only be available after all checks pass.
+
+## Code Style
+
+This project uses [Ruff](https://docs.astral.sh/ruff/) for linting and formatting, following modern Python best practices. Pre-commit handles all formatting automatically.
+
+### Style Guidelines
+
+#### General Rules
+
+- **Line length:** 120 characters maximum
+- **Python version:** 3.11+ (use modern syntax)
+- **Quote style:** Single quotes for strings, double quotes for docstrings
+
+#### Type Hints
+
+Use modern Python 3.11+ type hints (PEP 585 and PEP 604):
+
+```python
+# Preferred (modern)
+def process(items: list[str], config: dict[str, int] | None = None) -> tuple[int, str]:
+    ...
+
+# Avoid (legacy)
+from typing import List, Dict, Optional, Tuple
+def process(items: List[str], config: Optional[Dict[str, int]] = None) -> Tuple[int, str]:
+    ...
+```
+
+#### Docstrings
+
+Use [Google-style docstrings](https://google.github.io/styleguide/pyguide.html#38-comments-and-docstrings) for all public APIs:
+
+```python
+def detect_faces(image: np.ndarray, threshold: float = 0.5) -> list[Face]:
+    """Detect faces in an image.
+
+    Args:
+        image: Input image as a numpy array with shape (H, W, C) in BGR format.
+        threshold: Confidence threshold for filtering detections. Defaults to 0.5.
+
+    Returns:
+        List of Face objects containing bounding boxes, confidence scores,
+        and facial landmarks.
+
+    Raises:
+        ValueError: If the input image has invalid dimensions.
+
+    Example:
+        >>> from uniface import detect_faces
+        >>> faces = detect_faces(image, threshold=0.8)
+        >>> print(f"Found {len(faces)} faces")
+    """
+```
+
+#### Import Order
+
+Imports are automatically sorted by Ruff with the following order:
+
+1. **Future** imports (`from __future__ import annotations`)
+2. **Standard library** (`os`, `sys`, `typing`, etc.)
+3. **Third-party** (`numpy`, `cv2`, `onnxruntime`, etc.)
+4. **First-party** (`uniface.*`)
+5. **Local** (relative imports like `.base`, `.models`)
+
+```python
+from __future__ import annotations
+
+import os
+from typing import Any
+
+import cv2
+import numpy as np
+
+from uniface.constants import RetinaFaceWeights
+from uniface.log import Logger
+
+from .base import BaseDetector
+```
+
+#### Code Comments
+
+- Add comments for complex logic, magic numbers, and non-obvious behavior
+- Avoid comments that merely restate the code
+- Use `# TODO:` with issue links for planned improvements
+
+```python
+# RetinaFace FPN strides and corresponding anchor sizes per level
+steps = [8, 16, 32]
+min_sizes = [[16, 32], [64, 128], [256, 512]]
+
+# Add small epsilon to prevent division by zero
+similarity = np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b) + 1e-5)
+```
+
+## Running Tests
+
+```bash
+# Run all tests
+pytest tests/
+
+# Run with verbose output
+pytest tests/ -v
+
+# Run specific test file
+pytest tests/test_factory.py
+
+# Run with coverage
+pytest tests/ --cov=uniface --cov-report=html
+```
+
+## Adding New Features
+
+When adding a new model or feature:
+
+1. **Create the model class** in the appropriate submodule (e.g., `uniface/detection/`)
+2. **Add weight constants** to `uniface/constants.py` with URLs and SHA256 hashes
+3. **Export in `__init__.py`** files at both module and package levels
+4. **Write tests** in `tests/` directory
+5. **Add example usage** in `tools/` or update existing notebooks
+6. **Update documentation** if needed
+
+## Examples
+
+Example notebooks demonstrating library usage:
+
+| Example | Notebook |
+|---------|----------|
+| Face Detection | [01_face_detection.ipynb](examples/01_face_detection.ipynb) |
+| Face Alignment | [02_face_alignment.ipynb](examples/02_face_alignment.ipynb) |
+| Face Verification | [03_face_verification.ipynb](examples/03_face_verification.ipynb) |
+| Face Search | [04_face_search.ipynb](examples/04_face_search.ipynb) |
+| Face Analyzer | [05_face_analyzer.ipynb](examples/05_face_analyzer.ipynb) |
+| Face Parsing | [06_face_parsing.ipynb](examples/06_face_parsing.ipynb) |
+| Face Anonymization | [07_face_anonymization.ipynb](examples/07_face_anonymization.ipynb) |
+| Gaze Estimation | [08_gaze_estimation.ipynb](examples/08_gaze_estimation.ipynb) |
+
+## Questions?
+
+Open an issue or start a discussion on GitHub.

MODELS.md

@@ -10,17 +10,17 @@ Complete guide to all available models, their performance characteristics, and s
 
 RetinaFace models are trained on the WIDER FACE dataset and provide excellent accuracy-speed tradeoffs.
 
-| Model Name          | Params | Size   | Easy   | Medium | Hard   | Use Case                    |
-|---------------------|--------|--------|--------|--------|--------|----------------------------|
-| `MNET_025`          | 0.4M   | 1.7MB  | 88.48% | 87.02% | 80.61% | Mobile/Edge devices         |
-| `MNET_050`          | 1.0M   | 2.6MB  | 89.42% | 87.97% | 82.40% | Mobile/Edge devices         |
-| `MNET_V1`           | 3.5M   | 3.8MB  | 90.59% | 89.14% | 84.13% | Balanced mobile             |
-| `MNET_V2` ⭐        | 3.2M   | 3.5MB  | 91.70% | 91.03% | 86.60% | **Recommended default**     |
-| `RESNET18`          | 11.7M  | 27MB   | 92.50% | 91.02% | 86.63% | Server/High accuracy        |
-| `RESNET34`          | 24.8M  | 56MB   | 94.16% | 93.12% | 88.90% | Maximum accuracy            |
+| Model Name     | Params | Size  | Easy   | Medium | Hard   | Use Case                      |
+| -------------- | ------ | ----- | ------ | ------ | ------ | ----------------------------- |
+| `MNET_025`   | 0.4M   | 1.7MB | 88.48% | 87.02% | 80.61% | Mobile/Edge devices           |
+| `MNET_050`   | 1.0M   | 2.6MB | 89.42% | 87.97% | 82.40% | Mobile/Edge devices           |
+| `MNET_V1`    | 3.5M   | 3.8MB | 90.59% | 89.14% | 84.13% | Balanced mobile               |
+| `MNET_V2` ⭐ | 3.2M   | 3.5MB | 91.70% | 91.03% | 86.60% | **Recommended default** |
+| `RESNET18`   | 11.7M  | 27MB  | 92.50% | 91.02% | 86.63% | Server/High accuracy          |
+| `RESNET34`   | 24.8M  | 56MB  | 94.16% | 93.12% | 88.90% | Maximum accuracy              |
 
 **Accuracy**: WIDER FACE validation set (Easy/Medium/Hard subsets) - from [RetinaFace paper](https://arxiv.org/abs/1905.00641)
-**Speed**: Benchmark on your own hardware using `scripts/run_detection.py --iterations 100`
+**Speed**: Benchmark on your own hardware using `tools/detection.py --source <image> --iterations 100`
 
 #### Usage
 
@@ -34,7 +34,7 @@ detector = RetinaFace()  # Uses MNET_V2
 # Specific model
 detector = RetinaFace(
     model_name=RetinaFaceWeights.MNET_025,  # Fastest
-    conf_thresh=0.5,
+    confidence_threshold=0.5,
     nms_thresh=0.4,
     input_size=(640, 640)
 )
@@ -46,13 +46,13 @@ detector = RetinaFace(
 
 SCRFD (Sample and Computation Redistribution for Efficient Face Detection) models offer state-of-the-art speed-accuracy tradeoffs.
 
-| Model Name      | Params | Size  | Easy   | Medium | Hard   | Use Case                    |
-|-----------------|--------|-------|--------|--------|--------|----------------------------|
-| `SCRFD_500M`    | 0.6M   | 2.5MB | 90.57% | 88.12% | 68.51% | Real-time applications      |
-| `SCRFD_10G` ⭐  | 4.2M   | 17MB  | 95.16% | 93.87% | 83.05% | **High accuracy + speed**   |
+| Model Name       | Params | Size  | Easy   | Medium | Hard   | Use Case                        |
+| ---------------- | ------ | ----- | ------ | ------ | ------ | ------------------------------- |
+| `SCRFD_500M`   | 0.6M   | 2.5MB | 90.57% | 88.12% | 68.51% | Real-time applications          |
+| `SCRFD_10G` ⭐ | 4.2M   | 17MB  | 95.16% | 93.87% | 83.05% | **High accuracy + speed** |
 
 **Accuracy**: WIDER FACE validation set - from [SCRFD paper](https://arxiv.org/abs/2105.04714)
-**Speed**: Benchmark on your own hardware using `scripts/run_detection.py --iterations 100`
+**Speed**: Benchmark on your own hardware using `tools/detection.py --source <image> --iterations 100`
 
 #### Usage
 
@@ -63,29 +63,79 @@ from uniface.constants import SCRFDWeights
 # Fast real-time detection
 detector = SCRFD(
     model_name=SCRFDWeights.SCRFD_500M_KPS,
-    conf_thresh=0.5,
+    confidence_threshold=0.5,
     input_size=(640, 640)
 )
 
 # High accuracy
 detector = SCRFD(
     model_name=SCRFDWeights.SCRFD_10G_KPS,
-    conf_thresh=0.5
+    confidence_threshold=0.5
 )
 ```
 
 ---
 
+### YOLOv5-Face Family
+
+YOLOv5-Face models provide excellent detection accuracy with 5-point facial landmarks, optimized for real-time applications.
+
+| Model Name     | Size | Easy   | Medium | Hard   | Use Case                       |
+| -------------- | ---- | ------ | ------ | ------ | ------------------------------ |
+| `YOLOV5N`    | 11MB | 93.61% | 91.52% | 80.53% | Lightweight/Mobile             |
+| `YOLOV5S` ⭐ | 28MB | 94.33% | 92.61% | 83.15% | **Real-time + accuracy** |
+| `YOLOV5M`    | 82MB | 95.30% | 93.76% | 85.28% | High accuracy                  |
+
+**Accuracy**: WIDER FACE validation set - from [YOLOv5-Face paper](https://arxiv.org/abs/2105.12931)
+**Speed**: Benchmark on your own hardware using `tools/detection.py --source <image> --iterations 100`
+**Note**: Fixed input size of 640×640. Models exported to ONNX from [deepcam-cn/yolov5-face](https://github.com/deepcam-cn/yolov5-face)
+
+#### Usage
+
+```python
+from uniface import YOLOv5Face
+from uniface.constants import YOLOv5FaceWeights
+
+# Lightweight/Mobile
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5N,
+    confidence_threshold=0.6,
+    nms_thresh=0.5
+)
+
+# Real-time detection (recommended)
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5S,
+    confidence_threshold=0.6,
+    nms_thresh=0.5
+)
+
+# High accuracy
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5M,
+    confidence_threshold=0.6
+)
+
+# Detect faces with landmarks
+faces = detector.detect(image)
+for face in faces:
+    bbox = face.bbox  # [x1, y1, x2, y2]
+    confidence = face.confidence
+    landmarks = face.landmarks  # 5-point landmarks (5, 2)
+```
+
+---
+
 ## Face Recognition Models
 
 ### ArcFace
 
 State-of-the-art face recognition using additive angular margin loss.
 
-| Model Name  | Backbone    | Params | Size  | Use Case                    |
-|-------------|-------------|--------|-------|----------------------------|
-| `MNET` ⭐   | MobileNet   | 2.0M   | 8MB   | **Balanced (recommended)** |
-| `RESNET`    | ResNet50    | 43.6M  | 166MB | Maximum accuracy           |
+| Model Name  | Backbone  | Params | Size  | Use Case                         |
+| ----------- | --------- | ------ | ----- | -------------------------------- |
+| `MNET` ⭐ | MobileNet | 2.0M   | 8MB   | **Balanced (recommended)** |
+| `RESNET`  | ResNet50  | 43.6M  | 166MB | Maximum accuracy                 |
 
 **Dataset**: Trained on MS1M-V2 (5.8M images, 85K identities)
 **Accuracy**: Benchmark on your own dataset or use standard face verification benchmarks
@@ -113,12 +163,12 @@ embedding = recognizer.get_normalized_embedding(image, landmarks)
 
 Lightweight face recognition optimized for mobile devices.
 
-| Model Name      | Backbone        | Params | Size | LFW   | CALFW | CPLFW | AgeDB-30 | Use Case           |
-|-----------------|-----------------|--------|------|-------|-------|-------|----------|--------------------|
-| `MNET_025`      | MobileNetV1 0.25| 0.36M  | 1MB  | 98.76%| 92.02%| 82.37%| 90.02%   | Ultra-lightweight  |
-| `MNET_V2` ⭐    | MobileNetV2     | 2.29M  | 4MB  | 99.55%| 94.87%| 86.89%| 95.16%   | **Mobile/Edge**    |
-| `MNET_V3_SMALL` | MobileNetV3-S   | 1.25M  | 3MB  | 99.30%| 93.77%| 85.29%| 92.79%   | Mobile optimized   |
-| `MNET_V3_LARGE` | MobileNetV3-L   | 3.52M  | 10MB | 99.53%| 94.56%| 86.79%| 95.13%   | Balanced mobile    |
+| Model Name        | Backbone         | Params | Size | LFW    | CALFW  | CPLFW  | AgeDB-30 | Use Case              |
+| ----------------- | ---------------- | ------ | ---- | ------ | ------ | ------ | -------- | --------------------- |
+| `MNET_025`      | MobileNetV1 0.25 | 0.36M  | 1MB  | 98.76% | 92.02% | 82.37% | 90.02%   | Ultra-lightweight     |
+| `MNET_V2` ⭐    | MobileNetV2      | 2.29M  | 4MB  | 99.55% | 94.87% | 86.89% | 95.16%   | **Mobile/Edge** |
+| `MNET_V3_SMALL` | MobileNetV3-S    | 1.25M  | 3MB  | 99.30% | 93.77% | 85.29% | 92.79%   | Mobile optimized      |
+| `MNET_V3_LARGE` | MobileNetV3-L    | 3.52M  | 10MB | 99.53% | 94.56% | 86.79% | 95.13%   | Balanced mobile       |
 
 **Dataset**: Trained on MS1M-V2 (5.8M images, 85K identities)
 **Accuracy**: Evaluated on LFW, CALFW, CPLFW, and AgeDB-30 benchmarks
@@ -140,10 +190,10 @@ recognizer = MobileFace(model_name=MobileFaceWeights.MNET_V2)
 
 Face recognition using angular softmax loss.
 
-| Model Name  | Backbone | Params | Size | LFW   | CALFW | CPLFW | AgeDB-30 | Use Case              |
-|-------------|----------|--------|------|-------|-------|-------|----------|----------------------|
-| `SPHERE20`  | Sphere20 | 24.5M  | 50MB | 99.67%| 95.61%| 88.75%| 96.58%   | Research/Comparison  |
-| `SPHERE36`  | Sphere36 | 34.6M  | 92MB | 99.72%| 95.64%| 89.92%| 96.83%   | Research/Comparison  |
+| Model Name   | Backbone | Params | Size | LFW    | CALFW  | CPLFW  | AgeDB-30 | Use Case            |
+| ------------ | -------- | ------ | ---- | ------ | ------ | ------ | -------- | ------------------- |
+| `SPHERE20` | Sphere20 | 24.5M  | 50MB | 99.67% | 95.61% | 88.75% | 96.58%   | Research/Comparison |
+| `SPHERE36` | Sphere36 | 34.6M  | 92MB | 99.72% | 95.64% | 89.92% | 96.83%   | Research/Comparison |
 
 **Dataset**: Trained on MS1M-V2 (5.8M images, 85K identities)
 **Accuracy**: Evaluated on LFW, CALFW, CPLFW, and AgeDB-30 benchmarks
@@ -166,9 +216,9 @@ recognizer = SphereFace(model_name=SphereFaceWeights.SPHERE20)
 
 High-precision facial landmark localization.
 
-| Model Name | Points | Params | Size | Use Case                    |
-|------------|--------|--------|------|-----------------------------|
-| `2D106`    | 106    | 3.7M   | 14MB | Face alignment, analysis    |
+| Model Name | Points | Params | Size | Use Case                 |
+| ---------- | ------ | ------ | ---- | ------------------------ |
+| `2D106`  | 106    | 3.7M   | 14MB | Face alignment, analysis |
 
 **Note**: Provides 106 facial keypoints for detailed face analysis and alignment
 
@@ -183,6 +233,7 @@ landmarks = landmarker.get_landmarks(image, bbox)
 ```
 
 **Landmark Groups:**
+
 - Face contour: 0-32 (33 points)
 - Eyebrows: 33-50 (18 points)
 - Nose: 51-62 (12 points)
@@ -195,9 +246,9 @@ landmarks = landmarker.get_landmarks(image, bbox)
 
 ### Age & Gender Detection
 
-| Model Name | Attributes  | Params | Size | Use Case           |
-|------------|-------------|--------|------|-------------------|
-| `DEFAULT`  | Age, Gender | 2.1M   | 8MB  | General purpose   |
+| Model Name  | Attributes  | Params | Size | Use Case        |
+| ----------- | ----------- | ------ | ---- | --------------- |
+| `DEFAULT` | Age, Gender | 2.1M   | 8MB  | General purpose |
 
 **Dataset**: Trained on CelebA
 **Note**: Accuracy varies by demographic and image quality. Test on your specific use case.
@@ -208,18 +259,50 @@ landmarks = landmarker.get_landmarks(image, bbox)
 from uniface import AgeGender
 
 predictor = AgeGender()
-gender, age = predictor.predict(image, bbox)
-# Returns: ("Male"/"Female", age_in_years)
+result = predictor.predict(image, bbox)
+# Returns: AttributeResult with gender, age, sex property
+# result.gender: 0 for Female, 1 for Male
+# result.sex: "Female" or "Male"
+# result.age: age in years
+```
+
+---
+
+### FairFace Attributes
+
+| Model Name  | Attributes            | Params | Size  | Use Case                    |
+| ----------- | --------------------- | ------ | ----- | --------------------------- |
+| `DEFAULT` | Race, Gender, Age Group | -      | 44MB  | Balanced demographic prediction |
+
+**Dataset**: Trained on FairFace dataset with balanced demographics
+**Note**: FairFace provides more equitable predictions across different racial and gender groups
+
+**Race Categories (7):** White, Black, Latino Hispanic, East Asian, Southeast Asian, Indian, Middle Eastern
+
+**Age Groups (9):** 0-2, 3-9, 10-19, 20-29, 30-39, 40-49, 50-59, 60-69, 70+
+
+#### Usage
+
+```python
+from uniface import FairFace
+
+predictor = FairFace()
+result = predictor.predict(image, bbox)
+# Returns: AttributeResult with gender, age_group, race, sex property
+# result.gender: 0 for Female, 1 for Male
+# result.sex: "Female" or "Male"
+# result.age_group: "20-29", "30-39", etc.
+# result.race: "East Asian", "White", etc.
 ```
 
 ---
 
 ### Emotion Detection
 
-| Model Name   | Classes | Params | Size | Use Case              |
-|--------------|---------|--------|------|-----------------------|
-| `AFFECNET7`  | 7       | 0.5M   | 2MB  | 7-class emotion       |
-| `AFFECNET8`  | 8       | 0.5M   | 2MB  | 8-class emotion       |
+| Model Name    | Classes | Params | Size | Use Case        |
+| ------------- | ------- | ------ | ---- | --------------- |
+| `AFFECNET7` | 7       | 0.5M   | 2MB  | 7-class emotion |
+| `AFFECNET8` | 8       | 0.5M   | 2MB  | 8-class emotion |
 
 **Classes (7)**: Neutral, Happy, Sad, Surprise, Fear, Disgust, Anger
 **Classes (8)**: Above + Contempt
@@ -234,120 +317,164 @@ from uniface import Emotion
 from uniface.constants import DDAMFNWeights
 
 predictor = Emotion(model_name=DDAMFNWeights.AFFECNET7)
-emotion, confidence = predictor.predict(image, landmarks)
+result = predictor.predict(image, landmarks)
+# result.emotion: predicted emotion label
+# result.confidence: confidence score
 ```
 
 ---
 
-## Model Selection Guide
+## Gaze Estimation Models
 
-### By Use Case
+### MobileGaze Family
 
-#### Mobile/Edge Devices
-- **Detection**: `RetinaFace(MNET_025)` or `SCRFD(SCRFD_500M)`
-- **Recognition**: `MobileFace(MNET_V2)`
-- **Priority**: Speed, small model size
+Real-time gaze direction prediction models trained on Gaze360 dataset. Returns pitch (vertical) and yaw (horizontal) angles in radians.
 
-#### Real-Time Applications (Webcam, Video)
-- **Detection**: `RetinaFace(MNET_V2)` or `SCRFD(SCRFD_500M)`
-- **Recognition**: `ArcFace(MNET)`
-- **Priority**: Speed-accuracy balance
+| Model Name     | Params | Size    | MAE*  | Use Case                      |
+| -------------- | ------ | ------- | ----- | ----------------------------- |
+| `RESNET18`   | 11.7M  | 43 MB   | 12.84 | Balanced accuracy/speed       |
+| `RESNET34` ⭐ | 24.8M  | 81.6 MB | 11.33 | **Recommended default** |
+| `RESNET50`   | 25.6M  | 91.3 MB | 11.34 | High accuracy                 |
+| `MOBILENET_V2` | 3.5M   | 9.59 MB | 13.07 | Mobile/Edge devices           |
+| `MOBILEONE_S0` | 2.1M   | 4.8 MB  | 12.58 | Lightweight/Real-time         |
 
-#### High-Accuracy Applications (Security, Verification)
-- **Detection**: `SCRFD(SCRFD_10G)` or `RetinaFace(RESNET34)`
-- **Recognition**: `ArcFace(RESNET)`
-- **Priority**: Maximum accuracy
+*MAE (Mean Absolute Error) in degrees on Gaze360 test set - lower is better
 
-#### Server/Cloud Deployment
-- **Detection**: `SCRFD(SCRFD_10G)`
-- **Recognition**: `ArcFace(RESNET)`
-- **Priority**: Accuracy, batch processing
+**Dataset**: Trained on Gaze360 (indoor/outdoor scenes with diverse head poses)
+**Training**: 200 epochs with classification-based approach (binned angles)
+
+#### Usage
+
+```python
+from uniface import MobileGaze
+from uniface.constants import GazeWeights
+import numpy as np
+
+# Default (recommended)
+gaze_estimator = MobileGaze()  # Uses RESNET34
+
+# Lightweight model
+gaze_estimator = MobileGaze(model_name=GazeWeights.MOBILEONE_S0)
+
+# Estimate gaze from face crop
+result = gaze_estimator.estimate(face_crop)
+print(f"Pitch: {np.degrees(result.pitch):.1f}°, Yaw: {np.degrees(result.yaw):.1f}°")
+```
+
+**Note**: Requires face crop as input. Use face detection first to obtain bounding boxes.
 
 ---
 
-### By Hardware
+## Face Parsing Models
 
-#### Apple Silicon (M1/M2/M3/M4)
-**Recommended**: All models work well with ARM64 optimizations (automatically included)
+### BiSeNet Family
 
-```bash
-pip install uniface
+BiSeNet (Bilateral Segmentation Network) models for semantic face parsing. Segments face images into 19 facial component classes.
+
+| Model Name     | Params | Size    | Classes | Use Case                      |
+| -------------- | ------ | ------- | ------- | ----------------------------- |
+| `RESNET18` ⭐ | 13.3M  | 50.7 MB | 19      | **Recommended default** |
+| `RESNET34`   | 24.1M  | 89.2 MB | 19      | Higher accuracy               |
+
+**19 Facial Component Classes:**
+1. Background
+2. Skin
+3. Left Eyebrow
+4. Right Eyebrow
+5. Left Eye
+6. Right Eye
+7. Eye Glasses
+8. Left Ear
+9. Right Ear
+10. Ear Ring
+11. Nose
+12. Mouth
+13. Upper Lip
+14. Lower Lip
+15. Neck
+16. Neck Lace
+17. Cloth
+18. Hair
+19. Hat
+
+**Dataset**: Trained on CelebAMask-HQ
+**Architecture**: BiSeNet with ResNet backbone
+**Input Size**: 512×512 (automatically resized)
+
+#### Usage
+
+```python
+from uniface.parsing import BiSeNet
+from uniface.constants import ParsingWeights
+from uniface.visualization import vis_parsing_maps
+import cv2
+
+# Default (recommended)
+parser = BiSeNet()  # Uses RESNET18
+
+# Higher accuracy model
+parser = BiSeNet(model_name=ParsingWeights.RESNET34)
+
+# Parse face image (already cropped)
+mask = parser.parse(face_image)
+
+# Visualize with overlay
+face_rgb = cv2.cvtColor(face_image, cv2.COLOR_BGR2RGB)
+vis_result = vis_parsing_maps(face_rgb, mask, save_image=False)
+
+# mask shape: (H, W) with values 0-18 representing classes
+print(f"Detected {len(np.unique(mask))} facial components")
 ```
 
-**Recommended models**:
-- **Fast**: `SCRFD(SCRFD_500M)` - Lightweight, real-time capable
-- **Balanced**: `RetinaFace(MNET_V2)` - Good accuracy/speed tradeoff
-- **Accurate**: `SCRFD(SCRFD_10G)` - High accuracy
+**Applications:**
+- Face makeup and beauty applications
+- Virtual try-on systems
+- Face editing and manipulation
+- Facial feature extraction
+- Portrait segmentation
 
-**Benchmark on your M4**: `python scripts/run_detection.py --iterations 100`
-
-#### NVIDIA GPU (CUDA)
-**Recommended**: Larger models for maximum throughput
-
-```bash
-pip install uniface[gpu]
-```
-
-**Recommended models**:
-- **Fast**: `SCRFD(SCRFD_500M)` - Maximum throughput
-- **Balanced**: `SCRFD(SCRFD_10G)` - Best overall
-- **Accurate**: `RetinaFace(RESNET34)` - Highest accuracy
-
-#### CPU Only
-**Recommended**: Lightweight models
-
-**Recommended models**:
-- **Fast**: `RetinaFace(MNET_025)` - Smallest, fastest
-- **Balanced**: `RetinaFace(MNET_V2)` - Recommended default
-- **Accurate**: `SCRFD(SCRFD_10G)` - Best accuracy on CPU
-
-**Note**: FPS values vary significantly based on image size, number of faces, and hardware. Always benchmark on your specific setup.
+**Note**: Input should be a cropped face image. For full pipeline, use face detection first to obtain face crops.
 
 ---
 
-## Benchmark Details
+## Anti-Spoofing Models
 
-### How to Benchmark
+### MiniFASNet Family
 
-Run benchmarks on your own hardware:
+Lightweight face anti-spoofing models for liveness detection. Detect if a face is real (live) or fake (photo, video replay, mask).
 
-```bash
-# Detection speed
-python scripts/run_detection.py --image assets/test.jpg --iterations 100
+| Model Name | Size   | Scale | Use Case                      |
+| ---------- | ------ | ----- | ----------------------------- |
+| `V1SE`   | 1.2 MB | 4.0   | Squeeze-and-excitation variant |
+| `V2` ⭐  | 1.2 MB | 2.7   | **Recommended default**       |
 
-# Compare models
-python scripts/run_detection.py --image assets/test.jpg --method retinaface --iterations 100
-python scripts/run_detection.py --image assets/test.jpg --method scrfd --iterations 100
+**Dataset**: Trained on face anti-spoofing datasets
+**Output**: Returns `SpoofingResult(is_real, confidence)` where is_real: True=Real, False=Fake
+
+#### Usage
+
+```python
+from uniface import RetinaFace
+from uniface.spoofing import MiniFASNet
+from uniface.constants import MiniFASNetWeights
+
+# Default (V2, recommended)
+detector = RetinaFace()
+spoofer = MiniFASNet()
+
+# V1SE variant
+spoofer = MiniFASNet(model_name=MiniFASNetWeights.V1SE)
+
+# Detect and check liveness
+faces = detector.detect(image)
+for face in faces:
+    result = spoofer.predict(image, face.bbox)
+    # result.is_real: True for real, False for fake
+    label = 'Real' if result.is_real else 'Fake'
+    print(f"{label}: {result.confidence:.1%}")
 ```
 
-### Accuracy Metrics Explained
-
-- **WIDER FACE**: Standard face detection benchmark with three difficulty levels
-  - **Easy**: Large faces (>50px), clear backgrounds
-  - **Medium**: Medium-sized faces (30-50px), moderate occlusion
-  - **Hard**: Small faces (<30px), heavy occlusion, blur
-
-  *Accuracy values are from the original papers - see references below*
-
-- **Model Size**: ONNX model file size (affects download time and memory)
-- **Params**: Number of model parameters (affects inference speed)
-
-### Important Notes
-
-1. **Speed varies by**:
-   - Image resolution
-   - Number of faces in image
-   - Hardware (CPU/GPU/CoreML)
-   - Batch size
-   - Operating system
-
-2. **Accuracy varies by**:
-   - Image quality
-   - Lighting conditions
-   - Face pose and occlusion
-   - Demographic factors
-
-3. **Always benchmark on your specific use case** before choosing a model
+**Note**: Requires face bounding box from a detector. Use with RetinaFace, SCRFD, or YOLOv5Face.
 
 ---
 
@@ -374,10 +501,10 @@ model_path = verify_model_weights(
 
 ```bash
 # Using the provided script
-python scripts/download_model.py
+python tools/download_model.py
 
 # Download specific model
-python scripts/download_model.py --model MNET_V2
+python tools/download_model.py --model MNET_V2
 ```
 
 ---
@@ -387,13 +514,20 @@ python scripts/download_model.py --model MNET_V2
 ### Model Training & Architectures
 
 - **RetinaFace Training**: [yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch) - PyTorch implementation and training code
+- **YOLOv5-Face Original**: [deepcam-cn/yolov5-face](https://github.com/deepcam-cn/yolov5-face) - Original PyTorch implementation
+- **YOLOv5-Face ONNX**: [yakhyo/yolov5-face-onnx-inference](https://github.com/yakhyo/yolov5-face-onnx-inference) - ONNX inference implementation
 - **Face Recognition Training**: [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition) - ArcFace, MobileFace, SphereFace training code
+- **Gaze Estimation Training**: [yakhyo/gaze-estimation](https://github.com/yakhyo/gaze-estimation) - MobileGaze training code and pretrained weights
+- **Face Parsing Training**: [yakhyo/face-parsing](https://github.com/yakhyo/face-parsing) - BiSeNet training code and pretrained weights
+- **Face Anti-Spoofing**: [yakhyo/face-anti-spoofing](https://github.com/yakhyo/face-anti-spoofing) - MiniFASNet ONNX inference (weights from [minivision-ai/Silent-Face-Anti-Spoofing](https://github.com/minivision-ai/Silent-Face-Anti-Spoofing))
+- **FairFace**: [yakhyo/fairface-onnx](https://github.com/yakhyo/fairface-onnx) - FairFace ONNX inference for race, gender, age prediction
 - **InsightFace**: [deepinsight/insightface](https://github.com/deepinsight/insightface) - Model architectures and pretrained weights
 
 ### Papers
 
 - **RetinaFace**: [Single-Shot Multi-Level Face Localisation in the Wild](https://arxiv.org/abs/1905.00641)
 - **SCRFD**: [Sample and Computation Redistribution for Efficient Face Detection](https://arxiv.org/abs/2105.04714)
+- **YOLOv5-Face**: [YOLO5Face: Why Reinventing a Face Detector](https://arxiv.org/abs/2105.12931)
 - **ArcFace**: [Additive Angular Margin Loss for Deep Face Recognition](https://arxiv.org/abs/1801.07698)
 - **SphereFace**: [Deep Hypersphere Embedding for Face Recognition](https://arxiv.org/abs/1704.08063)
-
+- **BiSeNet**: [Bilateral Segmentation Network for Real-time Semantic Segmentation](https://arxiv.org/abs/1808.00897)

QUICKSTART.md

@@ -39,12 +39,13 @@ faces = detector.detect(image)
 # Print results
 for i, face in enumerate(faces):
     print(f"Face {i+1}:")
-    print(f"  Confidence: {face['confidence']:.2f}")
-    print(f"  BBox: {face['bbox']}")
-    print(f"  Landmarks: {len(face['landmarks'])} points")
+    print(f"  Confidence: {face.confidence:.2f}")
+    print(f"  BBox: {face.bbox}")
+    print(f"  Landmarks: {len(face.landmarks)} points")
 ```
 
 **Output:**
+
 ```
 Face 1:
   Confidence: 0.99
@@ -69,12 +70,18 @@ image = cv2.imread("photo.jpg")
 faces = detector.detect(image)
 
 # Extract visualization data
-bboxes = [f['bbox'] for f in faces]
-scores = [f['confidence'] for f in faces]
-landmarks = [f['landmarks'] for f in faces]
+bboxes = [f.bbox for f in faces]
+scores = [f.confidence for f in faces]
+landmarks = [f.landmarks for f in faces]
 
 # Draw on image
-draw_detections(image, bboxes, scores, landmarks, vis_threshold=0.6)
+draw_detections(
+    image=image,
+    bboxes=bboxes,
+    scores=scores,
+    landmarks=landmarks,
+    vis_threshold=0.6,
+)
 
 # Save result
 cv2.imwrite("output.jpg", image)
@@ -106,8 +113,8 @@ faces2 = detector.detect(image2)
 
 if faces1 and faces2:
     # Extract embeddings
-    emb1 = recognizer.get_normalized_embedding(image1, faces1[0]['landmarks'])
-    emb2 = recognizer.get_normalized_embedding(image2, faces2[0]['landmarks'])
+    emb1 = recognizer.get_normalized_embedding(image1, faces1[0].landmarks)
+    emb2 = recognizer.get_normalized_embedding(image2, faces2[0].landmarks)
 
     # Compute similarity (cosine similarity)
     similarity = np.dot(emb1, emb2.T)[0][0]
@@ -122,6 +129,7 @@ else:
 ```
 
 **Similarity thresholds:**
+
 - `> 0.6`: Same person (high confidence)
 - `0.4 - 0.6`: Uncertain (manual review)
 - `< 0.4`: Different people
@@ -151,10 +159,15 @@ while True:
     faces = detector.detect(frame)
 
     # Draw results
-    bboxes = [f['bbox'] for f in faces]
-    scores = [f['confidence'] for f in faces]
-    landmarks = [f['landmarks'] for f in faces]
-    draw_detections(frame, bboxes, scores, landmarks)
+    bboxes = [f.bbox for f in faces]
+    scores = [f.confidence for f in faces]
+    landmarks = [f.landmarks for f in faces]
+    draw_detections(
+        image=frame,
+        bboxes=bboxes,
+        scores=scores,
+        landmarks=landmarks,
+    )
 
     # Show frame
     cv2.imshow("UniFace - Press 'q' to quit", frame)
@@ -186,11 +199,15 @@ faces = detector.detect(image)
 
 # Predict attributes
 for i, face in enumerate(faces):
-    gender, age = age_gender.predict(image, face['bbox'])
-    print(f"Face {i+1}: {gender}, {age} years old")
+    result = age_gender.predict(image, face.bbox)
+    print(f"Face {i+1}: {result.sex}, {result.age} years old")
+    # result.gender: 0=Female, 1=Male
+    # result.sex: "Female" or "Male"
+    # result.age: age in years
 ```
 
 **Output:**
+
 ```
 Face 1: Male, 32 years old
 Face 2: Female, 28 years old
@@ -198,6 +215,45 @@ Face 2: Female, 28 years old
 
 ---
 
+## 5b. FairFace Attributes (2 minutes)
+
+Detect race, gender, and age group with balanced demographics:
+
+```python
+import cv2
+from uniface import RetinaFace, FairFace
+
+# Initialize models
+detector = RetinaFace()
+fairface = FairFace()
+
+# Load image
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+# Predict attributes
+for i, face in enumerate(faces):
+    result = fairface.predict(image, face.bbox)
+    print(f"Face {i+1}: {result.sex}, {result.age_group}, {result.race}")
+    # result.gender: 0=Female, 1=Male
+    # result.sex: "Female" or "Male"
+    # result.age_group: "20-29", "30-39", etc.
+    # result.race: "East Asian", "White", etc.
+```
+
+**Output:**
+
+```
+Face 1: Male, 30-39, East Asian
+Face 2: Female, 20-29, White
+```
+
+**Race Categories:** White, Black, Latino Hispanic, East Asian, Southeast Asian, Indian, Middle Eastern
+
+**Age Groups:** 0-2, 3-9, 10-19, 20-29, 30-39, 40-49, 50-59, 60-69, 70+
+
+---
+
 ## 6. Facial Landmarks (2 minutes)
 
 Detect 106 facial landmarks:
@@ -215,7 +271,7 @@ image = cv2.imread("photo.jpg")
 faces = detector.detect(image)
 
 if faces:
-    landmarks = landmarker.get_landmarks(image, faces[0]['bbox'])
+    landmarks = landmarker.get_landmarks(image, faces[0].bbox)
     print(f"Detected {len(landmarks)} landmarks")
 
     # Draw landmarks
@@ -227,7 +283,223 @@ if faces:
 
 ---
 
-## 7. Batch Processing (3 minutes)
+## 7. Gaze Estimation (2 minutes)
+
+Estimate where a person is looking:
+
+```python
+import cv2
+import numpy as np
+from uniface import RetinaFace, MobileGaze
+from uniface.visualization import draw_gaze
+
+# Initialize models
+detector = RetinaFace()
+gaze_estimator = MobileGaze()
+
+# Load image
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+# Estimate gaze for each face
+for i, face in enumerate(faces):
+    x1, y1, x2, y2 = map(int, face.bbox[:4])
+    face_crop = image[y1:y2, x1:x2]
+
+    if face_crop.size > 0:
+        result = gaze_estimator.estimate(face_crop)
+        print(f"Face {i+1}: pitch={np.degrees(result.pitch):.1f}°, yaw={np.degrees(result.yaw):.1f}°")
+
+        # Draw gaze direction
+        draw_gaze(image, face.bbox, result.pitch, result.yaw)
+
+cv2.imwrite("gaze_output.jpg", image)
+```
+
+**Output:**
+
+```
+Face 1: pitch=5.2°, yaw=-12.3°
+Face 2: pitch=-8.1°, yaw=15.7°
+```
+
+---
+
+## 8. Face Parsing (2 minutes)
+
+Segment face into semantic components (skin, eyes, nose, mouth, hair, etc.):
+
+```python
+import cv2
+import numpy as np
+from uniface.parsing import BiSeNet
+from uniface.visualization import vis_parsing_maps
+
+# Initialize parser
+parser = BiSeNet()  # Uses ResNet18 by default
+
+# Load face image (already cropped)
+face_image = cv2.imread("face.jpg")
+
+# Parse face into 19 components
+mask = parser.parse(face_image)
+
+# Visualize with overlay
+face_rgb = cv2.cvtColor(face_image, cv2.COLOR_BGR2RGB)
+vis_result = vis_parsing_maps(face_rgb, mask, save_image=False)
+
+# Convert back to BGR for saving
+vis_bgr = cv2.cvtColor(vis_result, cv2.COLOR_RGB2BGR)
+cv2.imwrite("parsed_face.jpg", vis_bgr)
+
+print(f"Detected {len(np.unique(mask))} facial components")
+```
+
+**Output:**
+
+```
+Detected 12 facial components
+```
+
+**19 Facial Component Classes:**
+- Background, Skin, Eyebrows (L/R), Eyes (L/R), Eye Glasses
+- Ears (L/R), Ear Ring, Nose, Mouth, Lips (Upper/Lower)
+- Neck, Neck Lace, Cloth, Hair, Hat
+
+---
+
+## 9. Face Anonymization (2 minutes)
+
+Automatically blur faces for privacy protection:
+
+```python
+from uniface.privacy import anonymize_faces
+import cv2
+
+# One-liner: automatic detection and blurring
+image = cv2.imread("group_photo.jpg")
+anonymized = anonymize_faces(image, method='pixelate')
+cv2.imwrite("anonymized.jpg", anonymized)
+print("Faces anonymized successfully!")
+```
+
+**Manual control with custom parameters:**
+
+```python
+from uniface import RetinaFace
+from uniface.privacy import BlurFace
+
+# Initialize detector and blurrer
+detector = RetinaFace()
+blurrer = BlurFace(method='gaussian', blur_strength=5.0)
+
+# Detect and anonymize
+faces = detector.detect(image)
+anonymized = blurrer.anonymize(image, faces)
+cv2.imwrite("output.jpg", anonymized)
+```
+
+**Available blur methods:**
+
+```python
+# Pixelation (news media standard)
+blurrer = BlurFace(method='pixelate', pixel_blocks=8)
+
+# Gaussian blur (smooth, natural)
+blurrer = BlurFace(method='gaussian', blur_strength=4.0)
+
+# Black boxes (maximum privacy)
+blurrer = BlurFace(method='blackout', color=(0, 0, 0))
+
+# Elliptical blur (natural face shape)
+blurrer = BlurFace(method='elliptical', blur_strength=3.0, margin=30)
+
+# Median blur (edge-preserving)
+blurrer = BlurFace(method='median', blur_strength=3.0)
+```
+
+**Webcam anonymization:**
+
+```python
+import cv2
+from uniface import RetinaFace
+from uniface.privacy import BlurFace
+
+detector = RetinaFace()
+blurrer = BlurFace(method='pixelate')
+cap = cv2.VideoCapture(0)
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+    frame = blurrer.anonymize(frame, faces, inplace=True)
+
+    cv2.imshow('Anonymized', frame)
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+**Command-line tool:**
+
+```bash
+# Anonymize image with pixelation
+python tools/face_anonymize.py --source photo.jpg
+
+# Real-time webcam anonymization
+python tools/face_anonymize.py --source 0 --method gaussian
+
+# Custom blur strength
+python tools/face_anonymize.py --source photo.jpg --method gaussian --blur-strength 5.0
+```
+
+---
+
+## 10. Face Anti-Spoofing (2 minutes)
+
+Detect if a face is real or fake (photo, video replay, mask):
+
+```python
+from uniface import RetinaFace
+from uniface.spoofing import MiniFASNet
+
+detector = RetinaFace()
+spoofer = MiniFASNet()  # Uses V2 by default
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+for i, face in enumerate(faces):
+    result = spoofer.predict(image, face.bbox)
+    # result.is_real: True for real, False for fake
+    label = 'Real' if result.is_real else 'Fake'
+    print(f"Face {i+1}: {label} ({result.confidence:.1%})")
+```
+
+**Output:**
+
+```
+Face 1: Real (98.5%)
+```
+
+**Command-line tool:**
+
+```bash
+# Image
+python tools/spoofing.py --source photo.jpg
+
+# Webcam
+python tools/spoofing.py --source 0
+```
+
+---
+
+## 11. Batch Processing (3 minutes)
 
 Process multiple images:
 
@@ -260,20 +532,20 @@ print("Done!")
 
 ---
 
-## 8. Model Selection
+## 12. Model Selection
 
 Choose the right model for your use case:
 
 ### Detection Models
 
 ```python
-from uniface.detection import RetinaFace, SCRFD
-from uniface.constants import RetinaFaceWeights, SCRFDWeights
+from uniface.detection import RetinaFace, SCRFD, YOLOv5Face
+from uniface.constants import RetinaFaceWeights, SCRFDWeights, YOLOv5FaceWeights
 
 # Fast detection (mobile/edge devices)
 detector = RetinaFace(
     model_name=RetinaFaceWeights.MNET_025,
-    conf_thresh=0.7
+    confidence_threshold=0.7
 )
 
 # Balanced (recommended)
@@ -281,10 +553,17 @@ detector = RetinaFace(
     model_name=RetinaFaceWeights.MNET_V2
 )
 
+# Real-time with high accuracy
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5S,
+    confidence_threshold=0.6,
+    nms_thresh=0.5
+)
+
 # High accuracy (server/GPU)
 detector = SCRFD(
     model_name=SCRFDWeights.SCRFD_10G_KPS,
-    conf_thresh=0.5
+    confidence_threshold=0.5
 )
 ```
 
@@ -304,6 +583,35 @@ recognizer = MobileFace(model_name=MobileFaceWeights.MNET_V2)  # Fast, small siz
 recognizer = SphereFace(model_name=SphereFaceWeights.SPHERE20)  # Alternative method
 ```
 
+### Gaze Estimation Models
+
+```python
+from uniface import MobileGaze
+from uniface.constants import GazeWeights
+
+# Default (recommended)
+gaze_estimator = MobileGaze()  # Uses RESNET34
+
+# Lightweight (mobile/edge devices)
+gaze_estimator = MobileGaze(model_name=GazeWeights.MOBILEONE_S0)
+
+# High accuracy
+gaze_estimator = MobileGaze(model_name=GazeWeights.RESNET50)
+```
+
+### Face Parsing Models
+
+```python
+from uniface.parsing import BiSeNet
+from uniface.constants import ParsingWeights
+
+# Default (recommended, 50.7 MB)
+parser = BiSeNet()  # Uses RESNET18
+
+# Higher accuracy (89.2 MB)
+parser = BiSeNet(model_name=ParsingWeights.RESNET34)
+```
+
 ---
 
 ## Common Issues
@@ -354,7 +662,23 @@ from uniface import retinaface  # Module, not class
 
 ## Next Steps
 
-- **Detailed Examples**: Check the [examples/](examples/) folder for Jupyter notebooks
+### Jupyter Notebook Examples
+
+Explore interactive examples for common tasks:
+
+| Example | Description | Notebook |
+|---------|-------------|----------|
+| **Face Detection** | Detect faces and facial landmarks | [01_face_detection.ipynb](examples/01_face_detection.ipynb) |
+| **Face Alignment** | Align and crop faces for recognition | [02_face_alignment.ipynb](examples/02_face_alignment.ipynb) |
+| **Face Verification** | Compare two faces to verify identity | [03_face_verification.ipynb](examples/03_face_verification.ipynb) |
+| **Face Search** | Find a person in a group photo | [04_face_search.ipynb](examples/04_face_search.ipynb) |
+| **Face Analyzer** | All-in-one detection, recognition & attributes | [05_face_analyzer.ipynb](examples/05_face_analyzer.ipynb) |
+| **Face Parsing** | Segment face into semantic components | [06_face_parsing.ipynb](examples/06_face_parsing.ipynb) |
+| **Face Anonymization** | Blur or pixelate faces for privacy protection | [07_face_anonymization.ipynb](examples/07_face_anonymization.ipynb) |
+| **Gaze Estimation** | Estimate gaze direction | [08_gaze_estimation.ipynb](examples/08_gaze_estimation.ipynb) |
+
+### Additional Resources
+
 - **Model Benchmarks**: See [MODELS.md](MODELS.md) for performance comparisons
 - **Full Documentation**: Read [README.md](README.md) for complete API reference
 
@@ -363,10 +687,9 @@ from uniface import retinaface  # Module, not class
 ## References
 
 - **RetinaFace Training**: [yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch)
+- **YOLOv5-Face ONNX**: [yakhyo/yolov5-face-onnx-inference](https://github.com/yakhyo/yolov5-face-onnx-inference)
 - **Face Recognition Training**: [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition)
+- **Gaze Estimation Training**: [yakhyo/gaze-estimation](https://github.com/yakhyo/gaze-estimation)
+- **Face Parsing Training**: [yakhyo/face-parsing](https://github.com/yakhyo/face-parsing)
+- **FairFace**: [yakhyo/fairface-onnx](https://github.com/yakhyo/fairface-onnx) - Race, gender, age prediction
 - **InsightFace**: [deepinsight/insightface](https://github.com/deepinsight/insightface)
-
----
-
-Happy coding! 🚀
-

README.md

@@ -1,25 +1,34 @@
 # UniFace: All-in-One Face Analysis Library
 
+<div align="center">
+
 [![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
-![Python](https://img.shields.io/badge/Python-3.10%2B-blue)
-[![PyPI Version](https://img.shields.io/pypi/v/uniface.svg)](https://pypi.org/project/uniface/)
+[![Python](https://img.shields.io/badge/Python-3.11%2B-blue)](https://www.python.org/)
+[![PyPI](https://img.shields.io/pypi/v/uniface.svg)](https://pypi.org/project/uniface/)
 [![CI](https://github.com/yakhyo/uniface/actions/workflows/ci.yml/badge.svg)](https://github.com/yakhyo/uniface/actions)
-[![Downloads](https://pepy.tech/badge/uniface)](https://pepy.tech/project/uniface)
+[![Downloads](https://static.pepy.tech/badge/uniface)](https://pepy.tech/project/uniface)
+[![DeepWiki](https://img.shields.io/badge/DeepWiki-AI_Docs-blue.svg?logo=bookstack)](https://deepwiki.com/yakhyo/uniface)
+
+</div>
 
 <div align="center">
     <img src=".github/logos/logo_web.webp" width=75%>
 </div>
 
-**UniFace** is a lightweight, production-ready face analysis library built on ONNX Runtime. It provides high-performance face detection, recognition, landmark detection, and attribute analysis with hardware acceleration support across platforms.
+**UniFace** is a lightweight, production-ready face analysis library built on ONNX Runtime. It provides high-performance face detection, recognition, landmark detection, face parsing, gaze estimation, and attribute analysis with hardware acceleration support across platforms.
 
 ---
 
 ## Features
 
-- **High-Speed Face Detection**: ONNX-optimized RetinaFace and SCRFD models
+- **High-Speed Face Detection**: ONNX-optimized RetinaFace, SCRFD, and YOLOv5-Face models
 - **Facial Landmark Detection**: Accurate 106-point landmark localization
 - **Face Recognition**: ArcFace, MobileFace, and SphereFace embeddings
-- **Attribute Analysis**: Age, gender, and emotion detection
+- **Face Parsing**: BiSeNet-based semantic segmentation with 19 facial component classes
+- **Gaze Estimation**: Real-time gaze direction prediction with MobileGaze
+- **Attribute Analysis**: Age, gender, race (FairFace), and emotion detection
+- **Anti-Spoofing**: Face liveness detection with MiniFASNet models
+- **Face Anonymization**: Privacy-preserving face blurring with 5 methods (pixelate, gaussian, blackout, elliptical, median)
 - **Face Alignment**: Precise alignment for downstream tasks
 - **Hardware Acceleration**: ARM64 optimizations (Apple Silicon), CUDA (NVIDIA), CPU fallback
 - **Simple API**: Intuitive factory functions and clean interfaces
@@ -56,6 +65,7 @@ pip install uniface[gpu]
 ```
 
 **Requirements:**
+
 - CUDA 11.x or 12.x
 - cuDNN 8.x
 - See [ONNX Runtime GPU requirements](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html)
@@ -95,9 +105,9 @@ faces = detector.detect(image)
 
 # Process results
 for face in faces:
-    bbox = face['bbox']  # [x1, y1, x2, y2]
-    confidence = face['confidence']
-    landmarks = face['landmarks']  # 5-point landmarks
+    bbox = face.bbox  # np.ndarray [x1, y1, x2, y2]
+    confidence = face.confidence
+    landmarks = face.landmarks  # np.ndarray (5, 2) landmarks
     print(f"Face detected with confidence: {confidence:.2f}")
 ```
 
@@ -115,8 +125,8 @@ recognizer = ArcFace()
 faces1 = detector.detect(image1)
 faces2 = detector.detect(image2)
 
-embedding1 = recognizer.get_normalized_embedding(image1, faces1[0]['landmarks'])
-embedding2 = recognizer.get_normalized_embedding(image2, faces2[0]['landmarks'])
+embedding1 = recognizer.get_normalized_embedding(image1, faces1[0].landmarks)
+embedding2 = recognizer.get_normalized_embedding(image2, faces2[0].landmarks)
 
 # Compare faces
 similarity = compute_similarity(embedding1, embedding2)
@@ -132,7 +142,7 @@ detector = RetinaFace()
 landmarker = Landmark106()
 
 faces = detector.detect(image)
-landmarks = landmarker.get_landmarks(image, faces[0]['bbox'])
+landmarks = landmarker.get_landmarks(image, faces[0].bbox)
 # Returns 106 (x, y) landmark points
 ```
 
@@ -145,10 +155,145 @@ detector = RetinaFace()
 age_gender = AgeGender()
 
 faces = detector.detect(image)
-gender, age = age_gender.predict(image, faces[0]['bbox'])
-print(f"{gender}, {age} years old")
+result = age_gender.predict(image, faces[0].bbox)
+print(f"{result.sex}, {result.age} years old")
+# result.gender: 0=Female, 1=Male
+# result.sex: "Female" or "Male"
+# result.age: age in years
 ```
 
+### FairFace Attributes (Race, Gender, Age Group)
+
+```python
+from uniface import RetinaFace, FairFace
+
+detector = RetinaFace()
+fairface = FairFace()
+
+faces = detector.detect(image)
+result = fairface.predict(image, faces[0].bbox)
+print(f"{result.sex}, {result.age_group}, {result.race}")
+# result.gender: 0=Female, 1=Male
+# result.sex: "Female" or "Male"
+# result.age_group: "20-29", "30-39", etc.
+# result.race: "East Asian", "White", etc.
+```
+
+### Gaze Estimation
+
+```python
+from uniface import RetinaFace, MobileGaze
+from uniface.visualization import draw_gaze
+import numpy as np
+
+detector = RetinaFace()
+gaze_estimator = MobileGaze()
+
+faces = detector.detect(image)
+for face in faces:
+    x1, y1, x2, y2 = map(int, face.bbox[:4])
+    face_crop = image[y1:y2, x1:x2]
+
+    result = gaze_estimator.estimate(face_crop)
+    print(f"Gaze: pitch={np.degrees(result.pitch):.1f}°, yaw={np.degrees(result.yaw):.1f}°")
+
+    # Visualize
+    draw_gaze(image, face.bbox, result.pitch, result.yaw)
+```
+
+### Face Parsing
+
+```python
+from uniface.parsing import BiSeNet
+from uniface.visualization import vis_parsing_maps
+
+# Initialize parser
+parser = BiSeNet()  # Uses ResNet18 by default
+
+# Parse face image (already cropped)
+mask = parser.parse(face_image)
+
+# Visualize with overlay
+import cv2
+face_rgb = cv2.cvtColor(face_image, cv2.COLOR_BGR2RGB)
+vis_result = vis_parsing_maps(face_rgb, mask, save_image=False)
+
+# mask contains 19 classes: skin, eyes, nose, mouth, hair, etc.
+print(f"Unique classes: {len(np.unique(mask))}")
+```
+
+### Face Anti-Spoofing
+
+Detect if a face is real or fake (photo, video replay, mask):
+
+```python
+from uniface import RetinaFace
+from uniface.spoofing import MiniFASNet
+
+detector = RetinaFace()
+spoofer = MiniFASNet()  # Uses V2 by default
+
+faces = detector.detect(image)
+for face in faces:
+    result = spoofer.predict(image, face.bbox)
+    # result.is_real: True for real, False for fake
+    # result.confidence: confidence score
+    label = 'Real' if result.is_real else 'Fake'
+    print(f"{label}: {result.confidence:.1%}")
+```
+
+### Face Anonymization
+
+Protect privacy by blurring or pixelating faces with 5 different methods:
+
+```python
+from uniface import RetinaFace
+from uniface.privacy import BlurFace, anonymize_faces
+import cv2
+
+# Method 1: One-liner with automatic detection
+image = cv2.imread("photo.jpg")
+anonymized = anonymize_faces(image, method='pixelate')
+cv2.imwrite("anonymized.jpg", anonymized)
+
+# Method 2: Manual control with custom parameters
+detector = RetinaFace()
+blurrer = BlurFace(method='gaussian', blur_strength=5.0)
+
+faces = detector.detect(image)
+anonymized = blurrer.anonymize(image, faces)
+
+# Available blur methods:
+methods = {
+    'pixelate': BlurFace(method='pixelate', pixel_blocks=10),      # Blocky effect (news media standard)
+    'gaussian': BlurFace(method='gaussian', blur_strength=3.0),    # Smooth, natural blur
+    'blackout': BlurFace(method='blackout', color=(0, 0, 0)),      # Solid color boxes (maximum privacy)
+    'elliptical': BlurFace(method='elliptical', margin=20),        # Soft oval blur (natural face shape)
+    'median': BlurFace(method='median', blur_strength=3.0)         # Edge-preserving blur
+}
+
+# Real-time webcam anonymization
+cap = cv2.VideoCapture(0)
+detector = RetinaFace()
+blurrer = BlurFace(method='pixelate')
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+    frame = blurrer.anonymize(frame, faces, inplace=True)
+
+    cv2.imshow('Anonymized', frame)
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+
 ---
 
 ## Documentation
@@ -167,16 +312,20 @@ print(f"{gender}, {age} years old")
 from uniface.detection import RetinaFace, SCRFD
 from uniface.recognition import ArcFace
 from uniface.landmark import Landmark106
+from uniface.privacy import BlurFace, anonymize_faces
+
+from uniface.constants import SCRFDWeights
 
 # Create detector with default settings
 detector = RetinaFace()
 
 # Create with custom config
 detector = SCRFD(
-    model_name='scrfd_10g_kps',
-    conf_thresh=0.8,
+    model_name=SCRFDWeights.SCRFD_10G_KPS, # SCRFDWeights.SCRFD_500M_KPS
+    confidence_threshold=0.4,
     input_size=(640, 640)
 )
+# Or with defaults settings: detector = SCRFD()
 
 # Recognition and landmarks
 recognizer = ArcFace()
@@ -186,15 +335,24 @@ landmarker = Landmark106()
 ### Direct Model Instantiation
 
 ```python
-from uniface import RetinaFace, SCRFD, ArcFace, MobileFace, SphereFace
-from uniface.constants import RetinaFaceWeights
+from uniface import RetinaFace, SCRFD, YOLOv5Face, ArcFace, MobileFace, SphereFace
+from uniface.constants import RetinaFaceWeights, YOLOv5FaceWeights
 
 # Detection
 detector = RetinaFace(
     model_name=RetinaFaceWeights.MNET_V2,
-    conf_thresh=0.5,
-    nms_thresh=0.4
+    confidence_threshold=0.5,
+    nms_threshold=0.4
 )
+# Or detector = RetinaFace()
+
+# YOLOv5-Face detection
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5S,
+    confidence_threshold=0.6,
+    nms_threshold=0.5
+)
+# Or detector = YOLOv5Face
 
 # Recognition
 recognizer = ArcFace()  # Uses default weights
@@ -208,28 +366,77 @@ recognizer = SphereFace()  # Angular softmax alternative
 from uniface import detect_faces
 
 # One-line face detection
-faces = detect_faces(image, method='retinaface', conf_thresh=0.8)
+faces = detect_faces(image, method='retinaface', confidence_threshold=0.8)  # methods: retinaface, scrfd, yolov5face
 ```
 
+### Key Parameters (quick reference)
+
+**Detection**
+
+| Class          | Key params (defaults)                                                                                                                | Notes                                          |
+| -------------- | ------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------- |
+| `RetinaFace` | `model_name=RetinaFaceWeights.MNET_V2`, `confidence_threshold=0.5`, `nms_threshold=0.4`, `input_size=(640, 640)`, `dynamic_size=False` | Supports 5-point landmarks                     |
+| `SCRFD`      | `model_name=SCRFDWeights.SCRFD_10G_KPS`, `confidence_threshold=0.5`, `nms_threshold=0.4`, `input_size=(640, 640)`                        | Supports 5-point landmarks                     |
+| `YOLOv5Face` | `model_name=YOLOv5FaceWeights.YOLOV5S`, `confidence_threshold=0.6`, `nms_threshold=0.5`, `input_size=640` (fixed)                        | Supports 5-point landmarks; models: YOLOV5N/S/M; `input_size` must be 640 |
+
+**Recognition**
+
+| Class          | Key params (defaults)                     | Notes                                 |
+| -------------- | ----------------------------------------- | ------------------------------------- |
+| `ArcFace`    | `model_name=ArcFaceWeights.MNET`        | Returns 512-dim normalized embeddings |
+| `MobileFace` | `model_name=MobileFaceWeights.MNET_V2`  | Lightweight embeddings                |
+| `SphereFace` | `model_name=SphereFaceWeights.SPHERE20` | Angular softmax variant               |
+
+**Landmark & Attributes**
+
+| Class           | Key params (defaults)                                                 | Notes                                   |
+| --------------- | --------------------------------------------------------------------- | --------------------------------------- |
+| `Landmark106` | No required params                                                    | 106-point landmarks                     |
+| `AgeGender`   | `model_name=AgeGenderWeights.DEFAULT`; `input_size` auto-detected | Returns `AttributeResult` with gender, age |
+| `FairFace`    | `model_name=FairFaceWeights.DEFAULT`, `input_size=(224, 224)`     | Returns `AttributeResult` with gender, age_group, race |
+| `Emotion`     | `model_weights=DDAMFNWeights.AFFECNET7`, `input_size=(112, 112)`  | Requires 5-point landmarks; TorchScript |
+
+**Gaze Estimation**
+
+| Class         | Key params (defaults)                      | Notes                                |
+| ------------- | ------------------------------------------ | ------------------------------------ |
+| `MobileGaze` | `model_name=GazeWeights.RESNET34`       | Returns `GazeResult(pitch, yaw)` in radians; trained on Gaze360 |
+
+**Face Parsing**
+
+| Class      | Key params (defaults)                    | Notes                                |
+| ---------- | ---------------------------------------- | ------------------------------------ |
+| `BiSeNet` | `model_name=ParsingWeights.RESNET18`, `input_size=(512, 512)` | 19 facial component classes; BiSeNet architecture with ResNet backbone |
+
+**Anti-Spoofing**
+
+| Class         | Key params (defaults)                     | Notes                                |
+| ------------- | ----------------------------------------- | ------------------------------------ |
+| `MiniFASNet` | `model_name=MiniFASNetWeights.V2`       | Returns `SpoofingResult(is_real, confidence)` |
+
 ---
 
 ## Model Performance
 
 ### Face Detection (WIDER FACE Dataset)
 
-| Model              | Easy   | Medium | Hard   | Use Case                |
-|--------------------|--------|--------|--------|-------------------------|
-| retinaface_mnet025 | 88.48% | 87.02% | 80.61% | Mobile/Edge devices     |
-| retinaface_mnet_v2 | 91.70% | 91.03% | 86.60% | Balanced (recommended)  |
-| retinaface_r34     | 94.16% | 93.12% | 88.90% | High accuracy           |
-| scrfd_500m         | 90.57% | 88.12% | 68.51% | Real-time applications  |
-| scrfd_10g          | 95.16% | 93.87% | 83.05% | Best accuracy/speed     |
+| Model              | Easy   | Medium | Hard   | Use Case               |
+| ------------------ | ------ | ------ | ------ | ---------------------- |
+| retinaface_mnet025 | 88.48% | 87.02% | 80.61% | Mobile/Edge devices    |
+| retinaface_mnet_v2 | 91.70% | 91.03% | 86.60% | Balanced (recommended) |
+| retinaface_r34     | 94.16% | 93.12% | 88.90% | High accuracy          |
+| scrfd_500m         | 90.57% | 88.12% | 68.51% | Real-time applications |
+| scrfd_10g          | 95.16% | 93.87% | 83.05% | Best accuracy/speed    |
+| yolov5n_face       | 93.61% | 91.52% | 80.53% | Lightweight/Mobile     |
+| yolov5s_face       | 94.33% | 92.61% | 83.15% | Real-time + accuracy   |
+| yolov5m_face       | 95.30% | 93.76% | 85.28% | High accuracy          |
 
-*Accuracy values from original papers: [RetinaFace](https://arxiv.org/abs/1905.00641), [SCRFD](https://arxiv.org/abs/2105.04714)*
+_Accuracy values from original papers: [RetinaFace](https://arxiv.org/abs/1905.00641), [SCRFD](https://arxiv.org/abs/2105.04714), [YOLOv5-Face](https://arxiv.org/abs/2105.12931)_
 
 **Benchmark on your hardware:**
+
 ```bash
-python scripts/run_detection.py --image assets/test.jpg --iterations 100
+python tools/detection.py --source assets/test.jpg --iterations 100
 ```
 
 See [MODELS.md](MODELS.md) for detailed model information and selection guide.
@@ -242,6 +449,21 @@ See [MODELS.md](MODELS.md) for detailed model information and selection guide.
 
 ## Examples
 
+### Jupyter Notebooks
+
+Interactive examples covering common face analysis tasks:
+
+| Example | Description | Notebook |
+|---------|-------------|----------|
+| **Face Detection** | Detect faces and facial landmarks | [01_face_detection.ipynb](examples/01_face_detection.ipynb) |
+| **Face Alignment** | Align and crop faces for recognition | [02_face_alignment.ipynb](examples/02_face_alignment.ipynb) |
+| **Face Verification** | Compare two faces to verify identity | [03_face_verification.ipynb](examples/03_face_verification.ipynb) |
+| **Face Search** | Find a person in a group photo | [04_face_search.ipynb](examples/04_face_search.ipynb) |
+| **Face Analyzer** | All-in-one detection, recognition & attributes | [05_face_analyzer.ipynb](examples/05_face_analyzer.ipynb) |
+| **Face Parsing** | Segment face into semantic components | [06_face_parsing.ipynb](examples/06_face_parsing.ipynb) |
+| **Face Anonymization** | Blur or pixelate faces for privacy protection | [07_face_anonymization.ipynb](examples/07_face_anonymization.ipynb) |
+| **Gaze Estimation** | Estimate gaze direction from face images | [08_gaze_estimation.ipynb](examples/08_gaze_estimation.ipynb) |
+
 ### Webcam Face Detection
 
 ```python
@@ -260,11 +482,17 @@ while True:
     faces = detector.detect(frame)
 
     # Extract data for visualization
-    bboxes = [f['bbox'] for f in faces]
-    scores = [f['confidence'] for f in faces]
-    landmarks = [f['landmarks'] for f in faces]
+    bboxes = [f.bbox for f in faces]
+    scores = [f.confidence for f in faces]
+    landmarks = [f.landmarks for f in faces]
 
-    draw_detections(frame, bboxes, scores, landmarks, vis_threshold=0.6)
+    draw_detections(
+        image=frame,
+        bboxes=bboxes,
+        scores=scores,
+        landmarks=landmarks,
+        vis_threshold=0.6,
+    )
 
     cv2.imshow("Face Detection", frame)
     if cv2.waitKey(1) & 0xFF == ord('q'):
@@ -290,7 +518,7 @@ for person_id, image_path in person_images.items():
     faces = detector.detect(image)
     if faces:
         embedding = recognizer.get_normalized_embedding(
-            image, faces[0]['landmarks']
+            image, faces[0].landmarks
         )
         database[person_id] = embedding
 
@@ -299,7 +527,7 @@ query_image = cv2.imread("query.jpg")
 query_faces = detector.detect(query_image)
 if query_faces:
     query_embedding = recognizer.get_normalized_embedding(
-        query_image, query_faces[0]['landmarks']
+        query_image, query_faces[0].landmarks
     )
 
     # Find best match
@@ -394,12 +622,29 @@ pip install -e ".[dev]"
 
 # Run tests
 pytest
-
-# Format code
-black uniface/
-isort uniface/
 ```
 
+### Code Formatting
+
+This project uses [Ruff](https://docs.astral.sh/ruff/) for linting and formatting.
+
+```bash
+# Format code
+ruff format .
+
+# Check for linting errors
+ruff check .
+
+# Auto-fix linting errors
+ruff check . --fix
+```
+
+Ruff configuration is in `pyproject.toml`. Key settings:
+
+- Line length: 120
+- Python target: 3.10+
+- Import sorting: `uniface` as first-party
+
 ### Project Structure
 
 ```
@@ -408,34 +653,32 @@ uniface/
 │   ├── detection/       # Face detection models
 │   ├── recognition/     # Face recognition models
 │   ├── landmark/        # Landmark detection
+│   ├── parsing/         # Face parsing
+│   ├── gaze/            # Gaze estimation
 │   ├── attribute/       # Age, gender, emotion
+│   ├── spoofing/        # Face anti-spoofing
+│   ├── privacy/         # Face anonymization & blurring
 │   ├── onnx_utils.py    # ONNX Runtime utilities
 │   ├── model_store.py   # Model download & caching
 │   └── visualization.py # Drawing utilities
 ├── tests/               # Unit tests
 ├── examples/            # Example notebooks
-└── scripts/             # Utility scripts
+└── tools/               # CLI utilities
 ```
 
 ---
 
 ## References
 
-### Model Training & Architectures
-
 - **RetinaFace Training**: [yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch) - PyTorch implementation and training code
+- **YOLOv5-Face ONNX**: [yakhyo/yolov5-face-onnx-inference](https://github.com/yakhyo/yolov5-face-onnx-inference) - ONNX inference implementation
 - **Face Recognition Training**: [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition) - ArcFace, MobileFace, SphereFace training code
+- **Face Parsing Training**: [yakhyo/face-parsing](https://github.com/yakhyo/face-parsing) - BiSeNet face parsing training code and pretrained weights
+- **Gaze Estimation Training**: [yakhyo/gaze-estimation](https://github.com/yakhyo/gaze-estimation) - MobileGaze training code and pretrained weights
+- **Face Anti-Spoofing**: [yakhyo/face-anti-spoofing](https://github.com/yakhyo/face-anti-spoofing) - MiniFASNet ONNX inference (weights from [minivision-ai/Silent-Face-Anti-Spoofing](https://github.com/minivision-ai/Silent-Face-Anti-Spoofing))
+- **FairFace**: [yakhyo/fairface-onnx](https://github.com/yakhyo/fairface-onnx) - FairFace ONNX inference for race, gender, age prediction
 - **InsightFace**: [deepinsight/insightface](https://github.com/deepinsight/insightface) - Model architectures and pretrained weights
 
-### Papers
-
-- **RetinaFace**: [Single-Shot Multi-Level Face Localisation in the Wild](https://arxiv.org/abs/1905.00641)
-- **SCRFD**: [Sample and Computation Redistribution for Efficient Face Detection](https://arxiv.org/abs/2105.04714)
-- **ArcFace**: [Additive Angular Margin Loss for Deep Face Recognition](https://arxiv.org/abs/1801.07698)
-
----
-
 ## Contributing
 
 Contributions are welcome! Please open an issue or submit a pull request on [GitHub](https://github.com/yakhyo/uniface).
-

pyproject.toml

@@ -1,12 +1,44 @@
 [project]
 name = "uniface"
-version = "1.1.0"
-description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Age, and Gender Detection"
+version = "2.0.0"
+description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Face Parsing, Gaze Estimation, Age, and Gender Detection"
 readme = "README.md"
 license = { text = "MIT" }
-authors = [
-    { name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" }
+authors = [{ name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" }]
+maintainers = [
+    { name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" },
 ]
+
+requires-python = ">=3.11,<3.14"
+keywords = [
+    "face-detection",
+    "face-recognition",
+    "facial-landmarks",
+    "face-parsing",
+    "face-segmentation",
+    "gaze-estimation",
+    "age-detection",
+    "gender-detection",
+    "computer-vision",
+    "deep-learning",
+    "onnx",
+    "onnxruntime",
+    "face-analysis",
+    "bisenet",
+]
+
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+]
+
 dependencies = [
     "numpy>=1.21.0",
     "opencv-python>=4.5.0",
@@ -14,24 +46,103 @@ dependencies = [
     "onnxruntime>=1.16.0",
     "scikit-image>=0.19.0",
     "requests>=2.28.0",
-    "tqdm>=4.64.0"
+    "tqdm>=4.64.0",
 ]
-requires-python = ">=3.10"
 
 [project.optional-dependencies]
-dev = ["pytest>=7.0.0"]
+dev = ["pytest>=7.0.0", "ruff>=0.4.0"]
 gpu = ["onnxruntime-gpu>=1.16.0"]
 
 [project.urls]
 Homepage = "https://github.com/yakhyo/uniface"
 Repository = "https://github.com/yakhyo/uniface"
+Documentation = "https://github.com/yakhyo/uniface/blob/main/README.md"
+"Quick Start" = "https://github.com/yakhyo/uniface/blob/main/QUICKSTART.md"
+"Model Zoo" = "https://github.com/yakhyo/uniface/blob/main/MODELS.md"
 
 [build-system]
 requires = ["setuptools>=64", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [tool.setuptools]
-packages = { find = {} }
+packages = { find = { where = ["."], include = ["uniface*"] } }
 
 [tool.setuptools.package-data]
-"uniface" = ["*.txt", "*.md"]
+uniface = ["py.typed"]
+
+[tool.ruff]
+line-length = 120
+target-version = "py311"
+exclude = [
+    ".git",
+    ".ruff_cache",
+    "__pycache__",
+    "build",
+    "dist",
+    "*.egg-info",
+    ".venv",
+    "venv",
+    ".pytest_cache",
+    ".mypy_cache",
+    "*.ipynb",
+]
+
+[tool.ruff.format]
+quote-style = "single"
+docstring-code-format = true
+
+[tool.ruff.lint]
+select = [
+    "E",      # pycodestyle errors
+    "F",      # pyflakes
+    "I",      # isort
+    "W",      # pycodestyle warnings
+    "UP",     # pyupgrade (modern Python syntax)
+    "B",      # flake8-bugbear
+    "C4",     # flake8-comprehensions
+    "SIM",    # flake8-simplify
+    "RUF",    # Ruff-specific rules
+]
+ignore = [
+    "E501",   # Line too long (handled by formatter)
+    "B008",   # Function call in default argument (common in FastAPI/Click)
+    "SIM108", # Use ternary operator (can reduce readability)
+    "RUF022", # Allow logical grouping in __all__ instead of alphabetical sorting
+]
+
+[tool.ruff.lint.flake8-quotes]
+docstring-quotes = "double"
+
+[tool.ruff.lint.isort]
+force-single-line = false
+force-sort-within-sections = true
+known-first-party = ["uniface"]
+section-order = [
+    "future",
+    "standard-library",
+    "third-party",
+    "first-party",
+    "local-folder",
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.mypy]
+python_version = "3.11"
+warn_return_any = false
+warn_unused_ignores = true
+ignore_missing_imports = true
+exclude = ["tests/", "scripts/", "examples/"]
+# Disable strict return type checking for numpy operations
+disable_error_code = ["no-any-return"]
+
+[tool.bandit]
+exclude_dirs = ["tests", "scripts", "examples"]
+skips = ["B101", "B614"]  # B101: assert, B614: torch.jit.load (models are SHA256 verified)
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+python_functions = ["test_*"]
+addopts = "-v --tb=short"

scripts/README.md

@@ -1,97 +0,0 @@
-# Scripts
-
-Collection of example scripts demonstrating UniFace functionality.
-
-## Available Scripts
-
-- `run_detection.py` - Face detection on images
-- `run_age_gender.py` - Age and gender prediction
-- `run_landmarks.py` - Facial landmark detection
-- `run_recognition.py` - Face recognition and embeddings
-- `run_face_search.py` - Face search and matching
-- `run_video_detection.py` - Video processing with face detection
-- `batch_process.py` - Batch processing of image folders
-- `download_model.py` - Download and manage models
-
-## Quick Start
-
-```bash
-# Face detection
-python scripts/run_detection.py --image assets/test.jpg
-
-# Age and gender detection
-python scripts/run_age_gender.py --image assets/test.jpg
-
-# Webcam demo
-python scripts/run_age_gender.py --webcam
-
-# Batch processing
-python scripts/batch_process.py --input images/ --output results/
-```
-
-## Import Examples
-
-The scripts use direct class imports for better developer experience:
-
-```python
-# Face Detection
-from uniface.detection import RetinaFace, SCRFD
-
-detector = RetinaFace()  # or SCRFD()
-faces = detector.detect(image)
-
-# Face Recognition
-from uniface.recognition import ArcFace, MobileFace, SphereFace
-
-recognizer = ArcFace()  # or MobileFace(), SphereFace()
-embedding = recognizer.get_embedding(image, landmarks)
-
-# Age & Gender
-from uniface.attribute import AgeGender
-
-age_gender = AgeGender()
-gender, age = age_gender.predict(image, bbox)
-
-# Landmarks
-from uniface.landmark import Landmark106
-
-landmarker = Landmark106()
-landmarks = landmarker.get_landmarks(image, bbox)
-```
-
-## Available Classes
-
-**Detection:**
-- `RetinaFace` - High accuracy face detection
-- `SCRFD` - Fast face detection
-
-**Recognition:**
-- `ArcFace` - High accuracy face recognition
-- `MobileFace` - Lightweight face recognition
-- `SphereFace` - Alternative face recognition
-
-**Attributes:**
-- `AgeGender` - Age and gender prediction
-
-**Landmarks:**
-- `Landmark106` - 106-point facial landmarks
-
-## Common Options
-
-Most scripts support:
-- `--help` - Show usage information
-- `--verbose` - Enable detailed logging
-- `--detector` - Choose detector (retinaface, scrfd)
-- `--threshold` - Set confidence threshold
-
-## Testing
-
-Run basic functionality test:
-```bash
-python scripts/run_detection.py --image assets/test.jpg
-```
-
-For comprehensive testing, see the main project tests:
-```bash
-pytest tests/
-```

scripts/batch_process.py

@@ -1,157 +0,0 @@
-"""Batch Image Processing Script"""
-
-import os
-import cv2
-import argparse
-from pathlib import Path
-from tqdm import tqdm
-
-from uniface import RetinaFace, SCRFD
-from uniface.visualization import draw_detections
-
-
-def get_image_files(input_dir: Path, extensions: tuple) -> list:
-    image_files = []
-    for ext in extensions:
-        image_files.extend(input_dir.glob(f"*.{ext}"))
-        image_files.extend(input_dir.glob(f"*.{ext.upper()}"))
-
-    return sorted(image_files)
-
-
-def process_single_image(detector, image_path: Path, output_dir: Path,
-                        vis_threshold: float, skip_existing: bool) -> dict:
-    output_path = output_dir / f"{image_path.stem}_detected{image_path.suffix}"
-
-    # Skip if already processed
-    if skip_existing and output_path.exists():
-        return {"status": "skipped", "faces": 0}
-
-    # Load image
-    image = cv2.imread(str(image_path))
-    if image is None:
-        return {"status": "error", "error": "Failed to load image"}
-
-    # Detect faces
-    try:
-        faces = detector.detect(image)
-    except Exception as e:
-        return {"status": "error", "error": str(e)}
-
-    # Draw detections
-    bboxes = [f['bbox'] for f in faces]
-    scores = [f['confidence'] for f in faces]
-    landmarks = [f['landmarks'] for f in faces]
-    draw_detections(image, bboxes, scores, landmarks, vis_threshold=vis_threshold)
-
-    # Add face count
-    cv2.putText(image, f"Faces: {len(faces)}", (10, 30),
-               cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-
-    # Save result
-    cv2.imwrite(str(output_path), image)
-
-    return {"status": "success", "faces": len(faces)}
-
-
-def batch_process(detector, input_dir: str, output_dir: str, extensions: tuple,
-                 vis_threshold: float, skip_existing: bool):
-    input_path = Path(input_dir)
-    output_path = Path(output_dir)
-
-    # Create output directory
-    output_path.mkdir(parents=True, exist_ok=True)
-
-    # Get image files
-    image_files = get_image_files(input_path, extensions)
-
-    if not image_files:
-        print(f"No image files found in '{input_dir}' with extensions {extensions}")
-        return
-
-    print(f"Input: {input_dir}")
-    print(f"Output: {output_dir}")
-    print(f"Found {len(image_files)} images\n")
-
-    # Process images
-    results = {
-        "success": 0,
-        "skipped": 0,
-        "error": 0,
-        "total_faces": 0
-    }
-
-    with tqdm(image_files, desc="Processing images", unit="img") as pbar:
-        for image_path in pbar:
-            result = process_single_image(
-                detector, image_path, output_path,
-                vis_threshold, skip_existing
-            )
-
-            if result["status"] == "success":
-                results["success"] += 1
-                results["total_faces"] += result["faces"]
-                pbar.set_postfix({"faces": result["faces"]})
-            elif result["status"] == "skipped":
-                results["skipped"] += 1
-            else:
-                results["error"] += 1
-                print(f"\nError processing {image_path.name}: {result.get('error', 'Unknown error')}")
-
-    # Print summary
-    print(f"\nBatch processing complete!")
-    print(f"   Total images: {len(image_files)}")
-    print(f"   Successfully processed: {results['success']}")
-    print(f"   Skipped: {results['skipped']}")
-    print(f"   Errors: {results['error']}")
-    print(f"   Total faces detected: {results['total_faces']}")
-    if results['success'] > 0:
-        print(f"   Average faces per image: {results['total_faces']/results['success']:.2f}")
-    print(f"\nResults saved to: {output_dir}")
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Batch process images with face detection")
-    parser.add_argument("--input", type=str, required=True,
-                       help="Input directory containing images")
-    parser.add_argument("--output", type=str, required=True,
-                       help="Output directory for processed images")
-    parser.add_argument("--detector", type=str, default="retinaface",
-                       choices=['retinaface', 'scrfd'], help="Face detector to use")
-    parser.add_argument("--threshold", type=float, default=0.6,
-                       help="Confidence threshold for visualization")
-    parser.add_argument("--extensions", type=str, default="jpg,jpeg,png,bmp",
-                       help="Comma-separated list of image extensions")
-    parser.add_argument("--skip_existing", action="store_true",
-                       help="Skip files that already exist in output directory")
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-
-    args = parser.parse_args()
-
-    # Check input directory exists
-    if not Path(args.input).exists():
-        print(f"Error: Input directory '{args.input}' does not exist")
-        return
-
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
-
-    # Parse extensions
-    extensions = tuple(ext.strip() for ext in args.extensions.split(','))
-
-    # Initialize detector
-    print(f"Initializing detector: {args.detector}")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-    print("Detector initialized\n")
-
-    # Process batch
-    batch_process(detector, args.input, args.output, extensions,
-                 args.threshold, args.skip_existing)
-
-
-if __name__ == "__main__":
-    main()

scripts/download_model.py

@@ -1,77 +0,0 @@
-import argparse
-from uniface.constants import (
-    RetinaFaceWeights, SphereFaceWeights, MobileFaceWeights, ArcFaceWeights,
-    SCRFDWeights, DDAMFNWeights, AgeGenderWeights, LandmarkWeights
-)
-from uniface.model_store import verify_model_weights
-
-
-# All available model types
-ALL_MODEL_TYPES = {
-    'retinaface': RetinaFaceWeights,
-    'sphereface': SphereFaceWeights,
-    'mobileface': MobileFaceWeights,
-    'arcface': ArcFaceWeights,
-    'scrfd': SCRFDWeights,
-    'ddamfn': DDAMFNWeights,
-    'agegender': AgeGenderWeights,
-    'landmark': LandmarkWeights,
-}
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Download and verify model weights.")
-    parser.add_argument(
-        "--model-type",
-        type=str,
-        choices=list(ALL_MODEL_TYPES.keys()),
-        help="Model type to download (e.g. retinaface, arcface). If not specified, all models will be downloaded.",
-    )
-    parser.add_argument(
-        "--model",
-        type=str,
-        help="Specific model to download (e.g. MNET_V2). For RetinaFace backward compatibility.",
-    )
-    args = parser.parse_args()
-
-    if args.model and not args.model_type:
-        # Backward compatibility - assume RetinaFace
-        try:
-            weight = RetinaFaceWeights[args.model]
-            print(f"Downloading RetinaFace model: {weight.value}")
-            verify_model_weights(weight)
-            print("Model downloaded successfully.")
-        except KeyError:
-            print(f"Invalid RetinaFace model: {args.model}")
-            print(f"Available models: {[m.name for m in RetinaFaceWeights]}")
-        return
-
-    if args.model_type:
-        # Download all models from specific type
-        model_enum = ALL_MODEL_TYPES[args.model_type]
-        print(f"Downloading all {args.model_type} models...")
-        for weight in model_enum:
-            print(f"Downloading: {weight.value}")
-            try:
-                verify_model_weights(weight)
-                print(f"Downloaded: {weight.value}")
-            except Exception as e:
-                print(f"Failed to download {weight.value}: {e}")
-    else:
-        # Download all models from all types
-        print("Downloading all models...")
-        for model_type, model_enum in ALL_MODEL_TYPES.items():
-            print(f"\nDownloading {model_type} models...")
-            for weight in model_enum:
-                print(f"Downloading: {weight.value}")
-                try:
-                    verify_model_weights(weight)
-                    print(f"Downloaded: {weight.value}")
-                except Exception as e:
-                    print(f"Failed to download {weight.value}: {e}")
-
-    print("\nDownload process completed.")
-
-
-if __name__ == "__main__":
-    main()

scripts/run_age_gender.py

@@ -1,163 +0,0 @@
-"""Age and Gender Detection Demo Script"""
-
-import os
-import cv2
-import argparse
-from pathlib import Path
-
-from uniface import RetinaFace, SCRFD, AgeGender
-from uniface.visualization import draw_detections
-
-
-def process_image(detector, age_gender, image_path: str, save_dir: str = "outputs", vis_threshold: float = 0.6):
-    image = cv2.imread(image_path)
-    if image is None:
-        print(f"Error: Failed to load image from '{image_path}'")
-        return
-
-    print(f"Processing: {image_path}")
-
-    # Detect faces
-    faces = detector.detect(image)
-    print(f"  Detected {len(faces)} face(s)")
-
-    if not faces:
-        print("  No faces detected")
-        return
-
-    # Draw detections
-    bboxes = [f['bbox'] for f in faces]
-    scores = [f['confidence'] for f in faces]
-    landmarks = [f['landmarks'] for f in faces]
-    draw_detections(image, bboxes, scores, landmarks, vis_threshold=vis_threshold)
-
-    # Predict and draw age/gender for each face
-    for i, face in enumerate(faces):
-        gender, age = age_gender.predict(image, face['bbox'])
-        print(f"  Face {i+1}: {gender}, {age} years old")
-
-        # Draw age and gender text
-        bbox = face['bbox']
-        x1, y1 = int(bbox[0]), int(bbox[1])
-        text = f"{gender}, {age}y"
-
-        # Background rectangle for text
-        (text_width, text_height), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
-        cv2.rectangle(image, (x1, y1 - text_height - 10),
-                    (x1 + text_width + 10, y1), (0, 255, 0), -1)
-        cv2.putText(image, text, (x1 + 5, y1 - 5),
-                   cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)
-
-    # Save result
-    os.makedirs(save_dir, exist_ok=True)
-    output_path = os.path.join(save_dir, f"{Path(image_path).stem}_age_gender.jpg")
-    cv2.imwrite(output_path, image)
-    print(f"Output saved: {output_path}")
-
-
-def run_webcam(detector, age_gender, vis_threshold: float = 0.6):
-    cap = cv2.VideoCapture(0)
-
-    if not cap.isOpened():
-        print("Cannot open webcam")
-        return
-
-    print("Webcam opened")
-    print("Press 'q' to quit\n")
-
-    frame_count = 0
-
-    try:
-        while True:
-            ret, frame = cap.read()
-            if not ret:
-                break
-
-            frame_count += 1
-
-            # Detect faces
-            faces = detector.detect(frame)
-
-            # Draw detections
-            bboxes = [f['bbox'] for f in faces]
-            scores = [f['confidence'] for f in faces]
-            landmarks = [f['landmarks'] for f in faces]
-            draw_detections(frame, bboxes, scores, landmarks, vis_threshold=vis_threshold)
-
-            # Predict and draw age/gender for each face
-            for face in faces:
-                gender, age = age_gender.predict(frame, face['bbox'])
-
-                # Draw age and gender text
-                bbox = face['bbox']
-                x1, y1 = int(bbox[0]), int(bbox[1])
-                text = f"{gender}, {age}y"
-
-                # Background rectangle for text
-                (text_width, text_height), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
-                cv2.rectangle(frame, (x1, y1 - text_height - 10),
-                            (x1 + text_width + 10, y1), (0, 255, 0), -1)
-                cv2.putText(frame, text, (x1 + 5, y1 - 5),
-                           cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)
-
-            # Add info
-            cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
-                       cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-            cv2.putText(frame, "Press 'q' to quit", (10, frame.shape[0] - 10),
-                       cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1)
-
-            cv2.imshow("Age & Gender Detection", frame)
-
-            if cv2.waitKey(1) & 0xFF == ord('q'):
-                break
-
-    except KeyboardInterrupt:
-        print("\nInterrupted")
-    finally:
-        cap.release()
-        cv2.destroyAllWindows()
-        print(f"\nProcessed {frame_count} frames")
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Run age and gender detection")
-    parser.add_argument("--image", type=str, help="Path to input image")
-    parser.add_argument("--webcam", action="store_true", help="Use webcam instead of image")
-    parser.add_argument("--detector", type=str, default="retinaface",
-                       choices=['retinaface', 'scrfd'], help="Face detector to use")
-    parser.add_argument("--threshold", type=float, default=0.6,
-                       help="Confidence threshold for visualization")
-    parser.add_argument("--save_dir", type=str, default="outputs",
-                       help="Directory to save output images")
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-
-    args = parser.parse_args()
-
-    # Validate input
-    if not args.image and not args.webcam:
-        parser.error("Either --image or --webcam must be specified")
-
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
-
-    # Initialize models
-    print(f"Initializing detector: {args.detector}")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-
-    print("Initializing age/gender model...")
-    age_gender = AgeGender()
-    print("Models initialized\n")
-
-    # Process
-    if args.webcam:
-        run_webcam(detector, age_gender, args.threshold)
-    else:
-        process_image(detector, age_gender, args.image, args.save_dir, args.threshold)
-
-
-if __name__ == "__main__":
-    main()

scripts/run_detection.py

@@ -1,80 +0,0 @@
-import os
-import cv2
-import time
-import argparse
-import numpy as np
-
-from uniface.detection import RetinaFace, SCRFD
-from uniface.visualization import draw_detections
-
-
-def run_inference(detector, image_path: str, vis_threshold: float = 0.6, save_dir: str = "outputs"):
-    image = cv2.imread(image_path)
-    if image is None:
-        print(f"Error: Failed to load image from '{image_path}'")
-        return
-
-    # 1. Get the list of face dictionaries from the detector
-    faces = detector.detect(image)
-
-    if faces:
-        # 2. Unpack the data into separate lists
-        bboxes = [face['bbox'] for face in faces]
-        scores = [face['confidence'] for face in faces]
-        landmarks = [face['landmarks'] for face in faces]
-
-        # 3. Pass the unpacked lists to the drawing function
-        draw_detections(image, bboxes, scores, landmarks, vis_threshold=0.6)
-
-
-    os.makedirs(save_dir, exist_ok=True)
-    output_path = os.path.join(save_dir, f"{os.path.splitext(os.path.basename(image_path))[0]}_out.jpg")
-    cv2.imwrite(output_path, image)
-    print(f"Output saved at: {output_path}")
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Run face detection on an image.")
-    parser.add_argument("--image", type=str, required=True, help="Path to the input image")
-    parser.add_argument(
-        "--method",
-        type=str,
-        default="retinaface",
-        choices=['retinaface', 'scrfd'],
-        help="Detection method to use."
-    )
-    parser.add_argument("--threshold", type=float, default=0.6, help="Visualization confidence threshold")
-    parser.add_argument("--iterations", type=int, default=1, help="Number of inference runs for benchmarking")
-    parser.add_argument("--save_dir", type=str, default="outputs", help="Directory to save output images")
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-
-    args = parser.parse_args()
-
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
-
-    print(f"Initializing detector: {args.method}")
-    if args.method == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-
-    avg_time = 0
-    for i in range(args.iterations):
-        start = time.time()
-        run_inference(detector, args.image, args.threshold, args.save_dir)
-        elapsed = time.time() - start
-        print(f"[{i + 1}/{args.iterations}] Inference time: {elapsed:.4f} seconds")
-        if i >= 0:  # Avoid counting the first run if it includes model loading time
-            avg_time += elapsed
-
-    if args.iterations > 1:
-        # Adjust average calculation to exclude potential first-run overhead
-        effective_iterations = max(1, args.iterations)
-        print(
-            f"\nAverage inference time over {effective_iterations} runs: {avg_time / effective_iterations:.4f} seconds")
-
-
-if __name__ == "__main__":
-    main()

scripts/run_face_search.py

@@ -1,110 +0,0 @@
-import argparse
-
-import cv2
-import numpy as np
-
-from uniface.detection import RetinaFace, SCRFD
-from uniface.face_utils import compute_similarity
-from uniface.recognition import ArcFace, MobileFace, SphereFace
-
-
-def extract_reference_embedding(detector, recognizer, image_path: str) -> np.ndarray:
-    image = cv2.imread(image_path)
-    if image is None:
-        raise RuntimeError(f"Failed to load image: {image_path}")
-
-    faces = detector.detect(image)
-    if not faces:
-        raise RuntimeError("No faces found in reference image.")
-
-    # Get landmarks from the first detected face dictionary
-    landmarks = np.array(faces[0]["landmarks"])
-
-    # Use normalized embedding for more reliable similarity comparison
-    embedding = recognizer.get_normalized_embedding(image, landmarks)
-    return embedding
-
-
-def run_video(detector, recognizer, ref_embedding: np.ndarray, threshold: float = 0.4):
-    cap = cv2.VideoCapture(0)
-    if not cap.isOpened():
-        raise RuntimeError("Webcam could not be opened.")
-    print("Webcam started. Press 'q' to quit.")
-
-    while True:
-        ret, frame = cap.read()
-        if not ret:
-            break
-
-        faces = detector.detect(frame)
-
-        # Loop through each detected face
-        for face in faces:
-            # Extract bbox and landmarks from the dictionary
-            bbox = face["bbox"]
-            landmarks = np.array(face["landmarks"])
-
-            x1, y1, x2, y2 = map(int, bbox)
-
-            # Get the normalized embedding for the current face
-            embedding = recognizer.get_normalized_embedding(frame, landmarks)
-
-            # Compare with the reference embedding
-            sim = compute_similarity(ref_embedding, embedding)
-
-            # Draw results
-            label = f"Match ({sim:.2f})" if sim > threshold else f"Unknown ({sim:.2f})"
-            color = (0, 255, 0) if sim > threshold else (0, 0, 255)
-            cv2.rectangle(frame, (x1, y1), (x2, y2), color, 2)
-            cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
-
-        cv2.imshow("Face Recognition", frame)
-        if cv2.waitKey(1) & 0xFF == ord("q"):
-            break
-
-    cap.release()
-    cv2.destroyAllWindows()
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Face recognition using a reference image.")
-    parser.add_argument("--image", type=str, required=True, help="Path to the reference face image.")
-    parser.add_argument(
-        "--detector", type=str, default="scrfd", choices=["retinaface", "scrfd"], help="Face detection method."
-    )
-    parser.add_argument(
-        "--recognizer",
-        type=str,
-        default="arcface",
-        choices=["arcface", "mobileface", "sphereface"],
-        help="Face recognition method.",
-    )
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-    args = parser.parse_args()
-
-    if args.verbose:
-        from uniface import enable_logging
-
-        enable_logging()
-
-    print("Initializing models...")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-
-    if args.recognizer == 'arcface':
-        recognizer = ArcFace()
-    elif args.recognizer == 'mobileface':
-        recognizer = MobileFace()
-    else:
-        recognizer = SphereFace()
-
-    print("Extracting reference embedding...")
-    ref_embedding = extract_reference_embedding(detector, recognizer, args.image)
-
-    run_video(detector, recognizer, ref_embedding)
-
-
-if __name__ == "__main__":
-    main()

scripts/run_landmarks.py

@@ -1,149 +0,0 @@
-"""Facial Landmark Detection Demo Script"""
-
-import os
-import cv2
-import argparse
-from pathlib import Path
-
-from uniface import RetinaFace, SCRFD, Landmark106
-
-
-def process_image(detector, landmarker, image_path: str, save_dir: str = "outputs"):
-    image = cv2.imread(image_path)
-    if image is None:
-        print(f"Error: Failed to load image from '{image_path}'")
-        return
-
-    print(f"Processing: {image_path}")
-
-    # Detect faces
-    faces = detector.detect(image)
-    print(f"  Detected {len(faces)} face(s)")
-
-    if not faces:
-        print("  No faces detected")
-        return
-
-    # Process each face
-    for i, face in enumerate(faces):
-        # Draw bounding box
-        bbox = face['bbox']
-        x1, y1, x2, y2 = map(int, bbox)
-        cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
-
-        # Get and draw 106 landmarks
-        landmarks = landmarker.get_landmarks(image, bbox)
-        print(f"  Face {i+1}: Extracted {len(landmarks)} landmarks")
-
-        for x, y in landmarks.astype(int):
-            cv2.circle(image, (x, y), 1, (0, 255, 0), -1)
-
-        # Add face count
-        cv2.putText(image, f"Face {i+1}", (x1, y1 - 10),
-                   cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
-
-    # Add total count
-    cv2.putText(image, f"Faces: {len(faces)}", (10, 30),
-               cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-
-    # Save result
-    os.makedirs(save_dir, exist_ok=True)
-    output_path = os.path.join(save_dir, f"{Path(image_path).stem}_landmarks.jpg")
-    cv2.imwrite(output_path, image)
-    print(f"Output saved: {output_path}")
-
-
-def run_webcam(detector, landmarker):
-    cap = cv2.VideoCapture(0)
-
-    if not cap.isOpened():
-        print("Cannot open webcam")
-        return
-
-    print("Webcam opened")
-    print("Press 'q' to quit\n")
-
-    frame_count = 0
-
-    try:
-        while True:
-            ret, frame = cap.read()
-            if not ret:
-                break
-
-            frame_count += 1
-
-            # Detect faces
-            faces = detector.detect(frame)
-
-            # Process each face
-            for face in faces:
-                # Draw bounding box
-                bbox = face['bbox']
-                x1, y1, x2, y2 = map(int, bbox)
-                cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
-
-                # Get and draw 106 landmarks
-                landmarks = landmarker.get_landmarks(frame, bbox)
-                for x, y in landmarks.astype(int):
-                    cv2.circle(frame, (x, y), 1, (0, 255, 0), -1)
-
-            # Add info
-            cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
-                       cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-            cv2.putText(frame, "Press 'q' to quit", (10, frame.shape[0] - 10),
-                       cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1)
-
-            cv2.imshow("106-Point Landmarks", frame)
-
-            if cv2.waitKey(1) & 0xFF == ord('q'):
-                break
-
-    except KeyboardInterrupt:
-        print("\nInterrupted")
-    finally:
-        cap.release()
-        cv2.destroyAllWindows()
-        print(f"\nProcessed {frame_count} frames")
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Run facial landmark detection")
-    parser.add_argument("--image", type=str, help="Path to input image")
-    parser.add_argument("--webcam", action="store_true", help="Use webcam instead of image")
-    parser.add_argument("--detector", type=str, default="retinaface",
-                       choices=['retinaface', 'scrfd'], help="Face detector to use")
-    parser.add_argument("--save_dir", type=str, default="outputs",
-                       help="Directory to save output images")
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-
-    args = parser.parse_args()
-
-    # Validate input
-    if not args.image and not args.webcam:
-        parser.error("Either --image or --webcam must be specified")
-
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
-
-    # Initialize models
-    print(f"Initializing detector: {args.detector}")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-
-    print("Initializing landmark detector...")
-    landmarker = Landmark106()
-    print("Models initialized\n")
-
-    # Process
-    if args.webcam:
-        run_webcam(detector, landmarker)
-    else:
-        process_image(detector, landmarker, args.image, args.save_dir)
-
-
-if __name__ == "__main__":
-    main()

scripts/run_recognition.py

@@ -1,128 +0,0 @@
-import cv2
-import argparse
-import numpy as np
-
-from uniface.detection import RetinaFace, SCRFD
-from uniface.recognition import ArcFace, MobileFace, SphereFace
-from uniface.face_utils import compute_similarity
-
-
-def run_inference(detector, recognizer, image_path: str):
-    image = cv2.imread(image_path)
-    if image is None:
-        print(f"Error: Failed to load image from '{image_path}'")
-        return
-
-    faces = detector.detect(image)
-
-    if not faces:
-        print("No faces detected.")
-        return
-
-    print(f"Detected {len(faces)} face(s). Extracting embeddings for the first face...")
-
-    # Process the first detected face
-    first_face = faces[0]
-    landmarks = np.array(first_face['landmarks'])  # Convert landmarks to numpy array
-
-    # Extract embedding using the landmarks from the face dictionary
-    embedding = recognizer.get_embedding(image, landmarks)
-    norm_embedding = recognizer.get_normalized_embedding(image, landmarks)
-
-    # Print some info about the embeddings
-    print(f"  - Embedding shape: {embedding.shape}")
-    print(f"  - L2 norm of unnormalized embedding: {np.linalg.norm(embedding):.4f}")
-    print(f"  - L2 norm of normalized embedding: {np.linalg.norm(norm_embedding):.4f}")
-
-
-def compare_faces(detector, recognizer, image1_path: str, image2_path: str, threshold: float = 0.35):
-
-    # Load images
-    img1 = cv2.imread(image1_path)
-    img2 = cv2.imread(image2_path)
-
-    if img1 is None or img2 is None:
-        print(f"Error: Failed to load images")
-        return
-
-    # Detect faces
-    faces1 = detector.detect(img1)
-    faces2 = detector.detect(img2)
-
-    if not faces1 or not faces2:
-        print("Error: No faces detected in one or both images")
-        return
-
-    # Get landmarks for first face in each image
-    landmarks1 = np.array(faces1[0]['landmarks'])
-    landmarks2 = np.array(faces2[0]['landmarks'])
-
-    # Get normalized embeddings
-    embedding1 = recognizer.get_normalized_embedding(img1, landmarks1)
-    embedding2 = recognizer.get_normalized_embedding(img2, landmarks2)
-
-    # Compute similarity
-    similarity = compute_similarity(embedding1, embedding2, normalized=True)
-    is_match = similarity > threshold
-
-    print(f"Similarity: {similarity:.4f}")
-    print(f"Result: {'Same person' if is_match else 'Different person'}")
-    print(f"Threshold: {threshold}")
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Face recognition and comparison.")
-    parser.add_argument("--image", type=str, help="Path to single image for embedding extraction.")
-    parser.add_argument("--image1", type=str, help="Path to first image for comparison.")
-    parser.add_argument("--image2", type=str, help="Path to second image for comparison.")
-    parser.add_argument("--threshold", type=float, default=0.35, help="Similarity threshold for face matching.")
-    parser.add_argument(
-        "--detector",
-        type=str,
-        default="retinaface",
-        choices=['retinaface', 'scrfd'],
-        help="Face detection method to use."
-    )
-    parser.add_argument(
-        "--recognizer",
-        type=str,
-        default="arcface",
-        choices=['arcface', 'mobileface', 'sphereface'],
-        help="Face recognition method to use."
-    )
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-
-    args = parser.parse_args()
-
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
-
-    print(f"Initializing detector: {args.detector}")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-
-    print(f"Initializing recognizer: {args.recognizer}")
-    if args.recognizer == 'arcface':
-        recognizer = ArcFace()
-    elif args.recognizer == 'mobileface':
-        recognizer = MobileFace()
-    else:
-        recognizer = SphereFace()
-
-    if args.image1 and args.image2:
-        # Face comparison mode
-        print(f"Comparing faces: {args.image1} vs {args.image2}")
-        compare_faces(detector, recognizer, args.image1, args.image2, args.threshold)
-    elif args.image:
-        # Single image embedding extraction mode
-        run_inference(detector, recognizer, args.image)
-    else:
-        print("Error: Provide either --image for single image processing or --image1 and --image2 for comparison")
-        parser.print_help()
-
-
-if __name__ == "__main__":
-    main()

scripts/run_video_detection.py

@@ -1,142 +0,0 @@
-"""Video Face Detection Script"""
-
-import cv2
-import argparse
-from pathlib import Path
-from tqdm import tqdm
-
-from uniface import RetinaFace, SCRFD
-from uniface.visualization import draw_detections
-
-
-def process_video(detector, input_path: str, output_path: str, vis_threshold: float = 0.6,
-                 fps: int = None, show_preview: bool = False):
-    # Open input video
-    cap = cv2.VideoCapture(input_path)
-    if not cap.isOpened():
-        print(f"Error: Cannot open video file '{input_path}'")
-        return
-
-    # Get video properties
-    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
-    source_fps = cap.get(cv2.CAP_PROP_FPS)
-    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-
-    output_fps = fps if fps is not None else source_fps
-
-    print(f"📹 Input: {input_path}")
-    print(f"   Resolution: {width}x{height}")
-    print(f"   FPS: {source_fps:.2f}")
-    print(f"   Total frames: {total_frames}")
-    print(f"\n📹 Output: {output_path}")
-    print(f"   FPS: {output_fps:.2f}\n")
-
-    # Initialize video writer
-    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
-    out = cv2.VideoWriter(output_path, fourcc, output_fps, (width, height))
-
-    if not out.isOpened():
-        print(f"Error: Cannot create output video '{output_path}'")
-        cap.release()
-        return
-
-    # Process frames
-    frame_count = 0
-    total_faces = 0
-
-    try:
-        with tqdm(total=total_frames, desc="Processing", unit="frames") as pbar:
-            while True:
-                ret, frame = cap.read()
-                if not ret:
-                    break
-
-                frame_count += 1
-
-                # Detect faces
-                faces = detector.detect(frame)
-                total_faces += len(faces)
-
-                # Draw detections
-                bboxes = [f['bbox'] for f in faces]
-                scores = [f['confidence'] for f in faces]
-                landmarks = [f['landmarks'] for f in faces]
-                draw_detections(frame, bboxes, scores, landmarks, vis_threshold=vis_threshold)
-
-                # Add frame info
-                cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
-                           cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-
-                # Write frame
-                out.write(frame)
-
-                # Show preview if requested
-                if show_preview:
-                    cv2.imshow("Processing Video - Press 'q' to cancel", frame)
-                    if cv2.waitKey(1) & 0xFF == ord('q'):
-                        print("\nProcessing cancelled by user")
-                        break
-
-                pbar.update(1)
-
-    except KeyboardInterrupt:
-        print("\nProcessing interrupted")
-    finally:
-        cap.release()
-        out.release()
-        if show_preview:
-            cv2.destroyAllWindows()
-
-    # Summary
-    print(f"\nProcessing complete!")
-    print(f"   Processed: {frame_count} frames")
-    print(f"   Total faces detected: {total_faces}")
-    print(f"   Average faces per frame: {total_faces/frame_count:.2f}" if frame_count > 0 else "")
-    print(f"   Output saved: {output_path}")
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Process video with face detection")
-    parser.add_argument("--input", type=str, required=True, help="Path to input video")
-    parser.add_argument("--output", type=str, required=True, help="Path to output video")
-    parser.add_argument("--detector", type=str, default="retinaface",
-                       choices=['retinaface', 'scrfd'], help="Face detector to use")
-    parser.add_argument("--threshold", type=float, default=0.6,
-                       help="Confidence threshold for visualization")
-    parser.add_argument("--fps", type=int, default=None,
-                       help="Output FPS (default: same as input)")
-    parser.add_argument("--preview", action="store_true",
-                       help="Show live preview during processing")
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
-
-    args = parser.parse_args()
-
-    # Check input exists
-    if not Path(args.input).exists():
-        print(f"Error: Input file '{args.input}' does not exist")
-        return
-
-    # Create output directory if needed
-    output_dir = Path(args.output).parent
-    if output_dir != Path('.'):
-        output_dir.mkdir(parents=True, exist_ok=True)
-
-    if args.verbose:
-        from uniface import enable_logging
-        enable_logging()
-
-    # Initialize detector
-    print(f"Initializing detector: {args.detector}")
-    if args.detector == 'retinaface':
-        detector = RetinaFace()
-    else:
-        detector = SCRFD()
-    print("Detector initialized\n")
-
-    # Process video
-    process_video(detector, args.input, args.output, args.threshold, args.fps, args.preview)
-
-
-if __name__ == "__main__":
-    main()

scripts/sha256_generate.py

@@ -1,35 +0,0 @@
-import argparse
-import hashlib
-from pathlib import Path
-
-
-def compute_sha256(file_path: Path, chunk_size: int = 8192) -> str:
-    sha256_hash = hashlib.sha256()
-    with file_path.open("rb") as f:
-        for chunk in iter(lambda: f.read(chunk_size), b""):
-            sha256_hash.update(chunk)
-    return sha256_hash.hexdigest()
-
-
-def main():
-    parser = argparse.ArgumentParser(
-        description="Compute SHA256 hash of a model weight file."
-    )
-    parser.add_argument(
-        "file",
-        type=Path,
-        help="Path to the model weight file (.onnx, .pth, etc)."
-    )
-
-    args = parser.parse_args()
-
-    if not args.file.exists() or not args.file.is_file():
-        print(f"File does not exist: {args.file}")
-        return
-
-    sha256 = compute_sha256(args.file)
-    print(f"`SHA256 hash for '{args.file.name}':\n{sha256}")
-
-
-if __name__ == "__main__":
-    main()

tests/test_age_gender.py

@@ -1,7 +1,15 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Tests for AgeGender attribute predictor."""
+
+from __future__ import annotations
+
 import numpy as np
 import pytest
 
-from uniface.attribute import AgeGender
+from uniface.attribute import AgeGender, AttributeResult
 
 
 @pytest.fixture
@@ -20,23 +28,26 @@ def mock_bbox():
 
 
 def test_model_initialization(age_gender_model):
-    assert age_gender_model is not None, "AgeGender model initialization failed."
+    assert age_gender_model is not None, 'AgeGender model initialization failed.'
 
 
 def test_prediction_output_format(age_gender_model, mock_image, mock_bbox):
-    gender, age = age_gender_model.predict(mock_image, mock_bbox)
-    assert isinstance(gender, str), f"Gender should be string, got {type(gender)}"
-    assert isinstance(age, int), f"Age should be int, got {type(age)}"
+    result = age_gender_model.predict(mock_image, mock_bbox)
+    assert isinstance(result, AttributeResult), f'Result should be AttributeResult, got {type(result)}'
+    assert isinstance(result.gender, int), f'Gender should be int, got {type(result.gender)}'
+    assert isinstance(result.age, int), f'Age should be int, got {type(result.age)}'
+    assert isinstance(result.sex, str), f'Sex should be str, got {type(result.sex)}'
 
 
 def test_gender_values(age_gender_model, mock_image, mock_bbox):
-    gender, age = age_gender_model.predict(mock_image, mock_bbox)
-    assert gender in ['Male', 'Female'], f"Gender should be 'Male' or 'Female', got '{gender}'"
+    result = age_gender_model.predict(mock_image, mock_bbox)
+    assert result.gender in [0, 1], f'Gender should be 0 (Female) or 1 (Male), got {result.gender}'
+    assert result.sex in ['Female', 'Male'], f'Sex should be Female or Male, got {result.sex}'
 
 
 def test_age_range(age_gender_model, mock_image, mock_bbox):
-    gender, age = age_gender_model.predict(mock_image, mock_bbox)
-    assert 0 <= age <= 120, f"Age should be between 0 and 120, got {age}"
+    result = age_gender_model.predict(mock_image, mock_bbox)
+    assert 0 <= result.age <= 120, f'Age should be between 0 and 120, got {result.age}'
 
 
 def test_different_bbox_sizes(age_gender_model, mock_image):
@@ -47,9 +58,9 @@ def test_different_bbox_sizes(age_gender_model, mock_image):
     ]
 
     for bbox in test_bboxes:
-        gender, age = age_gender_model.predict(mock_image, bbox)
-        assert gender in ['Male', 'Female'], f"Failed for bbox {bbox}"
-        assert 0 <= age <= 120, f"Age out of range for bbox {bbox}"
+        result = age_gender_model.predict(mock_image, bbox)
+        assert result.gender in [0, 1], f'Failed for bbox {bbox}'
+        assert 0 <= result.age <= 120, f'Age out of range for bbox {bbox}'
 
 
 def test_different_image_sizes(age_gender_model, mock_bbox):
@@ -57,31 +68,31 @@ def test_different_image_sizes(age_gender_model, mock_bbox):
 
     for size in test_sizes:
         mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
-        gender, age = age_gender_model.predict(mock_image, mock_bbox)
-        assert gender in ['Male', 'Female'], f"Failed for image size {size}"
-        assert 0 <= age <= 120, f"Age out of range for image size {size}"
+        result = age_gender_model.predict(mock_image, mock_bbox)
+        assert result.gender in [0, 1], f'Failed for image size {size}'
+        assert 0 <= result.age <= 120, f'Age out of range for image size {size}'
 
 
 def test_consistency(age_gender_model, mock_image, mock_bbox):
-    gender1, age1 = age_gender_model.predict(mock_image, mock_bbox)
-    gender2, age2 = age_gender_model.predict(mock_image, mock_bbox)
+    result1 = age_gender_model.predict(mock_image, mock_bbox)
+    result2 = age_gender_model.predict(mock_image, mock_bbox)
 
-    assert gender1 == gender2, "Same input should produce same gender prediction"
-    assert age1 == age2, "Same input should produce same age prediction"
+    assert result1.gender == result2.gender, 'Same input should produce same gender prediction'
+    assert result1.age == result2.age, 'Same input should produce same age prediction'
 
 
 def test_bbox_list_format(age_gender_model, mock_image):
     bbox_list = [100, 100, 300, 300]
-    gender, age = age_gender_model.predict(mock_image, bbox_list)
-    assert gender in ['Male', 'Female'], "Should work with bbox as list"
-    assert 0 <= age <= 120, "Age should be in valid range"
+    result = age_gender_model.predict(mock_image, bbox_list)
+    assert result.gender in [0, 1], 'Should work with bbox as list'
+    assert 0 <= result.age <= 120, 'Age should be in valid range'
 
 
 def test_bbox_array_format(age_gender_model, mock_image):
     bbox_array = np.array([100, 100, 300, 300])
-    gender, age = age_gender_model.predict(mock_image, bbox_array)
-    assert gender in ['Male', 'Female'], "Should work with bbox as numpy array"
-    assert 0 <= age <= 120, "Age should be in valid range"
+    result = age_gender_model.predict(mock_image, bbox_array)
+    assert result.gender in [0, 1], 'Should work with bbox as numpy array'
+    assert 0 <= result.age <= 120, 'Age should be in valid range'
 
 
 def test_multiple_predictions(age_gender_model, mock_image):
@@ -93,24 +104,37 @@ def test_multiple_predictions(age_gender_model, mock_image):
 
     results = []
     for bbox in bboxes:
-        gender, age = age_gender_model.predict(mock_image, bbox)
-        results.append((gender, age))
+        result = age_gender_model.predict(mock_image, bbox)
+        results.append(result)
 
-    assert len(results) == 3, "Should have 3 predictions"
-    for gender, age in results:
-        assert gender in ['Male', 'Female']
-        assert 0 <= age <= 120
+    assert len(results) == 3, 'Should have 3 predictions'
+    for result in results:
+        assert result.gender in [0, 1]
+        assert 0 <= result.age <= 120
 
 
 def test_age_is_positive(age_gender_model, mock_image, mock_bbox):
     for _ in range(5):
-        gender, age = age_gender_model.predict(mock_image, mock_bbox)
-        assert age >= 0, f"Age should be non-negative, got {age}"
+        result = age_gender_model.predict(mock_image, mock_bbox)
+        assert result.age >= 0, f'Age should be non-negative, got {result.age}'
 
 
 def test_output_format_for_visualization(age_gender_model, mock_image, mock_bbox):
-    gender, age = age_gender_model.predict(mock_image, mock_bbox)
-    text = f"{gender}, {age}y"
-    assert isinstance(text, str), "Should be able to format as string"
-    assert "Male" in text or "Female" in text, "Text should contain gender"
-    assert "y" in text, "Text should contain 'y' for years"
+    result = age_gender_model.predict(mock_image, mock_bbox)
+    text = f'{result.sex}, {result.age}y'
+    assert isinstance(text, str), 'Should be able to format as string'
+    assert 'Male' in text or 'Female' in text, 'Text should contain gender'
+    assert 'y' in text, "Text should contain 'y' for years"
+
+
+def test_attribute_result_fields(age_gender_model, mock_image, mock_bbox):
+    """Test that AttributeResult has correct fields for AgeGender model."""
+    result = age_gender_model.predict(mock_image, mock_bbox)
+
+    # AgeGender should set gender and age
+    assert result.gender is not None
+    assert result.age is not None
+
+    # AgeGender should NOT set race and age_group (FairFace only)
+    assert result.race is None
+    assert result.age_group is None

tests/test_factory.py

@@ -1,3 +1,11 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Tests for factory functions (create_detector, create_recognizer, etc.)."""
+
+from __future__ import annotations
+
 import numpy as np
 import pytest
 
@@ -17,7 +25,7 @@ def test_create_detector_retinaface():
     Test creating a RetinaFace detector using factory function.
     """
     detector = create_detector('retinaface')
-    assert detector is not None, "Failed to create RetinaFace detector"
+    assert detector is not None, 'Failed to create RetinaFace detector'
 
 
 def test_create_detector_scrfd():
@@ -25,7 +33,7 @@ def test_create_detector_scrfd():
     Test creating a SCRFD detector using factory function.
     """
     detector = create_detector('scrfd')
-    assert detector is not None, "Failed to create SCRFD detector"
+    assert detector is not None, 'Failed to create SCRFD detector'
 
 
 def test_create_detector_with_config():
@@ -35,10 +43,10 @@ def test_create_detector_with_config():
     detector = create_detector(
         'retinaface',
         model_name=RetinaFaceWeights.MNET_V2,
-        conf_thresh=0.8,
-        nms_thresh=0.3
+        confidence_threshold=0.8,
+        nms_threshold=0.3,
     )
-    assert detector is not None, "Failed to create detector with custom config"
+    assert detector is not None, 'Failed to create detector with custom config'
 
 
 def test_create_detector_invalid_method():
@@ -53,12 +61,8 @@ def test_create_detector_scrfd_with_model():
     """
     Test creating SCRFD detector with specific model.
     """
-    detector = create_detector(
-        'scrfd',
-        model_name=SCRFDWeights.SCRFD_10G_KPS,
-        conf_thresh=0.5
-    )
-    assert detector is not None, "Failed to create SCRFD with specific model"
+    detector = create_detector('scrfd', model_name=SCRFDWeights.SCRFD_10G_KPS, confidence_threshold=0.5)
+    assert detector is not None, 'Failed to create SCRFD with specific model'
 
 
 # create_recognizer tests
@@ -67,7 +71,7 @@ def test_create_recognizer_arcface():
     Test creating an ArcFace recognizer using factory function.
     """
     recognizer = create_recognizer('arcface')
-    assert recognizer is not None, "Failed to create ArcFace recognizer"
+    assert recognizer is not None, 'Failed to create ArcFace recognizer'
 
 
 def test_create_recognizer_mobileface():
@@ -75,7 +79,7 @@ def test_create_recognizer_mobileface():
     Test creating a MobileFace recognizer using factory function.
     """
     recognizer = create_recognizer('mobileface')
-    assert recognizer is not None, "Failed to create MobileFace recognizer"
+    assert recognizer is not None, 'Failed to create MobileFace recognizer'
 
 
 def test_create_recognizer_sphereface():
@@ -83,7 +87,7 @@ def test_create_recognizer_sphereface():
     Test creating a SphereFace recognizer using factory function.
     """
     recognizer = create_recognizer('sphereface')
-    assert recognizer is not None, "Failed to create SphereFace recognizer"
+    assert recognizer is not None, 'Failed to create SphereFace recognizer'
 
 
 def test_create_recognizer_invalid_method():
@@ -100,7 +104,7 @@ def test_create_landmarker():
     Test creating a Landmark106 detector using factory function.
     """
     landmarker = create_landmarker('2d106det')
-    assert landmarker is not None, "Failed to create Landmark106 detector"
+    assert landmarker is not None, 'Failed to create Landmark106 detector'
 
 
 def test_create_landmarker_default():
@@ -108,7 +112,7 @@ def test_create_landmarker_default():
     Test creating landmarker with default parameters.
     """
     landmarker = create_landmarker()
-    assert landmarker is not None, "Failed to create default landmarker"
+    assert landmarker is not None, 'Failed to create default landmarker'
 
 
 def test_create_landmarker_invalid_method():
@@ -127,7 +131,7 @@ def test_detect_faces_retinaface():
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
     faces = detect_faces(mock_image, method='retinaface')
 
-    assert isinstance(faces, list), "detect_faces should return a list"
+    assert isinstance(faces, list), 'detect_faces should return a list'
 
 
 def test_detect_faces_scrfd():
@@ -137,7 +141,7 @@ def test_detect_faces_scrfd():
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
     faces = detect_faces(mock_image, method='scrfd')
 
-    assert isinstance(faces, list), "detect_faces should return a list"
+    assert isinstance(faces, list), 'detect_faces should return a list'
 
 
 def test_detect_faces_with_threshold():
@@ -145,13 +149,13 @@ def test_detect_faces_with_threshold():
     Test detect_faces with custom confidence threshold.
     """
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-    faces = detect_faces(mock_image, method='retinaface', conf_thresh=0.8)
+    faces = detect_faces(mock_image, method='retinaface', confidence_threshold=0.8)
 
-    assert isinstance(faces, list), "detect_faces should return a list"
+    assert isinstance(faces, list), 'detect_faces should return a list'
 
     # All detections should respect threshold
     for face in faces:
-        assert face['confidence'] >= 0.8, "All detections should meet confidence threshold"
+        assert face.confidence >= 0.8, 'All detections should meet confidence threshold'
 
 
 def test_detect_faces_default_method():
@@ -161,7 +165,7 @@ def test_detect_faces_default_method():
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
     faces = detect_faces(mock_image)  # No method specified
 
-    assert isinstance(faces, list), "detect_faces should return a list with default method"
+    assert isinstance(faces, list), 'detect_faces should return a list with default method'
 
 
 def test_detect_faces_empty_image():
@@ -171,8 +175,8 @@ def test_detect_faces_empty_image():
     empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
     faces = detect_faces(empty_image, method='retinaface')
 
-    assert isinstance(faces, list), "Should return a list even for empty image"
-    assert len(faces) == 0, "Should detect no faces in blank image"
+    assert isinstance(faces, list), 'Should return a list even for empty image'
+    assert len(faces) == 0, 'Should detect no faces in blank image'
 
 
 # list_available_detectors tests
@@ -182,8 +186,8 @@ def test_list_available_detectors():
     """
     detectors = list_available_detectors()
 
-    assert isinstance(detectors, dict), "Should return a dictionary of detectors"
-    assert len(detectors) > 0, "Should have at least one detector available"
+    assert isinstance(detectors, dict), 'Should return a dictionary of detectors'
+    assert len(detectors) > 0, 'Should have at least one detector available'
 
 
 def test_list_available_detectors_contents():
@@ -206,7 +210,7 @@ def test_detector_inference_from_factory():
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
 
     faces = detector.detect(mock_image)
-    assert isinstance(faces, list), "Detector should return list of faces"
+    assert isinstance(faces, list), 'Detector should return list of faces'
 
 
 def test_recognizer_inference_from_factory():
@@ -217,8 +221,8 @@ def test_recognizer_inference_from_factory():
     mock_image = np.random.randint(0, 255, (112, 112, 3), dtype=np.uint8)
 
     embedding = recognizer.get_embedding(mock_image)
-    assert embedding is not None, "Recognizer should return embedding"
-    assert embedding.shape[1] == 512, "Should return 512-dimensional embedding"
+    assert embedding is not None, 'Recognizer should return embedding'
+    assert embedding.shape[1] == 512, 'Should return 512-dimensional embedding'
 
 
 def test_landmarker_inference_from_factory():
@@ -230,8 +234,8 @@ def test_landmarker_inference_from_factory():
     mock_bbox = [100, 100, 300, 300]
 
     landmarks = landmarker.get_landmarks(mock_image, mock_bbox)
-    assert landmarks is not None, "Landmarker should return landmarks"
-    assert landmarks.shape == (106, 2), "Should return 106 landmarks"
+    assert landmarks is not None, 'Landmarker should return landmarks'
+    assert landmarks.shape == (106, 2), 'Should return 106 landmarks'
 
 
 def test_multiple_detector_creation():
@@ -243,15 +247,15 @@ def test_multiple_detector_creation():
 
     assert detector1 is not None
     assert detector2 is not None
-    assert detector1 is not detector2, "Should create separate instances"
+    assert detector1 is not detector2, 'Should create separate instances'
 
 
 def test_detector_with_different_configs():
     """
     Test creating multiple detectors with different configurations.
     """
-    detector_high_thresh = create_detector('retinaface', conf_thresh=0.9)
-    detector_low_thresh = create_detector('retinaface', conf_thresh=0.3)
+    detector_high_thresh = create_detector('retinaface', confidence_threshold=0.9)
+    detector_low_thresh = create_detector('retinaface', confidence_threshold=0.3)
 
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
 
@@ -267,12 +271,12 @@ def test_factory_returns_correct_types():
     """
     Test that factory functions return instances of the correct types.
     """
-    from uniface import RetinaFace, ArcFace, Landmark106
+    from uniface import ArcFace, Landmark106, RetinaFace
 
     detector = create_detector('retinaface')
     recognizer = create_recognizer('arcface')
     landmarker = create_landmarker('2d106det')
 
-    assert isinstance(detector, RetinaFace), "Should return RetinaFace instance"
-    assert isinstance(recognizer, ArcFace), "Should return ArcFace instance"
-    assert isinstance(landmarker, Landmark106), "Should return Landmark106 instance"
+    assert isinstance(detector, RetinaFace), 'Should return RetinaFace instance'
+    assert isinstance(recognizer, ArcFace), 'Should return ArcFace instance'
+    assert isinstance(landmarker, Landmark106), 'Should return Landmark106 instance'

tests/test_landmark.py

@@ -1,3 +1,11 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Tests for 106-point facial landmark detector."""
+
+from __future__ import annotations
+
 import numpy as np
 import pytest
 
@@ -20,17 +28,17 @@ def mock_bbox():
 
 
 def test_model_initialization(landmark_model):
-    assert landmark_model is not None, "Landmark106 model initialization failed."
+    assert landmark_model is not None, 'Landmark106 model initialization failed.'
 
 
 def test_landmark_detection(landmark_model, mock_image, mock_bbox):
     landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
-    assert landmarks.shape == (106, 2), f"Expected shape (106, 2), got {landmarks.shape}"
+    assert landmarks.shape == (106, 2), f'Expected shape (106, 2), got {landmarks.shape}'
 
 
 def test_landmark_dtype(landmark_model, mock_image, mock_bbox):
     landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
-    assert landmarks.dtype == np.float32, f"Expected float32, got {landmarks.dtype}"
+    assert landmarks.dtype == np.float32, f'Expected float32, got {landmarks.dtype}'
 
 
 def test_landmark_coordinates_within_image(landmark_model, mock_image, mock_bbox):
@@ -45,8 +53,8 @@ def test_landmark_coordinates_within_image(landmark_model, mock_image, mock_bbox
     x_in_bounds = np.sum((x_coords >= x1 - margin) & (x_coords <= x2 + margin))
     y_in_bounds = np.sum((y_coords >= y1 - margin) & (y_coords <= y2 + margin))
 
-    assert x_in_bounds >= 95, f"Only {x_in_bounds}/106 x-coordinates within bounds"
-    assert y_in_bounds >= 95, f"Only {y_in_bounds}/106 y-coordinates within bounds"
+    assert x_in_bounds >= 95, f'Only {x_in_bounds}/106 x-coordinates within bounds'
+    assert y_in_bounds >= 95, f'Only {y_in_bounds}/106 y-coordinates within bounds'
 
 
 def test_different_bbox_sizes(landmark_model, mock_image):
@@ -58,22 +66,22 @@ def test_different_bbox_sizes(landmark_model, mock_image):
 
     for bbox in test_bboxes:
         landmarks = landmark_model.get_landmarks(mock_image, bbox)
-        assert landmarks.shape == (106, 2), f"Failed for bbox {bbox}"
+        assert landmarks.shape == (106, 2), f'Failed for bbox {bbox}'
 
 
 def test_landmark_array_format(landmark_model, mock_image, mock_bbox):
     landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
     landmarks_int = landmarks.astype(int)
 
-    assert landmarks_int.shape == (106, 2), "Integer conversion should preserve shape"
-    assert landmarks_int.dtype in [np.int32, np.int64], "Should convert to integer type"
+    assert landmarks_int.shape == (106, 2), 'Integer conversion should preserve shape'
+    assert landmarks_int.dtype in [np.int32, np.int64], 'Should convert to integer type'
 
 
 def test_consistency(landmark_model, mock_image, mock_bbox):
     landmarks1 = landmark_model.get_landmarks(mock_image, mock_bbox)
     landmarks2 = landmark_model.get_landmarks(mock_image, mock_bbox)
 
-    assert np.allclose(landmarks1, landmarks2), "Same input should produce same landmarks"
+    assert np.allclose(landmarks1, landmarks2), 'Same input should produce same landmarks'
 
 
 def test_different_image_sizes(landmark_model, mock_bbox):
@@ -82,19 +90,19 @@ def test_different_image_sizes(landmark_model, mock_bbox):
     for size in test_sizes:
         mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
         landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
-        assert landmarks.shape == (106, 2), f"Failed for image size {size}"
+        assert landmarks.shape == (106, 2), f'Failed for image size {size}'
 
 
 def test_bbox_list_format(landmark_model, mock_image):
     bbox_list = [100, 100, 300, 300]
     landmarks = landmark_model.get_landmarks(mock_image, bbox_list)
-    assert landmarks.shape == (106, 2), "Should work with bbox as list"
+    assert landmarks.shape == (106, 2), 'Should work with bbox as list'
 
 
 def test_bbox_array_format(landmark_model, mock_image):
     bbox_array = np.array([100, 100, 300, 300])
     landmarks = landmark_model.get_landmarks(mock_image, bbox_array)
-    assert landmarks.shape == (106, 2), "Should work with bbox as numpy array"
+    assert landmarks.shape == (106, 2), 'Should work with bbox as numpy array'
 
 
 def test_landmark_distribution(landmark_model, mock_image, mock_bbox):
@@ -103,5 +111,5 @@ def test_landmark_distribution(landmark_model, mock_image, mock_bbox):
     x_variance = np.var(landmarks[:, 0])
     y_variance = np.var(landmarks[:, 1])
 
-    assert x_variance > 0, "Landmarks should have variation in x-coordinates"
-    assert y_variance > 0, "Landmarks should have variation in y-coordinates"
+    assert x_variance > 0, 'Landmarks should have variation in x-coordinates'
+    assert y_variance > 0, 'Landmarks should have variation in y-coordinates'

tests/test_parsing.py

@@ -0,0 +1,122 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Tests for BiSeNet face parsing model."""
+
+from __future__ import annotations
+
+import numpy as np
+import pytest
+
+from uniface.constants import ParsingWeights
+from uniface.parsing import BiSeNet, create_face_parser
+
+
+def test_bisenet_initialization():
+    """Test BiSeNet initialization."""
+    parser = BiSeNet()
+    assert parser is not None
+    assert parser.input_size == (512, 512)
+
+
+def test_bisenet_with_different_models():
+    """Test BiSeNet with different model weights."""
+    parser_resnet18 = BiSeNet(model_name=ParsingWeights.RESNET18)
+    parser_resnet34 = BiSeNet(model_name=ParsingWeights.RESNET34)
+
+    assert parser_resnet18 is not None
+    assert parser_resnet34 is not None
+
+
+def test_bisenet_preprocess():
+    """Test preprocessing."""
+    parser = BiSeNet()
+
+    # Create a dummy face image
+    face_image = np.random.randint(0, 255, (256, 256, 3), dtype=np.uint8)
+
+    # Preprocess
+    preprocessed = parser.preprocess(face_image)
+
+    assert preprocessed.shape == (1, 3, 512, 512)
+    assert preprocessed.dtype == np.float32
+
+
+def test_bisenet_postprocess():
+    """Test postprocessing."""
+    parser = BiSeNet()
+
+    # Create dummy model output (batch_size=1, num_classes=19, H=512, W=512)
+    dummy_output = np.random.randn(1, 19, 512, 512).astype(np.float32)
+
+    # Postprocess
+    mask = parser.postprocess(dummy_output, original_size=(256, 256))
+
+    assert mask.shape == (256, 256)
+    assert mask.dtype == np.uint8
+    assert mask.min() >= 0
+    assert mask.max() < 19  # 19 classes (0-18)
+
+
+def test_bisenet_parse():
+    """Test end-to-end parsing."""
+    parser = BiSeNet()
+
+    # Create a dummy face image
+    face_image = np.random.randint(0, 255, (256, 256, 3), dtype=np.uint8)
+
+    # Parse
+    mask = parser.parse(face_image)
+
+    assert mask.shape == (256, 256)
+    assert mask.dtype == np.uint8
+    assert mask.min() >= 0
+    assert mask.max() < 19
+
+
+def test_bisenet_callable():
+    """Test that BiSeNet is callable."""
+    parser = BiSeNet()
+    face_image = np.random.randint(0, 255, (256, 256, 3), dtype=np.uint8)
+
+    # Should work as callable
+    mask = parser(face_image)
+
+    assert mask.shape == (256, 256)
+    assert mask.dtype == np.uint8
+
+
+def test_create_face_parser_with_enum():
+    """Test factory function with enum."""
+    parser = create_face_parser(ParsingWeights.RESNET18)
+    assert parser is not None
+    assert isinstance(parser, BiSeNet)
+
+
+def test_create_face_parser_with_string():
+    """Test factory function with string."""
+    parser = create_face_parser('parsing_resnet18')
+    assert parser is not None
+    assert isinstance(parser, BiSeNet)
+
+
+def test_create_face_parser_invalid_model():
+    """Test factory function with invalid model name."""
+    with pytest.raises(ValueError, match='Unknown face parsing model'):
+        create_face_parser('invalid_model')
+
+
+def test_bisenet_different_input_sizes():
+    """Test parsing with different input image sizes."""
+    parser = BiSeNet()
+
+    # Test with different sizes
+    sizes = [(128, 128), (256, 256), (512, 512), (640, 480)]
+
+    for h, w in sizes:
+        face_image = np.random.randint(0, 255, (h, w, 3), dtype=np.uint8)
+        mask = parser.parse(face_image)
+
+        assert mask.shape == (h, w), f'Failed for size {h}x{w}'
+        assert mask.dtype == np.uint8

tests/test_recognition.py

@@ -1,3 +1,11 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Tests for face recognition models (ArcFace, MobileFace, SphereFace)."""
+
+from __future__ import annotations
+
 import numpy as np
 import pytest
 
@@ -41,13 +49,16 @@ def mock_landmarks():
     """
     Create mock 5-point facial landmarks.
     """
-    return np.array([
-        [38.2946, 51.6963],
-        [73.5318, 51.5014],
-        [56.0252, 71.7366],
-        [41.5493, 92.3655],
-        [70.7299, 92.2041]
-    ], dtype=np.float32)
+    return np.array(
+        [
+            [38.2946, 51.6963],
+            [73.5318, 51.5014],
+            [56.0252, 71.7366],
+            [41.5493, 92.3655],
+            [70.7299, 92.2041],
+        ],
+        dtype=np.float32,
+    )
 
 
 # ArcFace Tests
@@ -55,7 +66,7 @@ def test_arcface_initialization(arcface_model):
     """
     Test that the ArcFace model initializes correctly.
     """
-    assert arcface_model is not None, "ArcFace model initialization failed."
+    assert arcface_model is not None, 'ArcFace model initialization failed.'
 
 
 def test_arcface_embedding_shape(arcface_model, mock_aligned_face):
@@ -65,8 +76,8 @@ def test_arcface_embedding_shape(arcface_model, mock_aligned_face):
     embedding = arcface_model.get_embedding(mock_aligned_face)
 
     # ArcFace typically produces 512-dimensional embeddings
-    assert embedding.shape[1] == 512, f"Expected 512-dim embedding, got {embedding.shape[1]}"
-    assert embedding.shape[0] == 1, "Embedding should have batch dimension of 1"
+    assert embedding.shape[1] == 512, f'Expected 512-dim embedding, got {embedding.shape[1]}'
+    assert embedding.shape[0] == 1, 'Embedding should have batch dimension of 1'
 
 
 def test_arcface_normalized_embedding(arcface_model, mock_landmarks):
@@ -80,7 +91,7 @@ def test_arcface_normalized_embedding(arcface_model, mock_landmarks):
 
     # Check that embedding is normalized (L2 norm ≈ 1.0)
     norm = np.linalg.norm(embedding)
-    assert np.isclose(norm, 1.0, atol=1e-5), f"Normalized embedding should have norm 1.0, got {norm}"
+    assert np.isclose(norm, 1.0, atol=1e-5), f'Normalized embedding should have norm 1.0, got {norm}'
 
 
 def test_arcface_embedding_dtype(arcface_model, mock_aligned_face):
@@ -88,7 +99,7 @@ def test_arcface_embedding_dtype(arcface_model, mock_aligned_face):
     Test that embeddings have the correct data type.
     """
     embedding = arcface_model.get_embedding(mock_aligned_face)
-    assert embedding.dtype == np.float32, f"Expected float32, got {embedding.dtype}"
+    assert embedding.dtype == np.float32, f'Expected float32, got {embedding.dtype}'
 
 
 def test_arcface_consistency(arcface_model, mock_aligned_face):
@@ -98,7 +109,7 @@ def test_arcface_consistency(arcface_model, mock_aligned_face):
     embedding1 = arcface_model.get_embedding(mock_aligned_face)
     embedding2 = arcface_model.get_embedding(mock_aligned_face)
 
-    assert np.allclose(embedding1, embedding2), "Same input should produce same embedding"
+    assert np.allclose(embedding1, embedding2), 'Same input should produce same embedding'
 
 
 # MobileFace Tests
@@ -106,7 +117,7 @@ def test_mobileface_initialization(mobileface_model):
     """
     Test that the MobileFace model initializes correctly.
     """
-    assert mobileface_model is not None, "MobileFace model initialization failed."
+    assert mobileface_model is not None, 'MobileFace model initialization failed.'
 
 
 def test_mobileface_embedding_shape(mobileface_model, mock_aligned_face):
@@ -116,8 +127,8 @@ def test_mobileface_embedding_shape(mobileface_model, mock_aligned_face):
     embedding = mobileface_model.get_embedding(mock_aligned_face)
 
     # MobileFace typically produces 512-dimensional embeddings
-    assert embedding.shape[1] == 512, f"Expected 512-dim embedding, got {embedding.shape[1]}"
-    assert embedding.shape[0] == 1, "Embedding should have batch dimension of 1"
+    assert embedding.shape[1] == 512, f'Expected 512-dim embedding, got {embedding.shape[1]}'
+    assert embedding.shape[0] == 1, 'Embedding should have batch dimension of 1'
 
 
 def test_mobileface_normalized_embedding(mobileface_model, mock_landmarks):
@@ -129,7 +140,7 @@ def test_mobileface_normalized_embedding(mobileface_model, mock_landmarks):
     embedding = mobileface_model.get_normalized_embedding(mock_image, mock_landmarks)
 
     norm = np.linalg.norm(embedding)
-    assert np.isclose(norm, 1.0, atol=1e-5), f"Normalized embedding should have norm 1.0, got {norm}"
+    assert np.isclose(norm, 1.0, atol=1e-5), f'Normalized embedding should have norm 1.0, got {norm}'
 
 
 # SphereFace Tests
@@ -137,7 +148,7 @@ def test_sphereface_initialization(sphereface_model):
     """
     Test that the SphereFace model initializes correctly.
     """
-    assert sphereface_model is not None, "SphereFace model initialization failed."
+    assert sphereface_model is not None, 'SphereFace model initialization failed.'
 
 
 def test_sphereface_embedding_shape(sphereface_model, mock_aligned_face):
@@ -147,8 +158,8 @@ def test_sphereface_embedding_shape(sphereface_model, mock_aligned_face):
     embedding = sphereface_model.get_embedding(mock_aligned_face)
 
     # SphereFace typically produces 512-dimensional embeddings
-    assert embedding.shape[1] == 512, f"Expected 512-dim embedding, got {embedding.shape[1]}"
-    assert embedding.shape[0] == 1, "Embedding should have batch dimension of 1"
+    assert embedding.shape[1] == 512, f'Expected 512-dim embedding, got {embedding.shape[1]}'
+    assert embedding.shape[0] == 1, 'Embedding should have batch dimension of 1'
 
 
 def test_sphereface_normalized_embedding(sphereface_model, mock_landmarks):
@@ -160,7 +171,7 @@ def test_sphereface_normalized_embedding(sphereface_model, mock_landmarks):
     embedding = sphereface_model.get_normalized_embedding(mock_image, mock_landmarks)
 
     norm = np.linalg.norm(embedding)
-    assert np.isclose(norm, 1.0, atol=1e-5), f"Normalized embedding should have norm 1.0, got {norm}"
+    assert np.isclose(norm, 1.0, atol=1e-5), f'Normalized embedding should have norm 1.0, got {norm}'
 
 
 # Cross-model comparison tests
@@ -173,8 +184,7 @@ def test_different_models_different_embeddings(arcface_model, mobileface_model,
 
     # Embeddings should be different (with high probability for random input)
     # We check that they're not identical
-    assert not np.allclose(arcface_emb, mobileface_emb), \
-        "Different models should produce different embeddings"
+    assert not np.allclose(arcface_emb, mobileface_emb), 'Different models should produce different embeddings'
 
 
 def test_embedding_similarity_computation(arcface_model, mock_aligned_face):
@@ -191,10 +201,11 @@ def test_embedding_similarity_computation(arcface_model, mock_aligned_face):
 
     # Compute cosine similarity
     from uniface import compute_similarity
+
     similarity = compute_similarity(emb1, emb2)
 
     # Similarity should be between -1 and 1
-    assert -1.0 <= similarity <= 1.0, f"Similarity should be in [-1, 1], got {similarity}"
+    assert -1.0 <= similarity <= 1.0, f'Similarity should be in [-1, 1], got {similarity}'
 
 
 def test_same_face_high_similarity(arcface_model, mock_aligned_face):
@@ -205,7 +216,8 @@ def test_same_face_high_similarity(arcface_model, mock_aligned_face):
     emb2 = arcface_model.get_embedding(mock_aligned_face)
 
     from uniface import compute_similarity
+
     similarity = compute_similarity(emb1, emb2)
 
     # Same image should have similarity close to 1.0
-    assert similarity > 0.99, f"Same face should have similarity > 0.99, got {similarity}"
+    assert similarity > 0.99, f'Same face should have similarity > 0.99, got {similarity}'

tests/test_retinaface.py

@@ -1,3 +1,11 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Tests for RetinaFace detector."""
+
+from __future__ import annotations
+
 import numpy as np
 import pytest
 
@@ -9,35 +17,35 @@ from uniface.detection import RetinaFace
 def retinaface_model():
     return RetinaFace(
         model_name=RetinaFaceWeights.MNET_V2,
-        conf_thresh=0.5,
+        confidence_threshold=0.5,
         pre_nms_topk=5000,
-        nms_thresh=0.4,
+        nms_threshold=0.4,
         post_nms_topk=750,
     )
 
 
 def test_model_initialization(retinaface_model):
-    assert retinaface_model is not None, "Model initialization failed."
+    assert retinaface_model is not None, 'Model initialization failed.'
 
 
 def test_inference_on_640x640_image(retinaface_model):
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
     faces = retinaface_model.detect(mock_image)
 
-    assert isinstance(faces, list), "Detections should be a list."
+    assert isinstance(faces, list), 'Detections should be a list.'
 
     for face in faces:
-        assert isinstance(face, dict), "Each detection should be a dictionary."
-        assert "bbox" in face, "Each detection should have a 'bbox' key."
-        assert "confidence" in face, "Each detection should have a 'confidence' key."
-        assert "landmarks" in face, "Each detection should have a 'landmarks' key."
+        # Face is a dataclass, check attributes exist
+        assert hasattr(face, 'bbox'), "Each detection should have a 'bbox' attribute."
+        assert hasattr(face, 'confidence'), "Each detection should have a 'confidence' attribute."
+        assert hasattr(face, 'landmarks'), "Each detection should have a 'landmarks' attribute."
 
-        bbox = face["bbox"]
-        assert len(bbox) == 4, "BBox should have 4 values (x1, y1, x2, y2)."
+        bbox = face.bbox
+        assert len(bbox) == 4, 'BBox should have 4 values (x1, y1, x2, y2).'
 
-        landmarks = face["landmarks"]
-        assert len(landmarks) == 5, "Should have 5 landmark points."
-        assert all(len(pt) == 2 for pt in landmarks), "Each landmark should be (x, y)."
+        landmarks = face.landmarks
+        assert len(landmarks) == 5, 'Should have 5 landmark points.'
+        assert all(len(pt) == 2 for pt in landmarks), 'Each landmark should be (x, y).'
 
 
 def test_confidence_threshold(retinaface_model):
@@ -45,11 +53,11 @@ def test_confidence_threshold(retinaface_model):
     faces = retinaface_model.detect(mock_image)
 
     for face in faces:
-        confidence = face["confidence"]
-        assert confidence >= 0.5, f"Detection has confidence {confidence} below threshold 0.5"
+        confidence = face.confidence
+        assert confidence >= 0.5, f'Detection has confidence {confidence} below threshold 0.5'
 
 
 def test_no_faces_detected(retinaface_model):
     empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
     faces = retinaface_model.detect(empty_image)
-    assert len(faces) == 0, "Should detect no faces in a blank image."
+    assert len(faces) == 0, 'Should detect no faces in a blank image.'

tests/test_scrfd.py

@@ -1,3 +1,11 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Tests for SCRFD detector."""
+
+from __future__ import annotations
+
 import numpy as np
 import pytest
 
@@ -9,33 +17,33 @@ from uniface.detection import SCRFD
 def scrfd_model():
     return SCRFD(
         model_name=SCRFDWeights.SCRFD_500M_KPS,
-        conf_thresh=0.5,
-        nms_thresh=0.4,
+        confidence_threshold=0.5,
+        nms_threshold=0.4,
     )
 
 
 def test_model_initialization(scrfd_model):
-    assert scrfd_model is not None, "Model initialization failed."
+    assert scrfd_model is not None, 'Model initialization failed.'
 
 
 def test_inference_on_640x640_image(scrfd_model):
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
     faces = scrfd_model.detect(mock_image)
 
-    assert isinstance(faces, list), "Detections should be a list."
+    assert isinstance(faces, list), 'Detections should be a list.'
 
     for face in faces:
-        assert isinstance(face, dict), "Each detection should be a dictionary."
-        assert "bbox" in face, "Each detection should have a 'bbox' key."
-        assert "confidence" in face, "Each detection should have a 'confidence' key."
-        assert "landmarks" in face, "Each detection should have a 'landmarks' key."
+        # Face is a dataclass, check attributes exist
+        assert hasattr(face, 'bbox'), "Each detection should have a 'bbox' attribute."
+        assert hasattr(face, 'confidence'), "Each detection should have a 'confidence' attribute."
+        assert hasattr(face, 'landmarks'), "Each detection should have a 'landmarks' attribute."
 
-        bbox = face["bbox"]
-        assert len(bbox) == 4, "BBox should have 4 values (x1, y1, x2, y2)."
+        bbox = face.bbox
+        assert len(bbox) == 4, 'BBox should have 4 values (x1, y1, x2, y2).'
 
-        landmarks = face["landmarks"]
-        assert len(landmarks) == 5, "Should have 5 landmark points."
-        assert all(len(pt) == 2 for pt in landmarks), "Each landmark should be (x, y)."
+        landmarks = face.landmarks
+        assert len(landmarks) == 5, 'Should have 5 landmark points.'
+        assert all(len(pt) == 2 for pt in landmarks), 'Each landmark should be (x, y).'
 
 
 def test_confidence_threshold(scrfd_model):
@@ -43,14 +51,14 @@ def test_confidence_threshold(scrfd_model):
     faces = scrfd_model.detect(mock_image)
 
     for face in faces:
-        confidence = face["confidence"]
-        assert confidence >= 0.5, f"Detection has confidence {confidence} below threshold 0.5"
+        confidence = face.confidence
+        assert confidence >= 0.5, f'Detection has confidence {confidence} below threshold 0.5'
 
 
 def test_no_faces_detected(scrfd_model):
     empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
     faces = scrfd_model.detect(empty_image)
-    assert len(faces) == 0, "Should detect no faces in a blank image."
+    assert len(faces) == 0, 'Should detect no faces in a blank image.'
 
 
 def test_different_input_sizes(scrfd_model):
@@ -59,13 +67,13 @@ def test_different_input_sizes(scrfd_model):
     for size in test_sizes:
         mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
         faces = scrfd_model.detect(mock_image)
-        assert isinstance(faces, list), f"Should return list for size {size}"
+        assert isinstance(faces, list), f'Should return list for size {size}'
 
 
 def test_scrfd_10g_model():
-    model = SCRFD(model_name=SCRFDWeights.SCRFD_10G_KPS, conf_thresh=0.5)
-    assert model is not None, "SCRFD 10G model initialization failed."
+    model = SCRFD(model_name=SCRFDWeights.SCRFD_10G_KPS, confidence_threshold=0.5)
+    assert model is not None, 'SCRFD 10G model initialization failed.'
 
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
     faces = model.detect(mock_image)
-    assert isinstance(faces, list), "SCRFD 10G should return list of detections."
+    assert isinstance(faces, list), 'SCRFD 10G should return list of detections.'

tests/test_types.py

@@ -0,0 +1,282 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Tests for UniFace type definitions (dataclasses)."""
+
+from __future__ import annotations
+
+import numpy as np
+import pytest
+
+from uniface.types import AttributeResult, EmotionResult, Face, GazeResult, SpoofingResult
+
+
+class TestGazeResult:
+    """Tests for GazeResult dataclass."""
+
+    def test_creation(self):
+        result = GazeResult(pitch=0.1, yaw=-0.2)
+        assert result.pitch == 0.1
+        assert result.yaw == -0.2
+
+    def test_immutability(self):
+        result = GazeResult(pitch=0.1, yaw=-0.2)
+        with pytest.raises(AttributeError):
+            result.pitch = 0.5  # type: ignore
+
+    def test_repr(self):
+        result = GazeResult(pitch=0.1234, yaw=-0.5678)
+        repr_str = repr(result)
+        assert 'GazeResult' in repr_str
+        assert '0.1234' in repr_str
+        assert '-0.5678' in repr_str
+
+    def test_equality(self):
+        result1 = GazeResult(pitch=0.1, yaw=-0.2)
+        result2 = GazeResult(pitch=0.1, yaw=-0.2)
+        assert result1 == result2
+
+    def test_hashable(self):
+        """Frozen dataclasses should be hashable."""
+        result = GazeResult(pitch=0.1, yaw=-0.2)
+        # Should not raise
+        hash(result)
+        # Can be used in sets/dicts
+        result_set = {result}
+        assert result in result_set
+
+
+class TestSpoofingResult:
+    """Tests for SpoofingResult dataclass."""
+
+    def test_creation_real(self):
+        result = SpoofingResult(is_real=True, confidence=0.95)
+        assert result.is_real is True
+        assert result.confidence == 0.95
+
+    def test_creation_fake(self):
+        result = SpoofingResult(is_real=False, confidence=0.87)
+        assert result.is_real is False
+        assert result.confidence == 0.87
+
+    def test_immutability(self):
+        result = SpoofingResult(is_real=True, confidence=0.95)
+        with pytest.raises(AttributeError):
+            result.is_real = False  # type: ignore
+
+    def test_repr_real(self):
+        result = SpoofingResult(is_real=True, confidence=0.9512)
+        repr_str = repr(result)
+        assert 'SpoofingResult' in repr_str
+        assert 'Real' in repr_str
+        assert '0.9512' in repr_str
+
+    def test_repr_fake(self):
+        result = SpoofingResult(is_real=False, confidence=0.8765)
+        repr_str = repr(result)
+        assert 'Fake' in repr_str
+
+    def test_hashable(self):
+        result = SpoofingResult(is_real=True, confidence=0.95)
+        hash(result)
+
+
+class TestEmotionResult:
+    """Tests for EmotionResult dataclass."""
+
+    def test_creation(self):
+        result = EmotionResult(emotion='Happy', confidence=0.92)
+        assert result.emotion == 'Happy'
+        assert result.confidence == 0.92
+
+    def test_immutability(self):
+        result = EmotionResult(emotion='Sad', confidence=0.75)
+        with pytest.raises(AttributeError):
+            result.emotion = 'Happy'  # type: ignore
+
+    def test_repr(self):
+        result = EmotionResult(emotion='Angry', confidence=0.8123)
+        repr_str = repr(result)
+        assert 'EmotionResult' in repr_str
+        assert 'Angry' in repr_str
+        assert '0.8123' in repr_str
+
+    def test_various_emotions(self):
+        emotions = ['Neutral', 'Happy', 'Sad', 'Surprise', 'Fear', 'Disgust', 'Angry']
+        for emotion in emotions:
+            result = EmotionResult(emotion=emotion, confidence=0.5)
+            assert result.emotion == emotion
+
+    def test_hashable(self):
+        result = EmotionResult(emotion='Happy', confidence=0.92)
+        hash(result)
+
+
+class TestAttributeResult:
+    """Tests for AttributeResult dataclass."""
+
+    def test_age_gender_result(self):
+        result = AttributeResult(gender=1, age=25)
+        assert result.gender == 1
+        assert result.age == 25
+        assert result.age_group is None
+        assert result.race is None
+        assert result.sex == 'Male'
+
+    def test_fairface_result(self):
+        result = AttributeResult(gender=0, age_group='20-29', race='East Asian')
+        assert result.gender == 0
+        assert result.age is None
+        assert result.age_group == '20-29'
+        assert result.race == 'East Asian'
+        assert result.sex == 'Female'
+
+    def test_sex_property_female(self):
+        result = AttributeResult(gender=0)
+        assert result.sex == 'Female'
+
+    def test_sex_property_male(self):
+        result = AttributeResult(gender=1)
+        assert result.sex == 'Male'
+
+    def test_immutability(self):
+        result = AttributeResult(gender=1, age=30)
+        with pytest.raises(AttributeError):
+            result.age = 31  # type: ignore
+
+    def test_repr_age_gender(self):
+        result = AttributeResult(gender=1, age=25)
+        repr_str = repr(result)
+        assert 'AttributeResult' in repr_str
+        assert 'Male' in repr_str
+        assert 'age=25' in repr_str
+
+    def test_repr_fairface(self):
+        result = AttributeResult(gender=0, age_group='30-39', race='White')
+        repr_str = repr(result)
+        assert 'Female' in repr_str
+        assert 'age_group=30-39' in repr_str
+        assert 'race=White' in repr_str
+
+    def test_hashable(self):
+        result = AttributeResult(gender=1, age=25)
+        hash(result)
+
+
+class TestFace:
+    """Tests for Face dataclass."""
+
+    @pytest.fixture
+    def sample_face(self):
+        return Face(
+            bbox=np.array([100, 100, 200, 200]),
+            confidence=0.95,
+            landmarks=np.array([[120, 130], [180, 130], [150, 160], [130, 180], [170, 180]]),
+        )
+
+    def test_creation(self, sample_face):
+        assert sample_face.confidence == 0.95
+        assert sample_face.bbox.shape == (4,)
+        assert sample_face.landmarks.shape == (5, 2)
+
+    def test_optional_attributes_default_none(self, sample_face):
+        assert sample_face.embedding is None
+        assert sample_face.gender is None
+        assert sample_face.age is None
+        assert sample_face.age_group is None
+        assert sample_face.race is None
+        assert sample_face.emotion is None
+        assert sample_face.emotion_confidence is None
+
+    def test_mutability(self, sample_face):
+        """Face should be mutable for FaceAnalyzer enrichment."""
+        sample_face.gender = 1
+        sample_face.age = 25
+        sample_face.embedding = np.random.randn(512)
+
+        assert sample_face.gender == 1
+        assert sample_face.age == 25
+        assert sample_face.embedding.shape == (512,)
+
+    def test_sex_property_none(self, sample_face):
+        assert sample_face.sex is None
+
+    def test_sex_property_female(self, sample_face):
+        sample_face.gender = 0
+        assert sample_face.sex == 'Female'
+
+    def test_sex_property_male(self, sample_face):
+        sample_face.gender = 1
+        assert sample_face.sex == 'Male'
+
+    def test_bbox_xyxy(self, sample_face):
+        bbox_xyxy = sample_face.bbox_xyxy
+        np.testing.assert_array_equal(bbox_xyxy, [100, 100, 200, 200])
+
+    def test_bbox_xywh(self, sample_face):
+        bbox_xywh = sample_face.bbox_xywh
+        np.testing.assert_array_equal(bbox_xywh, [100, 100, 100, 100])
+
+    def test_to_dict(self, sample_face):
+        result = sample_face.to_dict()
+        assert isinstance(result, dict)
+        assert 'bbox' in result
+        assert 'confidence' in result
+        assert 'landmarks' in result
+
+    def test_repr_minimal(self, sample_face):
+        repr_str = repr(sample_face)
+        assert 'Face' in repr_str
+        assert 'confidence=0.950' in repr_str
+
+    def test_repr_with_attributes(self, sample_face):
+        sample_face.gender = 1
+        sample_face.age = 30
+        sample_face.emotion = 'Happy'
+
+        repr_str = repr(sample_face)
+        assert 'age=30' in repr_str
+        assert 'sex=Male' in repr_str
+        assert 'emotion=Happy' in repr_str
+
+    def test_compute_similarity_no_embeddings(self, sample_face):
+        other_face = Face(
+            bbox=np.array([50, 50, 150, 150]),
+            confidence=0.90,
+            landmarks=np.random.randn(5, 2),
+        )
+        with pytest.raises(ValueError, match='Both faces must have embeddings'):
+            sample_face.compute_similarity(other_face)
+
+    def test_compute_similarity_with_embeddings(self, sample_face):
+        # Create normalized embeddings
+        sample_face.embedding = np.random.randn(512)
+        sample_face.embedding /= np.linalg.norm(sample_face.embedding)
+
+        other_face = Face(
+            bbox=np.array([50, 50, 150, 150]),
+            confidence=0.90,
+            landmarks=np.random.randn(5, 2),
+        )
+        other_face.embedding = np.random.randn(512)
+        other_face.embedding /= np.linalg.norm(other_face.embedding)
+
+        similarity = sample_face.compute_similarity(other_face)
+        assert isinstance(similarity, float)
+        assert -1 <= similarity <= 1
+
+    def test_compute_similarity_same_embedding(self, sample_face):
+        embedding = np.random.randn(512)
+        embedding /= np.linalg.norm(embedding)
+        sample_face.embedding = embedding.copy()
+
+        other_face = Face(
+            bbox=np.array([50, 50, 150, 150]),
+            confidence=0.90,
+            landmarks=np.random.randn(5, 2),
+            embedding=embedding.copy(),
+        )
+
+        similarity = sample_face.compute_similarity(other_face)
+        assert similarity == pytest.approx(1.0, abs=1e-5)

tests/test_utils.py

@@ -1,3 +1,11 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Tests for utility functions (compute_similarity, face_alignment, etc.)."""
+
+from __future__ import annotations
+
 import numpy as np
 import pytest
 
@@ -18,13 +26,16 @@ def mock_landmarks():
     Create mock 5-point facial landmarks.
     Standard positions for a face roughly centered at (112/2, 112/2).
     """
-    return np.array([
-        [38.2946, 51.6963],  # Left eye
-        [73.5318, 51.5014],  # Right eye
-        [56.0252, 71.7366],  # Nose
-        [41.5493, 92.3655],  # Left mouth corner
-        [70.7299, 92.2041]   # Right mouth corner
-    ], dtype=np.float32)
+    return np.array(
+        [
+            [38.2946, 51.6963],  # Left eye
+            [73.5318, 51.5014],  # Right eye
+            [56.0252, 71.7366],  # Nose
+            [41.5493, 92.3655],  # Left mouth corner
+            [70.7299, 92.2041],  # Right mouth corner
+        ],
+        dtype=np.float32,
+    )
 
 
 # compute_similarity tests
@@ -36,7 +47,7 @@ def test_compute_similarity_same_embedding():
     embedding = embedding / np.linalg.norm(embedding)  # Normalize
 
     similarity = compute_similarity(embedding, embedding)
-    assert np.isclose(similarity, 1.0, atol=1e-5), f"Self-similarity should be 1.0, got {similarity}"
+    assert np.isclose(similarity, 1.0, atol=1e-5), f'Self-similarity should be 1.0, got {similarity}'
 
 
 def test_compute_similarity_range():
@@ -53,7 +64,7 @@ def test_compute_similarity_range():
         emb2 = emb2 / np.linalg.norm(emb2)
 
         similarity = compute_similarity(emb1, emb2)
-        assert -1.0 <= similarity <= 1.0, f"Similarity should be in [-1, 1], got {similarity}"
+        assert -1.0 <= similarity <= 1.0, f'Similarity should be in [-1, 1], got {similarity}'
 
 
 def test_compute_similarity_orthogonal():
@@ -68,7 +79,7 @@ def test_compute_similarity_orthogonal():
     emb2[0, 1] = 1.0  # [0, 1, 0, ..., 0]
 
     similarity = compute_similarity(emb1, emb2)
-    assert np.isclose(similarity, 0.0, atol=1e-5), f"Orthogonal embeddings should have similarity 0.0, got {similarity}"
+    assert np.isclose(similarity, 0.0, atol=1e-5), f'Orthogonal embeddings should have similarity 0.0, got {similarity}'
 
 
 def test_compute_similarity_opposite():
@@ -81,7 +92,7 @@ def test_compute_similarity_opposite():
     emb2 = -emb1  # Opposite direction
 
     similarity = compute_similarity(emb1, emb2)
-    assert np.isclose(similarity, -1.0, atol=1e-5), f"Opposite embeddings should have similarity -1.0, got {similarity}"
+    assert np.isclose(similarity, -1.0, atol=1e-5), f'Opposite embeddings should have similarity -1.0, got {similarity}'
 
 
 def test_compute_similarity_symmetry():
@@ -98,7 +109,7 @@ def test_compute_similarity_symmetry():
     sim_12 = compute_similarity(emb1, emb2)
     sim_21 = compute_similarity(emb2, emb1)
 
-    assert np.isclose(sim_12, sim_21), "Similarity should be symmetric"
+    assert np.isclose(sim_12, sim_21), 'Similarity should be symmetric'
 
 
 def test_compute_similarity_dtype():
@@ -113,7 +124,7 @@ def test_compute_similarity_dtype():
     emb2 = emb2 / np.linalg.norm(emb2)
 
     similarity = compute_similarity(emb1, emb2)
-    assert isinstance(similarity, (float, np.floating)), f"Similarity should be float, got {type(similarity)}"
+    assert isinstance(similarity, float | np.floating), f'Similarity should be float, got {type(similarity)}'
 
 
 # face_alignment tests
@@ -123,7 +134,7 @@ def test_face_alignment_output_shape(mock_image, mock_landmarks):
     """
     aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
 
-    assert aligned.shape == (112, 112, 3), f"Expected shape (112, 112, 3), got {aligned.shape}"
+    assert aligned.shape == (112, 112, 3), f'Expected shape (112, 112, 3), got {aligned.shape}'
 
 
 def test_face_alignment_dtype(mock_image, mock_landmarks):
@@ -132,7 +143,7 @@ def test_face_alignment_dtype(mock_image, mock_landmarks):
     """
     aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
 
-    assert aligned.dtype == np.uint8, f"Expected uint8, got {aligned.dtype}"
+    assert aligned.dtype == np.uint8, f'Expected uint8, got {aligned.dtype}'
 
 
 def test_face_alignment_different_sizes(mock_image, mock_landmarks):
@@ -144,7 +155,7 @@ def test_face_alignment_different_sizes(mock_image, mock_landmarks):
 
     for size in test_sizes:
         aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=size)
-        assert aligned.shape == (*size, 3), f"Failed for size {size}"
+        assert aligned.shape == (*size, 3), f'Failed for size {size}'
 
 
 def test_face_alignment_consistency(mock_image, mock_landmarks):
@@ -154,7 +165,7 @@ def test_face_alignment_consistency(mock_image, mock_landmarks):
     aligned1, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
     aligned2, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
 
-    assert np.allclose(aligned1, aligned2), "Same input should produce same aligned face"
+    assert np.allclose(aligned1, aligned2), 'Same input should produce same aligned face'
 
 
 def test_face_alignment_landmarks_as_list(mock_image):
@@ -166,13 +177,13 @@ def test_face_alignment_landmarks_as_list(mock_image):
         [73.5318, 51.5014],
         [56.0252, 71.7366],
         [41.5493, 92.3655],
-        [70.7299, 92.2041]
+        [70.7299, 92.2041],
     ]
 
     # Convert list to numpy array before passing to face_alignment
     landmarks_array = np.array(landmarks_list, dtype=np.float32)
     aligned, _ = face_alignment(mock_image, landmarks_array, image_size=(112, 112))
-    assert aligned.shape == (112, 112, 3), "Should work with landmarks as array"
+    assert aligned.shape == (112, 112, 3), 'Should work with landmarks as array'
 
 
 def test_face_alignment_value_range(mock_image, mock_landmarks):
@@ -181,8 +192,8 @@ def test_face_alignment_value_range(mock_image, mock_landmarks):
     """
     aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
 
-    assert np.all(aligned >= 0), "Pixel values should be >= 0"
-    assert np.all(aligned <= 255), "Pixel values should be <= 255"
+    assert np.all(aligned >= 0), 'Pixel values should be >= 0'
+    assert np.all(aligned <= 255), 'Pixel values should be <= 255'
 
 
 def test_face_alignment_not_all_zeros(mock_image, mock_landmarks):
@@ -192,7 +203,7 @@ def test_face_alignment_not_all_zeros(mock_image, mock_landmarks):
     aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
 
     # At least some pixels should be non-zero
-    assert np.any(aligned > 0), "Aligned face should have some non-zero pixels"
+    assert np.any(aligned > 0), 'Aligned face should have some non-zero pixels'
 
 
 def test_face_alignment_from_different_positions(mock_image):
@@ -201,14 +212,23 @@ def test_face_alignment_from_different_positions(mock_image):
     """
     # Landmarks at different positions
     positions = [
-        np.array([[100, 100], [150, 100], [125, 130], [110, 150], [140, 150]], dtype=np.float32),
-        np.array([[300, 200], [350, 200], [325, 230], [310, 250], [340, 250]], dtype=np.float32),
-        np.array([[500, 400], [550, 400], [525, 430], [510, 450], [540, 450]], dtype=np.float32),
+        np.array(
+            [[100, 100], [150, 100], [125, 130], [110, 150], [140, 150]],
+            dtype=np.float32,
+        ),
+        np.array(
+            [[300, 200], [350, 200], [325, 230], [310, 250], [340, 250]],
+            dtype=np.float32,
+        ),
+        np.array(
+            [[500, 400], [550, 400], [525, 430], [510, 450], [540, 450]],
+            dtype=np.float32,
+        ),
     ]
 
     for landmarks in positions:
         aligned, _ = face_alignment(mock_image, landmarks, image_size=(112, 112))
-        assert aligned.shape == (112, 112, 3), f"Failed for landmarks at {landmarks[0]}"
+        assert aligned.shape == (112, 112, 3), f'Failed for landmarks at {landmarks[0]}'
 
 
 def test_face_alignment_landmark_count(mock_image):
@@ -216,16 +236,19 @@ def test_face_alignment_landmark_count(mock_image):
     Test that face_alignment works specifically with 5-point landmarks.
     """
     # Standard 5-point landmarks
-    landmarks_5pt = np.array([
-        [38.2946, 51.6963],
-        [73.5318, 51.5014],
-        [56.0252, 71.7366],
-        [41.5493, 92.3655],
-        [70.7299, 92.2041]
-    ], dtype=np.float32)
+    landmarks_5pt = np.array(
+        [
+            [38.2946, 51.6963],
+            [73.5318, 51.5014],
+            [56.0252, 71.7366],
+            [41.5493, 92.3655],
+            [70.7299, 92.2041],
+        ],
+        dtype=np.float32,
+    )
 
     aligned, _ = face_alignment(mock_image, landmarks_5pt, image_size=(112, 112))
-    assert aligned.shape == (112, 112, 3), "Should work with 5-point landmarks"
+    assert aligned.shape == (112, 112, 3), 'Should work with 5-point landmarks'
 
 
 def test_compute_similarity_with_recognition_embeddings():
@@ -244,4 +267,4 @@ def test_compute_similarity_with_recognition_embeddings():
 
     # Should be a valid similarity score
     assert -1.0 <= similarity <= 1.0
-    assert isinstance(similarity, (float, np.floating))
+    assert isinstance(similarity, float | np.floating)

tools/README.md

@@ -0,0 +1,121 @@
+# Tools
+
+CLI utilities for testing and running UniFace features.
+
+## Available Tools
+
+| Tool | Description |
+|------|-------------|
+| `detection.py` | Face detection on image, video, or webcam |
+| `face_anonymize.py` | Face anonymization/blurring for privacy |
+| `age_gender.py` | Age and gender prediction |
+| `face_emotion.py` | Emotion detection (7 or 8 emotions) |
+| `gaze_estimation.py` | Gaze direction estimation |
+| `landmarks.py` | 106-point facial landmark detection |
+| `recognition.py` | Face embedding extraction and comparison |
+| `face_analyzer.py` | Complete face analysis (detection + recognition + attributes) |
+| `face_search.py` | Real-time face matching against reference |
+| `fairface.py` | FairFace attribute prediction (race, gender, age) |
+| `spoofing.py` | Face anti-spoofing detection |
+| `face_parsing.py` | Face semantic segmentation |
+| `video_detection.py` | Face detection on video files with progress bar |
+| `batch_process.py` | Batch process folder of images |
+| `download_model.py` | Download model weights |
+| `sha256_generate.py` | Generate SHA256 hash for model files |
+
+## Unified `--source` Pattern
+
+All tools use a unified `--source` argument that accepts:
+- **Image path**: `--source photo.jpg`
+- **Video path**: `--source video.mp4`
+- **Camera ID**: `--source 0` (default webcam), `--source 1` (external camera)
+
+## Usage Examples
+
+```bash
+# Face detection
+python tools/detection.py --source assets/test.jpg           # image
+python tools/detection.py --source video.mp4                 # video
+python tools/detection.py --source 0                         # webcam
+
+# Face anonymization
+python tools/face_anonymize.py --source assets/test.jpg --method pixelate
+python tools/face_anonymize.py --source video.mp4 --method gaussian
+python tools/face_anonymize.py --source 0 --method pixelate
+
+# Age and gender
+python tools/age_gender.py --source assets/test.jpg
+python tools/age_gender.py --source 0
+
+# Emotion detection
+python tools/face_emotion.py --source assets/test.jpg
+python tools/face_emotion.py --source 0
+
+# Gaze estimation
+python tools/gaze_estimation.py --source assets/test.jpg
+python tools/gaze_estimation.py --source 0
+
+# Landmarks
+python tools/landmarks.py --source assets/test.jpg
+python tools/landmarks.py --source 0
+
+# FairFace attributes
+python tools/fairface.py --source assets/test.jpg
+python tools/fairface.py --source 0
+
+# Face parsing
+python tools/face_parsing.py --source assets/test.jpg
+python tools/face_parsing.py --source 0
+
+# Face anti-spoofing
+python tools/spoofing.py --source assets/test.jpg
+python tools/spoofing.py --source 0
+
+# Face analyzer
+python tools/face_analyzer.py --source assets/test.jpg
+python tools/face_analyzer.py --source 0
+
+# Face recognition (extract embedding)
+python tools/recognition.py --image assets/test.jpg
+
+# Face comparison
+python tools/recognition.py --image1 face1.jpg --image2 face2.jpg
+
+# Face search (match against reference)
+python tools/face_search.py --reference person.jpg --source 0
+python tools/face_search.py --reference person.jpg --source video.mp4
+
+# Video processing with progress bar
+python tools/video_detection.py --source video.mp4
+python tools/video_detection.py --source video.mp4 --output output.mp4
+
+# Batch processing
+python tools/batch_process.py --input images/ --output results/
+
+# Download models
+python tools/download_model.py --model-type retinaface
+python tools/download_model.py  # downloads all
+```
+
+## Common Options
+
+| Option | Description |
+|--------|-------------|
+| `--source` | Input source: image/video path or camera ID (0, 1, ...) |
+| `--detector` | Choose detector: `retinaface`, `scrfd`, `yolov5face` |
+| `--threshold` | Visualization confidence threshold (default: varies) |
+| `--save-dir` | Output directory (default: `outputs`) |
+
+## Supported Formats
+
+**Images:** `.jpg`, `.jpeg`, `.png`, `.bmp`, `.webp`, `.tiff`
+
+**Videos:** `.mp4`, `.avi`, `.mov`, `.mkv`, `.webm`, `.flv`
+
+**Camera:** Use integer IDs (`0`, `1`, `2`, ...)
+
+## Quick Test
+
+```bash
+python tools/detection.py --source assets/test.jpg
+```

tools/age_gender.py

@@ -0,0 +1,213 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Age and gender prediction on detected faces.
+
+Usage:
+    python tools/age_gender.py --source path/to/image.jpg
+    python tools/age_gender.py --source path/to/video.mp4
+    python tools/age_gender.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+
+from uniface import SCRFD, AgeGender, RetinaFace
+from uniface.visualization import draw_detections
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def draw_age_gender_label(image, bbox, sex: str, age: int):
+    """Draw age/gender label above the bounding box."""
+    x1, y1 = int(bbox[0]), int(bbox[1])
+    text = f'{sex}, {age}y'
+    (tw, th), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
+    cv2.rectangle(image, (x1, y1 - th - 10), (x1 + tw + 10, y1), (0, 255, 0), -1)
+    cv2.putText(image, text, (x1 + 5, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)
+
+
+def process_image(
+    detector,
+    age_gender,
+    image_path: str,
+    save_dir: str = 'outputs',
+    threshold: float = 0.6,
+):
+    """Process a single image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        return
+
+    bboxes = [f.bbox for f in faces]
+    scores = [f.confidence for f in faces]
+    landmarks = [f.landmarks for f in faces]
+    draw_detections(
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+    )
+
+    for i, face in enumerate(faces):
+        result = age_gender.predict(image, face.bbox)
+        print(f'  Face {i + 1}: {result.sex}, {result.age} years old')
+        draw_age_gender_label(image, face.bbox, result.sex, result.age)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_age_gender.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def process_video(
+    detector,
+    age_gender,
+    video_path: str,
+    save_dir: str = 'outputs',
+    threshold: float = 0.6,
+):
+    """Process a video file."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_age_gender.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        )
+
+        for face in faces:
+            result = age_gender.predict(frame, face.bbox)
+            draw_age_gender_label(frame, face.bbox, result.sex, result.age)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, age_gender, camera_id: int = 0, threshold: float = 0.6):
+    """Run real-time detection on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        )
+
+        for face in faces:
+            result = age_gender.predict(frame, face.bbox)
+            draw_age_gender_label(frame, face.bbox, result.sex, result.age)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('Age & Gender Detection', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Run age and gender detection')
+    parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--threshold', type=float, default=0.6, help='Visualization threshold')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    args = parser.parse_args()
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    age_gender = AgeGender()
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, age_gender, int(args.source), args.threshold)
+    elif source_type == 'image':
+        if not os.path.exists(args.source):
+            print(f'Error: Image not found: {args.source}')
+            return
+        process_image(detector, age_gender, args.source, args.save_dir, args.threshold)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, age_gender, args.source, args.save_dir, args.threshold)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/batch_process.py

@@ -0,0 +1,105 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Batch face detection on a folder of images.
+
+Usage:
+    python tools/batch_process.py --input images/ --output results/
+"""
+
+import argparse
+from pathlib import Path
+
+import cv2
+from tqdm import tqdm
+
+from uniface import SCRFD, RetinaFace
+from uniface.visualization import draw_detections
+
+
+def get_image_files(input_dir: Path, extensions: tuple) -> list:
+    files = []
+    for ext in extensions:
+        files.extend(input_dir.glob(f'*.{ext}'))
+        files.extend(input_dir.glob(f'*.{ext.upper()}'))
+    return sorted(files)
+
+
+def process_image(detector, image_path: Path, output_path: Path, threshold: float) -> int:
+    """Process single image. Returns face count or -1 on error."""
+    image = cv2.imread(str(image_path))
+    if image is None:
+        return -1
+
+    faces = detector.detect(image)
+
+    # unpack face data for visualization
+    bboxes = [f.bbox for f in faces]
+    scores = [f.confidence for f in faces]
+    landmarks = [f.landmarks for f in faces]
+    draw_detections(
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+    )
+
+    cv2.putText(
+        image,
+        f'Faces: {len(faces)}',
+        (10, 30),
+        cv2.FONT_HERSHEY_SIMPLEX,
+        1,
+        (0, 255, 0),
+        2,
+    )
+    cv2.imwrite(str(output_path), image)
+
+    return len(faces)
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Batch process images with face detection')
+    parser.add_argument('--input', type=str, required=True, help='Input directory')
+    parser.add_argument('--output', type=str, required=True, help='Output directory')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--threshold', type=float, default=0.6, help='Visualization threshold')
+    parser.add_argument('--extensions', type=str, default='jpg,jpeg,png,bmp', help='Image extensions')
+    args = parser.parse_args()
+
+    input_path = Path(args.input)
+    output_path = Path(args.output)
+
+    if not input_path.exists():
+        print(f"Error: Input directory '{args.input}' does not exist")
+        return
+
+    output_path.mkdir(parents=True, exist_ok=True)
+
+    extensions = tuple(ext.strip() for ext in args.extensions.split(','))
+    image_files = get_image_files(input_path, extensions)
+
+    if not image_files:
+        print(f'No images found with extensions {extensions}')
+        return
+
+    print(f'Found {len(image_files)} images')
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+
+    success, errors, total_faces = 0, 0, 0
+
+    for img_path in tqdm(image_files, desc='Processing', unit='img'):
+        out_path = output_path / f'{img_path.stem}_detected{img_path.suffix}'
+        result = process_image(detector, img_path, out_path, args.threshold)
+
+        if result >= 0:
+            success += 1
+            total_faces += result
+        else:
+            errors += 1
+            print(f'\nFailed: {img_path.name}')
+
+    print(f'\nDone! {success} processed, {errors} errors, {total_faces} faces total')
+
+
+if __name__ == '__main__':
+    main()

tools/detection.py

@@ -0,0 +1,196 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face detection on image, video, or webcam.
+
+Usage:
+    python tools/detection.py --source path/to/image.jpg
+    python tools/detection.py --source path/to/video.mp4
+    python tools/detection.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+
+from uniface.detection import SCRFD, RetinaFace, YOLOv5Face
+from uniface.visualization import draw_detections
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def process_image(detector, image_path: str, threshold: float = 0.6, save_dir: str = 'outputs'):
+    """Process a single image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+
+    if faces:
+        bboxes = [face.bbox for face in faces]
+        scores = [face.confidence for face in faces]
+        landmarks = [face.landmarks for face in faces]
+        draw_detections(image, bboxes, scores, landmarks, vis_threshold=threshold)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{os.path.splitext(os.path.basename(image_path))[0]}_out.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Detected {len(faces)} face(s). Output saved: {output_path}')
+
+
+def process_video(detector, video_path: str, threshold: float = 0.6, save_dir: str = 'outputs'):
+    """Process a video file."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    # Get video properties
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_out.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(
+            image=frame,
+            bboxes=bboxes,
+            scores=scores,
+            landmarks=landmarks,
+            vis_threshold=threshold,
+            draw_score=True,
+            fancy_bbox=True,
+        )
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(frame)
+
+        # Show progress
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, camera_id: int = 0, threshold: float = 0.6):
+    """Run real-time detection on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)  # mirror for natural interaction
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(
+            image=frame,
+            bboxes=bboxes,
+            scores=scores,
+            landmarks=landmarks,
+            vis_threshold=threshold,
+            draw_score=True,
+            fancy_bbox=True,
+        )
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('Face Detection', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Run face detection')
+    parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    parser.add_argument('--method', type=str, default='retinaface', choices=['retinaface', 'scrfd', 'yolov5face'])
+    parser.add_argument('--threshold', type=float, default=0.25, help='Visualization threshold')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    args = parser.parse_args()
+
+    # Initialize detector
+    if args.method == 'retinaface':
+        detector = RetinaFace()
+    elif args.method == 'scrfd':
+        detector = SCRFD()
+    else:
+        from uniface.constants import YOLOv5FaceWeights
+
+        detector = YOLOv5Face(model_name=YOLOv5FaceWeights.YOLOV5M)
+
+    # Determine source type and process
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, int(args.source), args.threshold)
+    elif source_type == 'image':
+        if not os.path.exists(args.source):
+            print(f'Error: Image not found: {args.source}')
+            return
+        process_image(detector, args.source, args.threshold, args.save_dir)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, args.source, args.threshold, args.save_dir)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/download_model.py

@@ -0,0 +1,60 @@
+import argparse
+
+from uniface.constants import (
+    AgeGenderWeights,
+    ArcFaceWeights,
+    DDAMFNWeights,
+    LandmarkWeights,
+    MobileFaceWeights,
+    RetinaFaceWeights,
+    SCRFDWeights,
+    SphereFaceWeights,
+)
+from uniface.model_store import verify_model_weights
+
+MODEL_TYPES = {
+    'retinaface': RetinaFaceWeights,
+    'sphereface': SphereFaceWeights,
+    'mobileface': MobileFaceWeights,
+    'arcface': ArcFaceWeights,
+    'scrfd': SCRFDWeights,
+    'ddamfn': DDAMFNWeights,
+    'agegender': AgeGenderWeights,
+    'landmark': LandmarkWeights,
+}
+
+
+def download_models(model_enum):
+    for weight in model_enum:
+        print(f'Downloading: {weight.value}')
+        try:
+            verify_model_weights(weight)
+            print(f'  Done: {weight.value}')
+        except Exception as e:
+            print(f'  Failed: {e}')
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Download model weights')
+    parser.add_argument(
+        '--model-type',
+        type=str,
+        choices=list(MODEL_TYPES.keys()),
+        help='Model type to download. If not specified, downloads all.',
+    )
+    args = parser.parse_args()
+
+    if args.model_type:
+        print(f'Downloading {args.model_type} models...')
+        download_models(MODEL_TYPES[args.model_type])
+    else:
+        print('Downloading all models...')
+        for name, model_enum in MODEL_TYPES.items():
+            print(f'\n{name}:')
+            download_models(model_enum)
+
+    print('\nDone!')
+
+
+if __name__ == '__main__':
+    main()

tools/face_analyzer.py

@@ -0,0 +1,239 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face analysis using FaceAnalyzer.
+
+Usage:
+    python tools/face_analyzer.py --source path/to/image.jpg
+    python tools/face_analyzer.py --source path/to/video.mp4
+    python tools/face_analyzer.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+from uniface import AgeGender, ArcFace, FaceAnalyzer, RetinaFace
+from uniface.visualization import draw_detections
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def draw_face_info(image, face, face_id):
+    """Draw face ID and attributes above bounding box."""
+    x1, y1, _x2, y2 = map(int, face.bbox)
+    lines = [f'ID: {face_id}', f'Conf: {face.confidence:.2f}']
+    if face.age and face.sex:
+        lines.append(f'{face.sex}, {face.age}y')
+
+    for i, line in enumerate(lines):
+        y_pos = y1 - 10 - (len(lines) - 1 - i) * 25
+        if y_pos < 20:
+            y_pos = y2 + 20 + i * 25
+        (tw, th), _ = cv2.getTextSize(line, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
+        cv2.rectangle(image, (x1, y_pos - th - 5), (x1 + tw + 10, y_pos + 5), (0, 255, 0), -1)
+        cv2.putText(image, line, (x1 + 5, y_pos), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 2)
+
+
+def process_image(analyzer, image_path: str, save_dir: str = 'outputs', show_similarity: bool = True):
+    """Process a single image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = analyzer.analyze(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        return
+
+    for i, face in enumerate(faces, 1):
+        info = f'  Face {i}: {face.sex}, {face.age}y' if face.age and face.sex else f'  Face {i}'
+        if face.embedding is not None:
+            info += f' (embedding: {face.embedding.shape})'
+        print(info)
+
+    if show_similarity and len(faces) >= 2:
+        print('\nSimilarity Matrix:')
+        n = len(faces)
+        sim_matrix = np.zeros((n, n))
+
+        for i in range(n):
+            for j in range(i, n):
+                if i == j:
+                    sim_matrix[i][j] = 1.0
+                else:
+                    sim = faces[i].compute_similarity(faces[j])
+                    sim_matrix[i][j] = sim
+                    sim_matrix[j][i] = sim
+
+        print('     ', end='')
+        for i in range(n):
+            print(f'  F{i + 1:2d}  ', end='')
+        print('\n     ' + '-' * (7 * n))
+
+        for i in range(n):
+            print(f'F{i + 1:2d} | ', end='')
+            for j in range(n):
+                print(f'{sim_matrix[i][j]:6.3f} ', end='')
+            print()
+
+        pairs = [(i, j, sim_matrix[i][j]) for i in range(n) for j in range(i + 1, n)]
+        pairs.sort(key=lambda x: x[2], reverse=True)
+
+        print('\nTop matches (>0.4 = same person):')
+        for i, j, sim in pairs[:3]:
+            status = 'Same' if sim > 0.4 else 'Different'
+            print(f'  Face {i + 1} ↔ Face {j + 1}: {sim:.3f} ({status})')
+
+    bboxes = [f.bbox for f in faces]
+    scores = [f.confidence for f in faces]
+    landmarks = [f.landmarks for f in faces]
+    draw_detections(image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, fancy_bbox=True)
+
+    for i, face in enumerate(faces, 1):
+        draw_face_info(image, face, i)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_analysis.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def process_video(analyzer, video_path: str, save_dir: str = 'outputs'):
+    """Process a video file."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_analysis.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = analyzer.analyze(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, fancy_bbox=True)
+
+        for i, face in enumerate(faces, 1):
+            draw_face_info(frame, face, i)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(analyzer, camera_id: int = 0):
+    """Run real-time analysis on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+        if not ret:
+            break
+
+        faces = analyzer.analyze(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, fancy_bbox=True)
+
+        for i, face in enumerate(faces, 1):
+            draw_face_info(frame, face, i)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('Face Analyzer', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Face analysis with detection, recognition, and attributes')
+    parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    parser.add_argument('--no-similarity', action='store_true', help='Skip similarity matrix computation')
+    args = parser.parse_args()
+
+    detector = RetinaFace()
+    recognizer = ArcFace()
+    age_gender = AgeGender()
+    analyzer = FaceAnalyzer(detector, recognizer, age_gender)
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(analyzer, int(args.source))
+    elif source_type == 'image':
+        if not os.path.exists(args.source):
+            print(f'Error: Image not found: {args.source}')
+            return
+        process_image(analyzer, args.source, args.save_dir, show_similarity=not args.no_similarity)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(analyzer, args.source, args.save_dir)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/face_anonymize.py

@@ -0,0 +1,281 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face anonymization/blurring for privacy.
+
+Usage:
+    python tools/face_anonymize.py --source path/to/image.jpg --method pixelate
+    python tools/face_anonymize.py --source path/to/video.mp4 --method gaussian
+    python tools/face_anonymize.py --source 0 --method pixelate  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+
+from uniface import RetinaFace
+from uniface.privacy import BlurFace
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def process_image(
+    detector,
+    blurrer: BlurFace,
+    image_path: str,
+    save_dir: str = 'outputs',
+    show_detections: bool = False,
+):
+    """Process a single image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if show_detections and faces:
+        from uniface.visualization import draw_detections
+
+        preview = image.copy()
+        bboxes = [face.bbox for face in faces]
+        scores = [face.confidence for face in faces]
+        landmarks = [face.landmarks for face in faces]
+        draw_detections(preview, bboxes, scores, landmarks)
+
+        cv2.imshow('Detections (Press any key to continue)', preview)
+        cv2.waitKey(0)
+        cv2.destroyAllWindows()
+
+    if faces:
+        anonymized = blurrer.anonymize(image, faces)
+    else:
+        anonymized = image
+
+    os.makedirs(save_dir, exist_ok=True)
+    basename = os.path.splitext(os.path.basename(image_path))[0]
+    output_path = os.path.join(save_dir, f'{basename}_anonymized.jpg')
+    cv2.imwrite(output_path, anonymized)
+    print(f'Output saved: {output_path}')
+
+
+def process_video(
+    detector,
+    blurrer: BlurFace,
+    video_path: str,
+    save_dir: str = 'outputs',
+):
+    """Process a video file."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_anonymized.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+
+        if faces:
+            frame = blurrer.anonymize(frame, faces, inplace=True)
+
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, blurrer: BlurFace, camera_id: int = 0):
+    """Run real-time anonymization on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+        if faces:
+            frame = blurrer.anonymize(frame, faces, inplace=True)
+
+        cv2.putText(
+            frame,
+            f'Faces blurred: {len(faces)} | Method: {blurrer.method}',
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.7,
+            (0, 255, 0),
+            2,
+        )
+
+        cv2.imshow('Face Anonymization (Press q to quit)', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description='Face anonymization using various blur methods',
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Anonymize image with pixelation (default)
+  python run_anonymization.py --source photo.jpg
+
+  # Use Gaussian blur with custom strength
+  python run_anonymization.py --source photo.jpg --method gaussian --blur-strength 5.0
+
+  # Real-time webcam anonymization
+  python run_anonymization.py --source 0 --method pixelate
+
+  # Black boxes for maximum privacy
+  python run_anonymization.py --source photo.jpg --method blackout
+
+  # Custom pixelation intensity
+  python run_anonymization.py --source photo.jpg --method pixelate --pixel-blocks 5
+        """,
+    )
+
+    # Input/output
+    parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+
+    # Blur method
+    parser.add_argument(
+        '--method',
+        type=str,
+        default='pixelate',
+        choices=['gaussian', 'pixelate', 'blackout', 'elliptical', 'median'],
+        help='Blur method (default: pixelate)',
+    )
+
+    # Method-specific parameters
+    parser.add_argument(
+        '--blur-strength',
+        type=float,
+        default=3.0,
+        help='Blur strength for gaussian/elliptical/median (default: 3.0)',
+    )
+    parser.add_argument(
+        '--pixel-blocks',
+        type=int,
+        default=20,
+        help='Number of pixel blocks for pixelate (default: 20, lower=more pixelated)',
+    )
+    parser.add_argument(
+        '--color',
+        type=str,
+        default='0,0,0',
+        help='Fill color for blackout as R,G,B (default: 0,0,0 for black)',
+    )
+    parser.add_argument('--margin', type=int, default=20, help='Margin for elliptical blur (default: 20)')
+
+    # Detection
+    parser.add_argument(
+        '--confidence-threshold',
+        type=float,
+        default=0.5,
+        help='Detection confidence threshold (default: 0.5)',
+    )
+
+    # Visualization
+    parser.add_argument(
+        '--show-detections',
+        action='store_true',
+        help='Show detection boxes before blurring (image mode only)',
+    )
+
+    args = parser.parse_args()
+
+    # Parse color
+    color_values = [int(x) for x in args.color.split(',')]
+    if len(color_values) != 3:
+        parser.error('--color must be in format R,G,B (e.g., 0,0,0)')
+    color = tuple(color_values)
+
+    # Initialize detector
+    print(f'Initializing face detector (confidence_threshold={args.confidence_threshold})...')
+    detector = RetinaFace(confidence_threshold=args.confidence_threshold)
+
+    # Initialize blurrer
+    print(f'Initializing blur method: {args.method}')
+    blurrer = BlurFace(
+        method=args.method,
+        blur_strength=args.blur_strength,
+        pixel_blocks=args.pixel_blocks,
+        color=color,
+        margin=args.margin,
+    )
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, blurrer, int(args.source))
+    elif source_type == 'image':
+        if not os.path.exists(args.source):
+            print(f'Error: Image not found: {args.source}')
+            return
+        process_image(detector, blurrer, args.source, args.save_dir, args.show_detections)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, blurrer, args.source, args.save_dir)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/face_emotion.py

@@ -0,0 +1,213 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Emotion detection on detected faces.
+
+Usage:
+    python tools/face_emotion.py --source path/to/image.jpg
+    python tools/face_emotion.py --source path/to/video.mp4
+    python tools/face_emotion.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+
+from uniface import SCRFD, Emotion, RetinaFace
+from uniface.visualization import draw_detections
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def draw_emotion_label(image, bbox, emotion: str, confidence: float):
+    """Draw emotion label above the bounding box."""
+    x1, y1 = int(bbox[0]), int(bbox[1])
+    text = f'{emotion} ({confidence:.2f})'
+    (tw, th), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)
+    cv2.rectangle(image, (x1, y1 - th - 10), (x1 + tw + 10, y1), (255, 0, 0), -1)
+    cv2.putText(image, text, (x1 + 5, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 2)
+
+
+def process_image(
+    detector,
+    emotion_predictor,
+    image_path: str,
+    save_dir: str = 'outputs',
+    threshold: float = 0.6,
+):
+    """Process a single image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        return
+
+    bboxes = [f.bbox for f in faces]
+    scores = [f.confidence for f in faces]
+    landmarks = [f.landmarks for f in faces]
+    draw_detections(
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+    )
+
+    for i, face in enumerate(faces):
+        result = emotion_predictor.predict(image, face.landmarks)
+        print(f'  Face {i + 1}: {result.emotion} (confidence: {result.confidence:.3f})')
+        draw_emotion_label(image, face.bbox, result.emotion, result.confidence)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_emotion.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def process_video(
+    detector,
+    emotion_predictor,
+    video_path: str,
+    save_dir: str = 'outputs',
+    threshold: float = 0.6,
+):
+    """Process a video file."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_emotion.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        )
+
+        for face in faces:
+            result = emotion_predictor.predict(frame, face.landmarks)
+            draw_emotion_label(frame, face.bbox, result.emotion, result.confidence)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, emotion_predictor, camera_id: int = 0, threshold: float = 0.6):
+    """Run real-time detection on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        )
+
+        for face in faces:
+            result = emotion_predictor.predict(frame, face.landmarks)
+            draw_emotion_label(frame, face.bbox, result.emotion, result.confidence)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('Emotion Detection', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Run emotion detection')
+    parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--threshold', type=float, default=0.6, help='Visualization threshold')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    args = parser.parse_args()
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    emotion_predictor = Emotion()
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, emotion_predictor, int(args.source), args.threshold)
+    elif source_type == 'image':
+        if not os.path.exists(args.source):
+            print(f'Error: Image not found: {args.source}')
+            return
+        process_image(detector, emotion_predictor, args.source, args.save_dir, args.threshold)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, emotion_predictor, args.source, args.save_dir, args.threshold)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/face_parsing.py

@@ -0,0 +1,250 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face parsing on detected faces.
+
+Usage:
+    python tools/face_parsing.py --source path/to/image.jpg
+    python tools/face_parsing.py --source path/to/video.mp4
+    python tools/face_parsing.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+from uniface import RetinaFace
+from uniface.constants import ParsingWeights
+from uniface.parsing import BiSeNet
+from uniface.visualization import vis_parsing_maps
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def expand_bbox(
+    bbox: np.ndarray,
+    image_shape: tuple[int, int],
+    expand_ratio: float = 0.2,
+    expand_top_ratio: float = 0.4,
+) -> tuple[int, int, int, int]:
+    """
+    Expand bounding box to include full head region for face parsing.
+
+    Face detection typically returns tight face boxes, but face parsing
+    requires the full head including hair, ears, and neck.
+
+    Args:
+        bbox: Original bounding box [x1, y1, x2, y2].
+        image_shape: Image dimensions as (height, width).
+        expand_ratio: Expansion ratio for left, right, and bottom (default: 0.2 = 20%).
+        expand_top_ratio: Expansion ratio for top to capture hair/forehead (default: 0.4 = 40%).
+
+    Returns:
+        Tuple[int, int, int, int]: Expanded bbox (x1, y1, x2, y2) clamped to image bounds.
+    """
+    x1, y1, x2, y2 = map(int, bbox[:4])
+    height, width = image_shape[:2]
+
+    face_width = x2 - x1
+    face_height = y2 - y1
+
+    expand_x = int(face_width * expand_ratio)
+    expand_y_bottom = int(face_height * expand_ratio)
+    expand_y_top = int(face_height * expand_top_ratio)
+
+    new_x1 = max(0, x1 - expand_x)
+    new_y1 = max(0, y1 - expand_y_top)
+    new_x2 = min(width, x2 + expand_x)
+    new_y2 = min(height, y2 + expand_y_bottom)
+
+    return new_x1, new_y1, new_x2, new_y2
+
+
+def process_image(detector, parser, image_path: str, save_dir: str = 'outputs', expand_ratio: float = 0.2):
+    """Process a single image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    result_image = image.copy()
+
+    for i, face in enumerate(faces):
+        x1, y1, x2, y2 = expand_bbox(face.bbox, image.shape, expand_ratio=expand_ratio)
+        face_crop = image[y1:y2, x1:x2]
+
+        if face_crop.size == 0:
+            continue
+
+        mask = parser.parse(face_crop)
+        print(f'  Face {i + 1}: parsed with {len(set(mask.flatten()))} unique classes')
+
+        face_crop_rgb = cv2.cvtColor(face_crop, cv2.COLOR_BGR2RGB)
+        vis_result = vis_parsing_maps(face_crop_rgb, mask, save_image=False)
+
+        result_image[y1:y2, x1:x2] = vis_result
+        cv2.rectangle(result_image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_parsing.jpg')
+    cv2.imwrite(output_path, result_image)
+    print(f'Output saved: {output_path}')
+
+
+def process_video(detector, parser, video_path: str, save_dir: str = 'outputs', expand_ratio: float = 0.2):
+    """Process a video file."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_parsing.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+
+        for face in faces:
+            x1, y1, x2, y2 = expand_bbox(face.bbox, frame.shape, expand_ratio=expand_ratio)
+            face_crop = frame[y1:y2, x1:x2]
+
+            if face_crop.size == 0:
+                continue
+
+            mask = parser.parse(face_crop)
+            face_crop_rgb = cv2.cvtColor(face_crop, cv2.COLOR_BGR2RGB)
+            vis_result = vis_parsing_maps(face_crop_rgb, mask, save_image=False)
+
+            frame[y1:y2, x1:x2] = vis_result
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, parser, camera_id: int = 0, expand_ratio: float = 0.2):
+    """Run real-time detection on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame = cv2.flip(frame, 1)
+        faces = detector.detect(frame)
+
+        for face in faces:
+            x1, y1, x2, y2 = expand_bbox(face.bbox, frame.shape, expand_ratio=expand_ratio)
+            face_crop = frame[y1:y2, x1:x2]
+
+            if face_crop.size == 0:
+                continue
+
+            mask = parser.parse(face_crop)
+            face_crop_rgb = cv2.cvtColor(face_crop, cv2.COLOR_BGR2RGB)
+            vis_result = vis_parsing_maps(face_crop_rgb, mask, save_image=False)
+
+            frame[y1:y2, x1:x2] = vis_result
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('Face Parsing', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser_arg = argparse.ArgumentParser(description='Run face parsing')
+    parser_arg.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    parser_arg.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    parser_arg.add_argument(
+        '--model', type=str, default=ParsingWeights.RESNET18, choices=[ParsingWeights.RESNET18, ParsingWeights.RESNET34]
+    )
+    parser_arg.add_argument(
+        '--expand-ratio',
+        type=float,
+        default=0.2,
+        help='Bbox expansion ratio for full head coverage (default: 0.2 = 20%%)',
+    )
+    args = parser_arg.parse_args()
+
+    detector = RetinaFace()
+    parser = BiSeNet(model_name=ParsingWeights.RESNET34)
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, parser, int(args.source), expand_ratio=args.expand_ratio)
+    elif source_type == 'image':
+        if not os.path.exists(args.source):
+            print(f'Error: Image not found: {args.source}')
+            return
+        process_image(detector, parser, args.source, args.save_dir, expand_ratio=args.expand_ratio)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, parser, args.source, args.save_dir, expand_ratio=args.expand_ratio)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/face_search.py

@@ -0,0 +1,190 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Real-time face search: match faces against a reference image.
+
+Usage:
+    python tools/face_search.py --reference person.jpg --source 0  # webcam
+    python tools/face_search.py --reference person.jpg --source video.mp4
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+from uniface.detection import SCRFD, RetinaFace
+from uniface.face_utils import compute_similarity
+from uniface.recognition import ArcFace, MobileFace, SphereFace
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def get_recognizer(name: str):
+    """Get recognizer by name."""
+    if name == 'arcface':
+        return ArcFace()
+    elif name == 'mobileface':
+        return MobileFace()
+    else:
+        return SphereFace()
+
+
+def extract_reference_embedding(detector, recognizer, image_path: str) -> np.ndarray:
+    """Extract embedding from reference image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        raise RuntimeError(f'Failed to load image: {image_path}')
+
+    faces = detector.detect(image)
+    if not faces:
+        raise RuntimeError('No faces found in reference image.')
+
+    landmarks = faces[0].landmarks
+    return recognizer.get_normalized_embedding(image, landmarks)
+
+
+def process_frame(frame, detector, recognizer, ref_embedding: np.ndarray, threshold: float = 0.4):
+    """Process a single frame and return annotated frame."""
+    faces = detector.detect(frame)
+
+    for face in faces:
+        bbox = face.bbox
+        landmarks = face.landmarks
+        x1, y1, x2, y2 = map(int, bbox)
+
+        embedding = recognizer.get_normalized_embedding(frame, landmarks)
+        sim = compute_similarity(ref_embedding, embedding)
+
+        label = f'Match ({sim:.2f})' if sim > threshold else f'Unknown ({sim:.2f})'
+        color = (0, 255, 0) if sim > threshold else (0, 0, 255)
+
+        cv2.rectangle(frame, (x1, y1), (x2, y2), color, 2)
+        cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
+
+    return frame
+
+
+def process_video(detector, recognizer, ref_embedding: np.ndarray, video_path: str, save_dir: str, threshold: float):
+    """Process a video file."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_search.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        frame = process_frame(frame, detector, recognizer, ref_embedding, threshold)
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, recognizer, ref_embedding: np.ndarray, camera_id: int = 0, threshold: float = 0.4):
+    """Run real-time face search on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+        if not ret:
+            break
+
+        frame = process_frame(frame, detector, recognizer, ref_embedding, threshold)
+
+        cv2.imshow('Face Recognition', frame)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Face search using a reference image')
+    parser.add_argument('--reference', type=str, required=True, help='Reference face image')
+    parser.add_argument('--source', type=str, required=True, help='Video path or camera ID (0, 1, ...)')
+    parser.add_argument('--threshold', type=float, default=0.4, help='Match threshold')
+    parser.add_argument('--detector', type=str, default='scrfd', choices=['retinaface', 'scrfd'])
+    parser.add_argument(
+        '--recognizer',
+        type=str,
+        default='arcface',
+        choices=['arcface', 'mobileface', 'sphereface'],
+    )
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    args = parser.parse_args()
+
+    if not os.path.exists(args.reference):
+        print(f'Error: Reference image not found: {args.reference}')
+        return
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    recognizer = get_recognizer(args.recognizer)
+
+    print(f'Loading reference: {args.reference}')
+    ref_embedding = extract_reference_embedding(detector, recognizer, args.reference)
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, recognizer, ref_embedding, int(args.source), args.threshold)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, recognizer, ref_embedding, args.source, args.save_dir, args.threshold)
+    else:
+        print(f"Error: Source must be a video file or camera ID, not '{args.source}'")
+        print('Supported formats: videos (.mp4, .avi, ...) or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/fairface.py

@@ -0,0 +1,214 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""FairFace attribute prediction (race, gender, age) on detected faces.
+
+Usage:
+    python tools/fairface.py --source path/to/image.jpg
+    python tools/fairface.py --source path/to/video.mp4
+    python tools/fairface.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+
+from uniface import SCRFD, RetinaFace
+from uniface.attribute import FairFace
+from uniface.visualization import draw_detections
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def draw_fairface_label(image, bbox, sex: str, age_group: str, race: str):
+    """Draw FairFace attributes above the bounding box."""
+    x1, y1 = int(bbox[0]), int(bbox[1])
+    text = f'{sex}, {age_group}, {race}'
+    (tw, th), _ = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 2)
+    cv2.rectangle(image, (x1, y1 - th - 10), (x1 + tw + 10, y1), (0, 255, 0), -1)
+    cv2.putText(image, text, (x1 + 5, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 2)
+
+
+def process_image(
+    detector,
+    fairface,
+    image_path: str,
+    save_dir: str = 'outputs',
+    threshold: float = 0.6,
+):
+    """Process a single image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        return
+
+    bboxes = [f.bbox for f in faces]
+    scores = [f.confidence for f in faces]
+    landmarks = [f.landmarks for f in faces]
+    draw_detections(
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+    )
+
+    for i, face in enumerate(faces):
+        result = fairface.predict(image, face.bbox)
+        print(f'  Face {i + 1}: {result.sex}, {result.age_group}, {result.race}')
+        draw_fairface_label(image, face.bbox, result.sex, result.age_group, result.race)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_fairface.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def process_video(
+    detector,
+    fairface,
+    video_path: str,
+    save_dir: str = 'outputs',
+    threshold: float = 0.6,
+):
+    """Process a video file."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_fairface.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        )
+
+        for face in faces:
+            result = fairface.predict(frame, face.bbox)
+            draw_fairface_label(frame, face.bbox, result.sex, result.age_group, result.race)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, fairface, camera_id: int = 0, threshold: float = 0.6):
+    """Run real-time detection on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        )
+
+        for face in faces:
+            result = fairface.predict(frame, face.bbox)
+            draw_fairface_label(frame, face.bbox, result.sex, result.age_group, result.race)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('FairFace Detection', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Run FairFace attribute prediction (race, gender, age)')
+    parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--threshold', type=float, default=0.6, help='Visualization threshold')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    args = parser.parse_args()
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    fairface = FairFace()
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, fairface, int(args.source), args.threshold)
+    elif source_type == 'image':
+        if not os.path.exists(args.source):
+            print(f'Error: Image not found: {args.source}')
+            return
+        process_image(detector, fairface, args.source, args.save_dir, args.threshold)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, fairface, args.source, args.save_dir, args.threshold)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/gaze_estimation.py

@@ -0,0 +1,190 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Gaze estimation on detected faces.
+
+Usage:
+    python tools/gaze_estimation.py --source path/to/image.jpg
+    python tools/gaze_estimation.py --source path/to/video.mp4
+    python tools/gaze_estimation.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+from uniface import RetinaFace
+from uniface.gaze import MobileGaze
+from uniface.visualization import draw_gaze
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def process_image(detector, gaze_estimator, image_path: str, save_dir: str = 'outputs'):
+    """Process a single image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    for i, face in enumerate(faces):
+        bbox = face.bbox
+        x1, y1, x2, y2 = map(int, bbox[:4])
+        face_crop = image[y1:y2, x1:x2]
+
+        if face_crop.size == 0:
+            continue
+
+        result = gaze_estimator.estimate(face_crop)
+        print(f'  Face {i + 1}: pitch={np.degrees(result.pitch):.1f}°, yaw={np.degrees(result.yaw):.1f}°')
+
+        draw_gaze(image, bbox, result.pitch, result.yaw, draw_angles=True)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_gaze.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def process_video(detector, gaze_estimator, video_path: str, save_dir: str = 'outputs'):
+    """Process a video file."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_gaze.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+
+        for face in faces:
+            bbox = face.bbox
+            x1, y1, x2, y2 = map(int, bbox[:4])
+            face_crop = frame[y1:y2, x1:x2]
+
+            if face_crop.size == 0:
+                continue
+
+            result = gaze_estimator.estimate(face_crop)
+            draw_gaze(frame, bbox, result.pitch, result.yaw)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, gaze_estimator, camera_id: int = 0):
+    """Run real-time detection on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame = cv2.flip(frame, 1)
+        faces = detector.detect(frame)
+
+        for face in faces:
+            bbox = face.bbox
+            x1, y1, x2, y2 = map(int, bbox[:4])
+            face_crop = frame[y1:y2, x1:x2]
+
+            if face_crop.size == 0:
+                continue
+
+            result = gaze_estimator.estimate(face_crop)
+            draw_gaze(frame, bbox, result.pitch, result.yaw)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('Gaze Estimation', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Run gaze estimation')
+    parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    args = parser.parse_args()
+
+    detector = RetinaFace()
+    gaze_estimator = MobileGaze()
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, gaze_estimator, int(args.source))
+    elif source_type == 'image':
+        if not os.path.exists(args.source):
+            print(f'Error: Image not found: {args.source}')
+            return
+        process_image(detector, gaze_estimator, args.source, args.save_dir)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, gaze_estimator, args.source, args.save_dir)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/landmarks.py

@@ -0,0 +1,187 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""106-point facial landmark detection.
+
+Usage:
+    python tools/landmarks.py --source path/to/image.jpg
+    python tools/landmarks.py --source path/to/video.mp4
+    python tools/landmarks.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+
+from uniface import SCRFD, Landmark106, RetinaFace
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def process_image(detector, landmarker, image_path: str, save_dir: str = 'outputs'):
+    """Process a single image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        return
+
+    for i, face in enumerate(faces):
+        bbox = face.bbox
+        x1, y1, x2, y2 = map(int, bbox)
+        cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+        landmarks = landmarker.get_landmarks(image, bbox)
+        print(f'  Face {i + 1}: {len(landmarks)} landmarks')
+
+        for x, y in landmarks.astype(int):
+            cv2.circle(image, (x, y), 1, (0, 255, 0), -1)
+
+        cv2.putText(image, f'Face {i + 1}', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_landmarks.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def process_video(detector, landmarker, video_path: str, save_dir: str = 'outputs'):
+    """Process a video file."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_landmarks.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+
+        for face in faces:
+            bbox = face.bbox
+            x1, y1, x2, y2 = map(int, bbox)
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+            landmarks = landmarker.get_landmarks(frame, bbox)
+            for x, y in landmarks.astype(int):
+                cv2.circle(frame, (x, y), 1, (0, 255, 0), -1)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, landmarker, camera_id: int = 0):
+    """Run real-time detection on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+
+        for face in faces:
+            bbox = face.bbox
+            x1, y1, x2, y2 = map(int, bbox)
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+            landmarks = landmarker.get_landmarks(frame, bbox)
+            for x, y in landmarks.astype(int):
+                cv2.circle(frame, (x, y), 1, (0, 255, 0), -1)
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('106-Point Landmarks', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Run facial landmark detection')
+    parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    args = parser.parse_args()
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    landmarker = Landmark106()
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, landmarker, int(args.source))
+    elif source_type == 'image':
+        if not os.path.exists(args.source):
+            print(f'Error: Image not found: {args.source}')
+            return
+        process_image(detector, landmarker, args.source, args.save_dir)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, landmarker, args.source, args.save_dir)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/recognition.py

@@ -0,0 +1,110 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face recognition: extract embeddings or compare two faces.
+
+Usage:
+    python tools/recognition.py --image path/to/image.jpg
+    python tools/recognition.py --image1 face1.jpg --image2 face2.jpg
+"""
+
+import argparse
+
+import cv2
+import numpy as np
+
+from uniface.detection import SCRFD, RetinaFace
+from uniface.face_utils import compute_similarity
+from uniface.recognition import ArcFace, MobileFace, SphereFace
+
+
+def get_recognizer(name: str):
+    if name == 'arcface':
+        return ArcFace()
+    elif name == 'mobileface':
+        return MobileFace()
+    else:
+        return SphereFace()
+
+
+def run_inference(detector, recognizer, image_path: str):
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    if not faces:
+        print('No faces detected.')
+        return
+
+    print(f'Detected {len(faces)} face(s). Extracting embedding for the first face...')
+
+    landmarks = faces[0]['landmarks']  # 5-point landmarks for alignment (already np.ndarray)
+    embedding = recognizer.get_embedding(image, landmarks)
+    norm_embedding = recognizer.get_normalized_embedding(image, landmarks)  # L2 normalized
+
+    print(f'  Embedding shape: {embedding.shape}')
+    print(f'  L2 norm (raw): {np.linalg.norm(embedding):.4f}')
+    print(f'  L2 norm (normalized): {np.linalg.norm(norm_embedding):.4f}')
+
+
+def compare_faces(detector, recognizer, image1_path: str, image2_path: str, threshold: float = 0.35):
+    img1 = cv2.imread(image1_path)
+    img2 = cv2.imread(image2_path)
+
+    if img1 is None or img2 is None:
+        print('Error: Failed to load one or both images')
+        return
+
+    faces1 = detector.detect(img1)
+    faces2 = detector.detect(img2)
+
+    if not faces1 or not faces2:
+        print('Error: No faces detected in one or both images')
+        return
+
+    landmarks1 = faces1[0]['landmarks']
+    landmarks2 = faces2[0]['landmarks']
+
+    embedding1 = recognizer.get_normalized_embedding(img1, landmarks1)
+    embedding2 = recognizer.get_normalized_embedding(img2, landmarks2)
+
+    # cosine similarity for normalized embeddings
+    similarity = compute_similarity(embedding1, embedding2, normalized=True)
+    is_match = similarity > threshold
+
+    print(f'Similarity: {similarity:.4f}')
+    print(f'Result: {"Same person" if is_match else "Different person"} (threshold: {threshold})')
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Face recognition and comparison')
+    parser.add_argument('--image', type=str, help='Single image for embedding extraction')
+    parser.add_argument('--image1', type=str, help='First image for comparison')
+    parser.add_argument('--image2', type=str, help='Second image for comparison')
+    parser.add_argument('--threshold', type=float, default=0.35, help='Similarity threshold')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument(
+        '--recognizer',
+        type=str,
+        default='arcface',
+        choices=['arcface', 'mobileface', 'sphereface'],
+    )
+    args = parser.parse_args()
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    recognizer = get_recognizer(args.recognizer)
+
+    if args.image1 and args.image2:
+        compare_faces(detector, recognizer, args.image1, args.image2, args.threshold)
+    elif args.image:
+        run_inference(detector, recognizer, args.image)
+    else:
+        print('Error: Provide --image or both --image1 and --image2')
+        parser.print_help()
+
+
+if __name__ == '__main__':
+    main()

tools/sha256_generate.py

@@ -0,0 +1,28 @@
+import argparse
+import hashlib
+from pathlib import Path
+
+
+def compute_sha256(file_path: Path, chunk_size: int = 8192) -> str:
+    sha256_hash = hashlib.sha256()
+    with file_path.open('rb') as f:
+        for chunk in iter(lambda: f.read(chunk_size), b''):
+            sha256_hash.update(chunk)
+    return sha256_hash.hexdigest()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Compute SHA256 hash of a file')
+    parser.add_argument('file', type=Path, help='Path to file')
+    args = parser.parse_args()
+
+    if not args.file.exists() or not args.file.is_file():
+        print(f'File does not exist: {args.file}')
+        return
+
+    sha256 = compute_sha256(args.file)
+    print(f"SHA256 hash for '{args.file.name}':\n{sha256}")
+
+
+if __name__ == '__main__':
+    main()

tools/spoofing.py

@@ -0,0 +1,214 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face Anti-Spoofing Detection.
+
+Usage:
+    python tools/spoofing.py --source path/to/image.jpg
+    python tools/spoofing.py --source path/to/video.mp4
+    python tools/spoofing.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+from uniface import RetinaFace
+from uniface.constants import MiniFASNetWeights
+from uniface.spoofing import create_spoofer
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def draw_spoofing_result(
+    image: np.ndarray,
+    bbox: list,
+    is_real: bool,
+    confidence: float,
+    thickness: int = 2,
+) -> None:
+    """Draw bounding box with anti-spoofing result.
+
+    Args:
+        image: Input image to draw on.
+        bbox: Bounding box in [x1, y1, x2, y2] format.
+        is_real: True if real face, False if fake.
+        confidence: Confidence score (0.0 to 1.0).
+        thickness: Line thickness for bounding box.
+    """
+    x1, y1, x2, y2 = map(int, bbox[:4])
+
+    color = (0, 255, 0) if is_real else (0, 0, 255)
+
+    cv2.rectangle(image, (x1, y1), (x2, y2), color, thickness)
+
+    label = 'Real' if is_real else 'Fake'
+    text = f'{label}: {confidence:.1%}'
+
+    (tw, th), _baseline = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2)
+    cv2.rectangle(image, (x1, y1 - th - 10), (x1 + tw + 10, y1), color, -1)
+    cv2.putText(image, text, (x1 + 5, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2)
+
+
+def process_image(detector, spoofer, image_path: str, save_dir: str = 'outputs') -> None:
+    """Process a single image for face anti-spoofing detection."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        print('No faces detected in the image.')
+        return
+
+    for i, face in enumerate(faces, 1):
+        result = spoofer.predict(image, face.bbox)
+        label = 'Real' if result.is_real else 'Fake'
+        print(f'  Face {i}: {label} ({result.confidence:.1%})')
+
+        draw_spoofing_result(image, face.bbox, result.is_real, result.confidence)
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_spoofing.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def process_video(detector, spoofer, video_path: str, save_dir: str = 'outputs') -> None:
+    """Process a video file for face anti-spoofing detection."""
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_spoofing.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+
+        for face in faces:
+            result = spoofer.predict(frame, face.bbox)
+            draw_spoofing_result(frame, face.bbox, result.is_real, result.confidence)
+
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, spoofer, camera_id: int = 0) -> None:
+    """Run real-time anti-spoofing detection on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame = cv2.flip(frame, 1)
+        faces = detector.detect(frame)
+
+        for face in faces:
+            result = spoofer.predict(frame, face.bbox)
+            draw_spoofing_result(frame, face.bbox, result.is_real, result.confidence)
+
+        cv2.imshow('Face Anti-Spoofing', frame)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Face Anti-Spoofing Detection')
+    parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    parser.add_argument(
+        '--model',
+        type=str,
+        default='v2',
+        choices=['v1se', 'v2'],
+        help='Model variant: v1se or v2 (default: v2)',
+    )
+    parser.add_argument('--scale', type=float, default=None, help='Custom crop scale (default: auto)')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    args = parser.parse_args()
+
+    # Select model variant
+    model_name = MiniFASNetWeights.V1SE if args.model == 'v1se' else MiniFASNetWeights.V2
+
+    # Initialize models
+    print(f'Initializing models (MiniFASNet {args.model.upper()})...')
+    detector = RetinaFace()
+    spoofer = create_spoofer(model_name=model_name, scale=args.scale)
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, spoofer, int(args.source))
+    elif source_type == 'image':
+        if not os.path.exists(args.source):
+            print(f'Error: Image not found: {args.source}')
+            return
+        process_image(detector, spoofer, args.source, args.save_dir)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, spoofer, args.source, args.save_dir)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: images (.jpg, .png, ...), videos (.mp4, .avi, ...), or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

tools/video_detection.py

@@ -0,0 +1,180 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face detection on video files with progress tracking.
+
+Usage:
+    python tools/video_detection.py --source video.mp4
+    python tools/video_detection.py --source video.mp4 --output output.mp4
+    python tools/video_detection.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+from tqdm import tqdm
+
+from uniface import SCRFD, RetinaFace
+from uniface.visualization import draw_detections
+
+IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
+VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
+
+
+def get_source_type(source: str) -> str:
+    """Determine if source is image, video, or camera."""
+    if source.isdigit():
+        return 'camera'
+    path = Path(source)
+    suffix = path.suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    elif suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    else:
+        return 'unknown'
+
+
+def process_video(
+    detector,
+    input_path: str,
+    output_path: str,
+    threshold: float = 0.6,
+    show_preview: bool = False,
+):
+    """Process a video file with progress bar."""
+    cap = cv2.VideoCapture(input_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{input_path}'")
+        return
+
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
+    print(f'Input: {input_path} ({width}x{height}, {fps:.1f} fps, {total_frames} frames)')
+    print(f'Output: {output_path}')
+
+    Path(output_path).parent.mkdir(parents=True, exist_ok=True)
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    if not out.isOpened():
+        print(f"Error: Cannot create output video '{output_path}'")
+        cap.release()
+        return
+
+    frame_count = 0
+    total_faces = 0
+
+    for _ in tqdm(range(total_frames), desc='Processing', unit='frames'):
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        faces = detector.detect(frame)
+        total_faces += len(faces)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        )
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(frame)
+
+        if show_preview:
+            cv2.imshow("Processing - Press 'q' to cancel", frame)
+            if cv2.waitKey(1) & 0xFF == ord('q'):
+                print('\nCancelled by user')
+                break
+
+    cap.release()
+    out.release()
+    if show_preview:
+        cv2.destroyAllWindows()
+
+    avg_faces = total_faces / frame_count if frame_count > 0 else 0
+    print(f'\nDone! {frame_count} frames, {total_faces} faces ({avg_faces:.1f} avg/frame)')
+    print(f'Saved: {output_path}')
+
+
+def run_camera(detector, camera_id: int = 0, threshold: float = 0.6):
+    """Run real-time detection on webcam."""
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+
+        bboxes = [f.bbox for f in faces]
+        scores = [f.confidence for f in faces]
+        landmarks = [f.landmarks for f in faces]
+        draw_detections(
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        )
+
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('Face Detection', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Process video with face detection')
+    parser.add_argument('--source', type=str, required=True, help='Video path or camera ID (0, 1, ...)')
+    parser.add_argument('--output', type=str, default=None, help='Output video path (auto-generated if not specified)')
+    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--threshold', type=float, default=0.6, help='Visualization threshold')
+    parser.add_argument('--preview', action='store_true', help='Show live preview')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory (if --output not specified)')
+    args = parser.parse_args()
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, int(args.source), args.threshold)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+
+        # Determine output path
+        if args.output:
+            output_path = args.output
+        else:
+            os.makedirs(args.save_dir, exist_ok=True)
+            output_path = os.path.join(args.save_dir, f'{Path(args.source).stem}_detected.mp4')
+
+        process_video(detector, args.source, output_path, args.threshold, args.preview)
+    else:
+        print(f"Error: Unknown source type for '{args.source}'")
+        print('Supported formats: videos (.mp4, .avi, ...) or camera ID (0, 1, ...)')
+
+
+if __name__ == '__main__':
+    main()

uniface/__init__.py

@@ -11,52 +11,105 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__license__ = "MIT"
-__author__ = "Yakhyokhuja Valikhujaev"
-__version__ = "1.1.0"
+"""UniFace: A comprehensive library for face analysis.
 
+This library provides unified APIs for:
+- Face detection (RetinaFace, SCRFD, YOLOv5Face)
+- Face recognition (ArcFace, MobileFace, SphereFace)
+- Facial landmarks (106-point detection)
+- Face parsing (semantic segmentation)
+- Gaze estimation
+- Age, gender, and emotion prediction
+- Face anti-spoofing
+- Privacy/anonymization
+"""
+
+from __future__ import annotations
+
+__license__ = 'MIT'
+__author__ = 'Yakhyokhuja Valikhujaev'
+__version__ = '2.0.0'
 
 from uniface.face_utils import compute_similarity, face_alignment
 from uniface.log import Logger, enable_logging
 from uniface.model_store import verify_model_weights
-from uniface.visualization import draw_detections
+from uniface.visualization import draw_detections, vis_parsing_maps
 
-from .attribute import AgeGender
+from .analyzer import FaceAnalyzer
+from .attribute import AgeGender, FairFace
+from .detection import (
+    SCRFD,
+    RetinaFace,
+    YOLOv5Face,
+    create_detector,
+    detect_faces,
+    list_available_detectors,
+)
+from .gaze import MobileGaze, create_gaze_estimator
+from .landmark import Landmark106, create_landmarker
+from .parsing import BiSeNet, create_face_parser
+from .privacy import BlurFace, anonymize_faces
+from .recognition import ArcFace, MobileFace, SphereFace, create_recognizer
+from .spoofing import MiniFASNet, create_spoofer
+from .types import AttributeResult, EmotionResult, Face, GazeResult, SpoofingResult
+
+# Optional: Emotion requires PyTorch
+Emotion: type | None
 try:
     from .attribute import Emotion
 except ImportError:
-    Emotion = None  # PyTorch not installed
-from .detection import SCRFD, RetinaFace, create_detector, detect_faces, list_available_detectors
-from .landmark import Landmark106, create_landmarker
-from .recognition import ArcFace, MobileFace, SphereFace, create_recognizer
+    Emotion = None
 
 __all__ = [
-    "__author__",
-    "__license__",
-    "__version__",
+    # Metadata
+    '__author__',
+    '__license__',
+    '__version__',
+    # Core classes
+    'Face',
+    'FaceAnalyzer',
     # Factory functions
-    "create_detector",
-    "create_landmarker",
-    "create_recognizer",
-    "detect_faces",
-    "list_available_detectors",
+    'create_detector',
+    'create_face_parser',
+    'create_gaze_estimator',
+    'create_landmarker',
+    'create_recognizer',
+    'create_spoofer',
+    'detect_faces',
+    'list_available_detectors',
     # Detection models
-    "RetinaFace",
-    "SCRFD",
+    'RetinaFace',
+    'SCRFD',
+    'YOLOv5Face',
     # Recognition models
-    "ArcFace",
-    "MobileFace",
-    "SphereFace",
+    'ArcFace',
+    'MobileFace',
+    'SphereFace',
     # Landmark models
-    "Landmark106",
+    'Landmark106',
+    # Gaze models
+    'GazeResult',
+    'MobileGaze',
+    # Parsing models
+    'BiSeNet',
     # Attribute models
-    "AgeGender",
-    "Emotion",
+    'AgeGender',
+    'AttributeResult',
+    'Emotion',
+    'EmotionResult',
+    'FairFace',
+    # Spoofing models
+    'MiniFASNet',
+    'SpoofingResult',
+    # Privacy
+    'BlurFace',
+    'anonymize_faces',
     # Utilities
-    "compute_similarity",
-    "draw_detections",
-    "face_alignment",
-    "verify_model_weights",
-    "Logger",
-    "enable_logging",
+    'Logger',
+    'compute_similarity',
+    'draw_detections',
+    'enable_logging',
+    'face_alignment',
+    'verify_model_weights',
+    'vis_parsing_maps',
 ]

uniface/analyzer.py

@@ -0,0 +1,113 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+import numpy as np
+
+from uniface.attribute.age_gender import AgeGender
+from uniface.attribute.fairface import FairFace
+from uniface.detection.base import BaseDetector
+from uniface.log import Logger
+from uniface.recognition.base import BaseRecognizer
+from uniface.types import Face
+
+__all__ = ['FaceAnalyzer']
+
+
+class FaceAnalyzer:
+    """Unified face analyzer combining detection, recognition, and attributes.
+
+    This class provides a high-level interface for face analysis by combining
+    multiple components: face detection, recognition (embedding extraction),
+    and attribute prediction (age, gender, race).
+
+    Args:
+        detector: Face detector instance for detecting faces in images.
+        recognizer: Optional face recognizer for extracting embeddings.
+        age_gender: Optional age/gender predictor.
+        fairface: Optional FairFace predictor for demographics.
+
+    Example:
+        >>> from uniface import RetinaFace, ArcFace, FaceAnalyzer
+        >>> detector = RetinaFace()
+        >>> recognizer = ArcFace()
+        >>> analyzer = FaceAnalyzer(detector, recognizer=recognizer)
+        >>> faces = analyzer.analyze(image)
+    """
+
+    def __init__(
+        self,
+        detector: BaseDetector,
+        recognizer: BaseRecognizer | None = None,
+        age_gender: AgeGender | None = None,
+        fairface: FairFace | None = None,
+    ) -> None:
+        self.detector = detector
+        self.recognizer = recognizer
+        self.age_gender = age_gender
+        self.fairface = fairface
+
+        Logger.info(f'Initialized FaceAnalyzer with detector={detector.__class__.__name__}')
+        if recognizer:
+            Logger.info(f'  - Recognition enabled: {recognizer.__class__.__name__}')
+        if age_gender:
+            Logger.info(f'  - Age/Gender enabled: {age_gender.__class__.__name__}')
+        if fairface:
+            Logger.info(f'  - FairFace enabled: {fairface.__class__.__name__}')
+
+    def analyze(self, image: np.ndarray) -> list[Face]:
+        """Analyze faces in an image.
+
+        Performs face detection and optionally extracts embeddings and
+        predicts attributes for each detected face.
+
+        Args:
+            image: Input image as numpy array with shape (H, W, C) in BGR format.
+
+        Returns:
+            List of Face objects with detection results and any predicted attributes.
+        """
+        faces = self.detector.detect(image)
+        Logger.debug(f'Detected {len(faces)} face(s)')
+
+        for idx, face in enumerate(faces):
+            if self.recognizer is not None:
+                try:
+                    face.embedding = self.recognizer.get_normalized_embedding(image, face.landmarks)
+                    Logger.debug(f'  Face {idx + 1}: Extracted embedding with shape {face.embedding.shape}')
+                except Exception as e:
+                    Logger.warning(f'  Face {idx + 1}: Failed to extract embedding: {e}')
+
+            if self.age_gender is not None:
+                try:
+                    result = self.age_gender.predict(image, face.bbox)
+                    face.gender = result.gender
+                    face.age = result.age
+                    Logger.debug(f'  Face {idx + 1}: Age={face.age}, Gender={face.sex}')
+                except Exception as e:
+                    Logger.warning(f'  Face {idx + 1}: Failed to predict age/gender: {e}')
+
+            if self.fairface is not None:
+                try:
+                    result = self.fairface.predict(image, face.bbox)
+                    face.gender = result.gender
+                    face.age_group = result.age_group
+                    face.race = result.race
+                    Logger.debug(f'  Face {idx + 1}: AgeGroup={face.age_group}, Gender={face.sex}, Race={face.race}')
+                except Exception as e:
+                    Logger.warning(f'  Face {idx + 1}: Failed to predict FairFace attributes: {e}')
+
+        Logger.info(f'Analysis complete: {len(faces)} face(s) processed')
+        return faces
+
+    def __repr__(self) -> str:
+        parts = [f'FaceAnalyzer(detector={self.detector.__class__.__name__}']
+        if self.recognizer:
+            parts.append(f'recognizer={self.recognizer.__class__.__name__}')
+        if self.age_gender:
+            parts.append(f'age_gender={self.age_gender.__class__.__name__}')
+        if self.fairface:
+            parts.append(f'fairface={self.fairface.__class__.__name__}')
+        return ', '.join(parts) + ')'

uniface/attribute/__init__.py

@@ -2,16 +2,22 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from typing import Dict, Any, List, Union
+from __future__ import annotations
+
+from typing import Any
+
 import numpy as np
 
 from uniface.attribute.age_gender import AgeGender
 from uniface.attribute.base import Attribute
-from uniface.constants import AgeGenderWeights, DDAMFNWeights
+from uniface.attribute.fairface import FairFace
+from uniface.constants import AgeGenderWeights, DDAMFNWeights, FairFaceWeights
+from uniface.types import AttributeResult, EmotionResult, Face
 
 # Emotion requires PyTorch - make it optional
 try:
     from uniface.attribute.emotion import Emotion
+
     _EMOTION_AVAILABLE = True
 except ImportError:
     Emotion = None
@@ -19,25 +25,28 @@ except ImportError:
 
 # Public API for the attribute module
 __all__ = [
-    "AgeGender",
-    "Emotion",
-    "create_attribute_predictor",
-    "predict_attributes"
+    'AgeGender',
+    'AttributeResult',
+    'Emotion',
+    'EmotionResult',
+    'FairFace',
+    'create_attribute_predictor',
+    'predict_attributes',
 ]
 
 # A mapping from model enums to their corresponding attribute classes
 _ATTRIBUTE_MODELS = {
-    **{model: AgeGender for model in AgeGenderWeights},
+    **dict.fromkeys(AgeGenderWeights, AgeGender),
+    **dict.fromkeys(FairFaceWeights, FairFace),
 }
 
 # Add Emotion models only if PyTorch is available
 if _EMOTION_AVAILABLE:
-    _ATTRIBUTE_MODELS.update({model: Emotion for model in DDAMFNWeights})
+    _ATTRIBUTE_MODELS.update(dict.fromkeys(DDAMFNWeights, Emotion))
 
 
 def create_attribute_predictor(
-    model_name: Union[AgeGenderWeights, DDAMFNWeights],
-    **kwargs: Any
+    model_name: AgeGenderWeights | DDAMFNWeights | FairFaceWeights, **kwargs: Any
 ) -> Attribute:
     """
     Factory function to create an attribute predictor instance.
@@ -47,11 +56,13 @@ def create_attribute_predictor(
 
     Args:
         model_name: The enum corresponding to the desired attribute model
-                    (e.g., AgeGenderWeights.DEFAULT or DDAMFNWeights.AFFECNET7).
+                    (e.g., AgeGenderWeights.DEFAULT, DDAMFNWeights.AFFECNET7,
+                    or FairFaceWeights.DEFAULT).
         **kwargs: Additional keyword arguments to pass to the model's constructor.
 
     Returns:
-        An initialized instance of an Attribute predictor class (e.g., AgeGender).
+        An initialized instance of an Attribute predictor class
+        (e.g., AgeGender, FairFace, or Emotion).
 
     Raises:
         ValueError: If the provided model_name is not a supported enum.
@@ -59,48 +70,45 @@ def create_attribute_predictor(
     model_class = _ATTRIBUTE_MODELS.get(model_name)
 
     if model_class is None:
-        raise ValueError(f"Unsupported attribute model: {model_name}. "
-                         f"Please choose from AgeGenderWeights or DDAMFNWeights.")
+        raise ValueError(
+            f'Unsupported attribute model: {model_name}. '
+            f'Please choose from AgeGenderWeights, FairFaceWeights, or DDAMFNWeights.'
+        )
 
     # Pass model_name to the constructor, as some classes might need it
     return model_class(model_name=model_name, **kwargs)
 
 
-def predict_attributes(
-    image: np.ndarray,
-    detections: List[Dict[str, np.ndarray]],
-    predictor: Attribute
-) -> List[Dict[str, Any]]:
+def predict_attributes(image: np.ndarray, faces: list[Face], predictor: Attribute) -> list[Face]:
     """
     High-level API to predict attributes for multiple detected faces.
 
-    This function iterates through a list of face detections, runs the
-    specified attribute predictor on each one, and appends the results back
-    into the detection dictionary.
+    This function iterates through a list of Face objects, runs the
+    specified attribute predictor on each one, and updates the Face
+    objects with the predicted attributes.
 
     Args:
         image (np.ndarray): The full input image in BGR format.
-        detections (List[Dict]): A list of detection results, where each dict
-                                 must contain a 'bbox' and optionally 'landmark'.
+        faces (List[Face]): A list of Face objects from face detection.
         predictor (Attribute): An initialized attribute predictor instance,
                                created by `create_attribute_predictor`.
 
     Returns:
-        The list of detections, where each dictionary is updated with a new
-        'attributes' key containing the prediction result.
+        List[Face]: The list of Face objects with updated attribute fields.
     """
-    for face in detections:
-        # Initialize attributes dict if it doesn't exist
-        if 'attributes' not in face:
-            face['attributes'] = {}
-
+    for face in faces:
         if isinstance(predictor, AgeGender):
-            gender, age = predictor(image, face['bbox'])
-            face['attributes']['gender'] = gender
-            face['attributes']['age'] = age
+            result = predictor(image, face.bbox)
+            face.gender = result.gender
+            face.age = result.age
+        elif isinstance(predictor, FairFace):
+            result = predictor(image, face.bbox)
+            face.gender = result.gender
+            face.age_group = result.age_group
+            face.race = result.race
         elif isinstance(predictor, Emotion):
-            emotion, confidence = predictor(image, face['landmark'])
-            face['attributes']['emotion'] = emotion
-            face['attributes']['confidence'] = confidence
+            result = predictor(image, face.landmarks)
+            face.emotion = result.emotion
+            face.emotion_confidence = result.confidence
 
-    return detections
+    return faces

uniface/attribute/age_gender.py

@@ -2,7 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from typing import List, Tuple, Union
 
 import cv2
 import numpy as np
@@ -13,8 +12,9 @@ from uniface.face_utils import bbox_center_alignment
 from uniface.log import Logger
 from uniface.model_store import verify_model_weights
 from uniface.onnx_utils import create_onnx_session
+from uniface.types import AttributeResult
 
-__all__ = ["AgeGender"]
+__all__ = ['AgeGender']
 
 
 class AgeGender(Attribute):
@@ -22,20 +22,32 @@ class AgeGender(Attribute):
     Age and gender prediction model using ONNX Runtime.
 
     This class inherits from the base `Attribute` class and implements the
-    functionality for predicting age (in years) and gender (0 for female,
-    1 for male) from a face image. It requires a bounding box to locate the face.
+    functionality for predicting age (in years) and gender ID (0 for Female,
+    1 for Male) from a face image. It requires a bounding box to locate the face.
+
+    Args:
+        model_name (AgeGenderWeights): The enum specifying the model weights to load.
+            Defaults to `AgeGenderWeights.DEFAULT`.
+        input_size (Optional[Tuple[int, int]]): Input size (height, width).
+            If None, automatically detected from model metadata. Defaults to None.
     """
 
-    def __init__(self, model_name: AgeGenderWeights = AgeGenderWeights.DEFAULT) -> None:
+    def __init__(
+        self,
+        model_name: AgeGenderWeights = AgeGenderWeights.DEFAULT,
+        input_size: tuple[int, int] | None = None,
+    ) -> None:
         """
         Initializes the AgeGender prediction model.
 
         Args:
-            model_name (AgeGenderWeights): The enum specifying the model weights
-                                           to load.
+            model_name (AgeGenderWeights): The enum specifying the model weights to load.
+            input_size (Optional[Tuple[int, int]]): Input size (height, width).
+                If None, automatically detected from model metadata. Defaults to None.
         """
-        Logger.info(f"Initializing AgeGender with model={model_name.name}")
+        Logger.info(f'Initializing AgeGender with model={model_name.name}')
         self.model_path = verify_model_weights(model_name)
+        self._user_input_size = input_size  # Store user preference
         self._initialize_model()
 
     def _initialize_model(self) -> None:
@@ -47,14 +59,29 @@ class AgeGender(Attribute):
             # Get model input details from the loaded model
             input_meta = self.session.get_inputs()[0]
             self.input_name = input_meta.name
-            self.input_size = tuple(input_meta.shape[2:4])  # (height, width)
-            self.output_names = [output.name for output in self.session.get_outputs()]
-            Logger.info(f"Successfully initialized AgeGender model with input size {self.input_size}")
-        except Exception as e:
-            Logger.error(f"Failed to load AgeGender model from '{self.model_path}'", exc_info=True)
-            raise RuntimeError(f"Failed to initialize AgeGender model: {e}")
 
-    def preprocess(self, image: np.ndarray, bbox: Union[List, np.ndarray]) -> np.ndarray:
+            # Use user-provided size if given, otherwise auto-detect from model
+            model_input_size = tuple(input_meta.shape[2:4])  # (height, width)
+            if self._user_input_size is not None:
+                self.input_size = self._user_input_size
+                if self._user_input_size != model_input_size:
+                    Logger.warning(
+                        f'Using custom input_size {self.input_size}, '
+                        f'but model expects {model_input_size}. This may affect accuracy.'
+                    )
+            else:
+                self.input_size = model_input_size
+
+            self.output_names = [output.name for output in self.session.get_outputs()]
+            Logger.info(f'Successfully initialized AgeGender model with input size {self.input_size}')
+        except Exception as e:
+            Logger.error(
+                f"Failed to load AgeGender model from '{self.model_path}'",
+                exc_info=True,
+            )
+            raise RuntimeError(f'Failed to initialize AgeGender model: {e}') from e
+
+    def preprocess(self, image: np.ndarray, bbox: list | np.ndarray) -> np.ndarray:
         """
         Aligns the face based on the bounding box and preprocesses it for inference.
 
@@ -76,11 +103,15 @@ class AgeGender(Attribute):
         aligned_face, _ = bbox_center_alignment(image, center, self.input_size[1], scale, rotation)
 
         blob = cv2.dnn.blobFromImage(
-            aligned_face, scalefactor=1.0, size=self.input_size[::-1], mean=(0.0, 0.0, 0.0), swapRB=True
+            aligned_face,
+            scalefactor=1.0,
+            size=self.input_size[::-1],
+            mean=(0.0, 0.0, 0.0),
+            swapRB=True,
         )
         return blob
 
-    def postprocess(self, prediction: np.ndarray) -> Tuple[str, int]:
+    def postprocess(self, prediction: np.ndarray) -> AttributeResult:
         """
         Processes the raw model output to extract gender and age.
 
@@ -88,17 +119,15 @@ class AgeGender(Attribute):
             prediction (np.ndarray): The raw output from the model inference.
 
         Returns:
-            Tuple[str, int]: A tuple containing the predicted gender label ("Female" or "Male")
-                             and age (in years).
+            AttributeResult: Result containing gender (0=Female, 1=Male) and age (in years).
         """
         # First two values are gender logits
-        gender_id = int(np.argmax(prediction[:2]))
-        gender = "Female" if gender_id == 0 else "Male"
+        gender = int(np.argmax(prediction[:2]))
         # Third value is normalized age, scaled by 100
         age = int(np.round(prediction[2] * 100))
-        return gender, age
+        return AttributeResult(gender=gender, age=age)
 
-    def predict(self, image: np.ndarray, bbox: Union[List, np.ndarray]) -> Tuple[str, int]:
+    def predict(self, image: np.ndarray, bbox: list | np.ndarray) -> AttributeResult:
         """
         Predicts age and gender for a single face specified by a bounding box.
 
@@ -107,66 +136,8 @@ class AgeGender(Attribute):
             bbox (Union[List, np.ndarray]): The face bounding box coordinates [x1, y1, x2, y2].
 
         Returns:
-            Tuple[str, int]: A tuple containing the predicted gender label and age.
+            AttributeResult: Result containing gender (0=Female, 1=Male) and age (in years).
         """
         face_blob = self.preprocess(image, bbox)
         prediction = self.session.run(self.output_names, {self.input_name: face_blob})[0][0]
-        gender, age = self.postprocess(prediction)
-        return gender, age
-
-
-# TODO: below is only for testing, remove it later
-if __name__ == "__main__":
-    # To run this script, you need to have uniface.detection installed
-    # or available in your path.
-    from uniface.constants import RetinaFaceWeights
-    from uniface.detection import create_detector
-
-    print("Initializing models for live inference...")
-    # 1. Initialize the face detector
-    # Using a smaller model for faster real-time performance
-    detector = create_detector(model_name=RetinaFaceWeights.MNET_V2)
-
-    # 2. Initialize the attribute predictor
-    age_gender_predictor = AgeGender()
-
-    # 3. Start webcam capture
-    cap = cv2.VideoCapture(0)
-    if not cap.isOpened():
-        print("Error: Could not open webcam.")
-        exit()
-
-    print("Starting webcam feed. Press 'q' to quit.")
-    while True:
-        ret, frame = cap.read()
-        if not ret:
-            print("Error: Failed to capture frame.")
-            break
-
-        # Detect faces in the current frame
-        detections = detector.detect(frame)
-
-        # For each detected face, predict age and gender
-        for detection in detections:
-            box = detection["bbox"]
-            x1, y1, x2, y2 = map(int, box)
-
-            # Predict attributes
-            gender, age = age_gender_predictor.predict(frame, box)
-
-            # Prepare text and draw on the frame
-            label = f"{gender}, {age}"
-            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
-            cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 255, 0), 2)
-
-        # Display the resulting frame
-        cv2.imshow("Age and Gender Inference (Press 'q' to quit)", frame)
-
-        # Break the loop if 'q' is pressed
-        if cv2.waitKey(1) & 0xFF == ord("q"):
-            break
-
-    # Release resources
-    cap.release()
-    cv2.destroyAllWindows()
-    print("Inference stopped.")
+        return self.postprocess(prediction)

uniface/attribute/base.py

@@ -4,8 +4,13 @@
 
 from abc import ABC, abstractmethod
 from typing import Any
+
 import numpy as np
 
+from uniface.types import AttributeResult, EmotionResult
+
+__all__ = ['Attribute', 'AttributeResult', 'EmotionResult']
+
 
 class Attribute(ABC):
     """
@@ -26,7 +31,7 @@ class Attribute(ABC):
         inference session (e.g., ONNX Runtime, PyTorch), and any necessary
         warm-up procedures to prepare the model for prediction.
         """
-        raise NotImplementedError("Subclasses must implement the _initialize_model method.")
+        raise NotImplementedError('Subclasses must implement the _initialize_model method.')
 
     @abstractmethod
     def preprocess(self, image: np.ndarray, *args: Any) -> Any:
@@ -46,7 +51,7 @@ class Attribute(ABC):
         Returns:
             The preprocessed data ready for model inference.
         """
-        raise NotImplementedError("Subclasses must implement the preprocess method.")
+        raise NotImplementedError('Subclasses must implement the preprocess method.')
 
     @abstractmethod
     def postprocess(self, prediction: Any) -> Any:
@@ -63,7 +68,7 @@ class Attribute(ABC):
         Returns:
             The final, processed attributes.
         """
-        raise NotImplementedError("Subclasses must implement the postprocess method.")
+        raise NotImplementedError('Subclasses must implement the postprocess method.')
 
     @abstractmethod
     def predict(self, image: np.ndarray, *args: Any) -> Any:
@@ -82,7 +87,7 @@ class Attribute(ABC):
         Returns:
             The final predicted attributes.
         """
-        raise NotImplementedError("Subclasses must implement the predict method.")
+        raise NotImplementedError('Subclasses must implement the predict method.')
 
     def __call__(self, *args, **kwargs) -> Any:
         """

uniface/attribute/emotion.py

@@ -2,18 +2,19 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+
 import cv2
-import torch
 import numpy as np
-from typing import Tuple, Union, List
+import torch
 
 from uniface.attribute.base import Attribute
-from uniface.log import Logger
 from uniface.constants import DDAMFNWeights
 from uniface.face_utils import face_alignment
+from uniface.log import Logger
 from uniface.model_store import verify_model_weights
+from uniface.types import EmotionResult
 
-__all__ = ["Emotion"]
+__all__ = ['Emotion']
 
 
 class Emotion(Attribute):
@@ -28,7 +29,7 @@ class Emotion(Attribute):
     def __init__(
         self,
         model_weights: DDAMFNWeights = DDAMFNWeights.AFFECNET7,
-        input_size: Tuple[int, int] = (112, 112),
+        input_size: tuple[int, int] = (112, 112),
     ) -> None:
         """
         Initializes the emotion recognition model.
@@ -37,15 +38,30 @@ class Emotion(Attribute):
             model_weights (DDAMFNWeights): The enum for the model weights to load.
             input_size (Tuple[int, int]): The expected input size for the model.
         """
-        Logger.info(f"Initializing Emotion with model={model_weights.name}")
-        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        Logger.info(f'Initializing Emotion with model={model_weights.name}')
+
+        if torch.backends.mps.is_available():
+            self.device = torch.device('mps')
+        elif torch.cuda.is_available():
+            self.device = torch.device('cuda')
+        else:
+            self.device = torch.device('cpu')
+
         self.input_size = input_size
         self.model_path = verify_model_weights(model_weights)
 
         # Define emotion labels based on the selected model
-        self.emotion_labels = ["Neutral", "Happy", "Sad", "Surprise", "Fear", "Disgust", "Angry"]
+        self.emotion_labels = [
+            'Neutral',
+            'Happy',
+            'Sad',
+            'Surprise',
+            'Fear',
+            'Disgust',
+            'Angry',
+        ]
         if model_weights == DDAMFNWeights.AFFECNET8:
-            self.emotion_labels.append("Contempt")
+            self.emotion_labels.append('Contempt')
 
         self._initialize_model()
 
@@ -60,12 +76,12 @@ class Emotion(Attribute):
             dummy_input = torch.randn(1, 3, *self.input_size).to(self.device)
             with torch.no_grad():
                 self.model(dummy_input)
-            Logger.info(f"Successfully initialized Emotion model on {self.device}")
+            Logger.info(f'Successfully initialized Emotion model on {self.device}')
         except Exception as e:
             Logger.error(f"Failed to load Emotion model from '{self.model_path}'", exc_info=True)
-            raise RuntimeError(f"Failed to initialize Emotion model: {e}")
+            raise RuntimeError(f'Failed to initialize Emotion model: {e}') from e
 
-    def preprocess(self, image: np.ndarray, landmark: Union[List, np.ndarray]) -> torch.Tensor:
+    def preprocess(self, image: np.ndarray, landmark: list | np.ndarray) -> torch.Tensor:
         """
         Aligns the face using landmarks and preprocesses it into a tensor.
 
@@ -77,7 +93,7 @@ class Emotion(Attribute):
             torch.Tensor: The preprocessed image tensor ready for inference.
         """
         landmark = np.asarray(landmark)
-        
+
         aligned_image, _ = face_alignment(image, landmark)
 
         # Convert BGR to RGB, resize, normalize, and convert to a CHW tensor
@@ -90,7 +106,7 @@ class Emotion(Attribute):
 
         return torch.from_numpy(transposed_image).unsqueeze(0).to(self.device)
 
-    def postprocess(self, prediction: torch.Tensor) -> Tuple[str, float]:
+    def postprocess(self, prediction: torch.Tensor) -> EmotionResult:
         """
         Processes the raw model output to get the emotion label and confidence score.
         """
@@ -98,9 +114,9 @@ class Emotion(Attribute):
         pred_index = np.argmax(probabilities)
         emotion_label = self.emotion_labels[pred_index]
         confidence = float(probabilities[pred_index])
-        return emotion_label, confidence
+        return EmotionResult(emotion=emotion_label, confidence=confidence)
 
-    def predict(self, image: np.ndarray, landmark: Union[List, np.ndarray]) -> Tuple[str, float]:
+    def predict(self, image: np.ndarray, landmark: list | np.ndarray) -> EmotionResult:
         """
         Predicts the emotion from a single face specified by its landmarks.
         """
@@ -111,60 +127,3 @@ class Emotion(Attribute):
                 output = output[0]
 
         return self.postprocess(output)
-
-
-# TODO: below is only for testing, remove it later
-if __name__ == "__main__":
-    from uniface.detection import create_detector
-    from uniface.constants import RetinaFaceWeights
-
-    print("Initializing models for live inference...")
-    # 1. Initialize the face detector
-    # Using a smaller model for faster real-time performance
-    detector = create_detector(model_name=RetinaFaceWeights.MNET_V2)
-
-    # 2. Initialize the attribute predictor
-    emotion_predictor = Emotion()
-
-    # 3. Start webcam capture
-    cap = cv2.VideoCapture(0)
-    if not cap.isOpened():
-        print("Error: Could not open webcam.")
-        exit()
-
-    print("Starting webcam feed. Press 'q' to quit.")
-    while True:
-        ret, frame = cap.read()
-        if not ret:
-            print("Error: Failed to capture frame.")
-            break
-
-        # Detect faces in the current frame.
-        # This method returns a list of dictionaries for each detected face.
-        detections = detector.detect(frame)
-
-        # For each detected face, predict the emotion
-        for detection in detections:
-            box = detection['bbox']
-            landmark = detection['landmarks']
-            x1, y1, x2, y2 = map(int, box)
-
-            # Predict attributes using the landmark
-            emotion, confidence = emotion_predictor.predict(frame, landmark)
-            
-            # Prepare text and draw on the frame
-            label = f"{emotion} ({confidence:.2f})"
-            cv2.rectangle(frame, (x1, y1), (x2, y2), (255, 0, 0), 2)
-            cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255, 0, 0), 2)
-
-        # Display the resulting frame
-        cv2.imshow("Emotion Inference (Press 'q' to quit)", frame)
-
-        # Break the loop if 'q' is pressed
-        if cv2.waitKey(1) & 0xFF == ord('q'):
-            break
-
-    # Release resources
-    cap.release()
-    cv2.destroyAllWindows()
-    print("Inference stopped.")

uniface/attribute/fairface.py

@@ -0,0 +1,193 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+import cv2
+import numpy as np
+
+from uniface.attribute.base import Attribute
+from uniface.constants import FairFaceWeights
+from uniface.log import Logger
+from uniface.model_store import verify_model_weights
+from uniface.onnx_utils import create_onnx_session
+from uniface.types import AttributeResult
+
+__all__ = ['AGE_LABELS', 'RACE_LABELS', 'FairFace']
+
+# Label definitions
+RACE_LABELS = [
+    'White',
+    'Black',
+    'Latino Hispanic',
+    'East Asian',
+    'Southeast Asian',
+    'Indian',
+    'Middle Eastern',
+]
+AGE_LABELS = ['0-2', '3-9', '10-19', '20-29', '30-39', '40-49', '50-59', '60-69', '70+']
+
+
+class FairFace(Attribute):
+    """
+    FairFace attribute prediction model using ONNX Runtime.
+
+    This class inherits from the base `Attribute` class and implements the
+    functionality for predicting race (7 categories), gender (2 categories),
+    and age (9 groups) from a face image. It requires a bounding box to locate the face.
+
+    The model is trained on the FairFace dataset which provides balanced demographics
+    for more equitable predictions across different racial and gender groups.
+
+    Args:
+        model_name (FairFaceWeights): The enum specifying the model weights to load.
+            Defaults to `FairFaceWeights.DEFAULT`.
+        input_size (Optional[Tuple[int, int]]): Input size (height, width).
+            If None, defaults to (224, 224). Defaults to None.
+    """
+
+    def __init__(
+        self,
+        model_name: FairFaceWeights = FairFaceWeights.DEFAULT,
+        input_size: tuple[int, int] | None = None,
+    ) -> None:
+        """
+        Initializes the FairFace prediction model.
+
+        Args:
+            model_name (FairFaceWeights): The enum specifying the model weights to load.
+            input_size (Optional[Tuple[int, int]]): Input size (height, width).
+                If None, defaults to (224, 224).
+        """
+        Logger.info(f'Initializing FairFace with model={model_name.name}')
+        self.model_path = verify_model_weights(model_name)
+        self.input_size = input_size if input_size is not None else (224, 224)
+        self._initialize_model()
+
+    def _initialize_model(self) -> None:
+        """
+        Initializes the ONNX model and creates an inference session.
+        """
+        try:
+            self.session = create_onnx_session(self.model_path)
+            # Get model input details from the loaded model
+            input_meta = self.session.get_inputs()[0]
+            self.input_name = input_meta.name
+            self.output_names = [output.name for output in self.session.get_outputs()]
+            Logger.info(f'Successfully initialized FairFace model with input size {self.input_size}')
+        except Exception as e:
+            Logger.error(
+                f"Failed to load FairFace model from '{self.model_path}'",
+                exc_info=True,
+            )
+            raise RuntimeError(f'Failed to initialize FairFace model: {e}') from e
+
+    def preprocess(self, image: np.ndarray, bbox: list | np.ndarray | None = None) -> np.ndarray:
+        """
+        Preprocesses the face image for inference.
+
+        Args:
+            image (np.ndarray): The input image in BGR format.
+            bbox (Optional[Union[List, np.ndarray]]): Face bounding box [x1, y1, x2, y2].
+                If None, uses the entire image.
+
+        Returns:
+            np.ndarray: The preprocessed image blob ready for inference.
+        """
+        # Crop face if bbox provided
+        if bbox is not None:
+            bbox = np.asarray(bbox, dtype=int)
+            x1, y1, x2, y2 = bbox[:4]
+
+            # Add padding (25% of face size)
+            w, h = x2 - x1, y2 - y1
+            padding = 0.25
+            x_pad = int(w * padding)
+            y_pad = int(h * padding)
+
+            x1 = max(0, x1 - x_pad)
+            y1 = max(0, y1 - y_pad)
+            x2 = min(image.shape[1], x2 + x_pad)
+            y2 = min(image.shape[0], y2 + y_pad)
+
+            image = image[y1:y2, x1:x2]
+
+        # Resize to input size (width, height for cv2.resize)
+        image = cv2.resize(image, self.input_size[::-1])
+
+        # Convert BGR to RGB
+        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+        # Normalize with ImageNet mean and std
+        image = image.astype(np.float32) / 255.0
+        mean = np.array([0.485, 0.456, 0.406], dtype=np.float32)
+        std = np.array([0.229, 0.224, 0.225], dtype=np.float32)
+        image = (image - mean) / std
+
+        # Transpose to CHW format and add batch dimension
+        image = np.transpose(image, (2, 0, 1))
+        image = np.expand_dims(image, axis=0)
+
+        return image
+
+    def postprocess(self, prediction: tuple[np.ndarray, np.ndarray, np.ndarray]) -> AttributeResult:
+        """
+        Processes the raw model output to extract race, gender, and age.
+
+        Args:
+            prediction (Tuple[np.ndarray, np.ndarray, np.ndarray]): Raw outputs from model
+                (race_logits, gender_logits, age_logits).
+
+        Returns:
+            AttributeResult: Result containing gender (0=Female, 1=Male), age_group, and race.
+        """
+        race_logits, gender_logits, age_logits = prediction
+
+        # Apply softmax
+        race_probs = self._softmax(race_logits[0])
+        gender_probs = self._softmax(gender_logits[0])
+        age_probs = self._softmax(age_logits[0])
+
+        # Get predictions
+        race_idx = int(np.argmax(race_probs))
+        raw_gender_idx = int(np.argmax(gender_probs))
+        age_idx = int(np.argmax(age_probs))
+
+        # Normalize gender: model outputs 0=Male, 1=Female → standard 0=Female, 1=Male
+        gender = 1 - raw_gender_idx
+
+        return AttributeResult(
+            gender=gender,
+            age_group=AGE_LABELS[age_idx],
+            race=RACE_LABELS[race_idx],
+        )
+
+    def predict(self, image: np.ndarray, bbox: list | np.ndarray | None = None) -> AttributeResult:
+        """
+        Predicts race, gender, and age for a face.
+
+        Args:
+            image (np.ndarray): The input image in BGR format.
+            bbox (Optional[Union[List, np.ndarray]]): Face bounding box [x1, y1, x2, y2].
+                If None, uses the entire image.
+
+        Returns:
+            AttributeResult: Result containing:
+                - gender: 0=Female, 1=Male
+                - age_group: Age range string like "20-29"
+                - race: Race/ethnicity label
+        """
+        # Preprocess
+        input_blob = self.preprocess(image, bbox)
+
+        # Inference
+        outputs = self.session.run(self.output_names, {self.input_name: input_blob})
+
+        # Postprocess
+        return self.postprocess(outputs)
+
+    @staticmethod
+    def _softmax(x: np.ndarray) -> np.ndarray:
+        """Compute softmax values for numerical stability."""
+        exp_x = np.exp(x - np.max(x))
+        return exp_x / np.sum(exp_x)

uniface/common.py

@@ -2,24 +2,42 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-import cv2
-import math
+from __future__ import annotations
+
 import itertools
+import math
+
+import cv2
 import numpy as np
 
-from typing import Tuple, List
+__all__ = [
+    'decode_boxes',
+    'decode_landmarks',
+    'distance2bbox',
+    'distance2kps',
+    'generate_anchors',
+    'non_max_suppression',
+    'resize_image',
+]
 
 
-def resize_image(frame, target_shape: Tuple[int, int] = (640, 640)) -> Tuple[np.ndarray, float]:
-    """
-    Resize an image to fit within a target shape while keeping its aspect ratio.
+def resize_image(
+    frame: np.ndarray,
+    target_shape: tuple[int, int] = (640, 640),
+) -> tuple[np.ndarray, float]:
+    """Resize an image to fit within a target shape while keeping its aspect ratio.
+
+    The image is resized to fit within the target dimensions and placed on a
+    blank canvas (zero-padded to target size).
 
     Args:
-        frame (np.ndarray): Input image.
-        target_shape (Tuple[int, int]): Target size (width, height). Defaults to (640, 640).
+        frame: Input image with shape (H, W, C).
+        target_shape: Target size as (width, height). Defaults to (640, 640).
 
     Returns:
-        Tuple[np.ndarray, float]: Resized image on a blank canvas and the resize factor.
+        A tuple containing:
+            - Resized image on a blank canvas with shape (height, width, 3).
+            - The resize factor as a float.
     """
     width, height = target_shape
 
@@ -43,28 +61,21 @@ def resize_image(frame, target_shape: Tuple[int, int] = (640, 640)) -> Tuple[np.
     return image, resize_factor
 
 
-def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> np.ndarray:
-    """
-    Generate anchor boxes for a given image size.
+def generate_anchors(image_size: tuple[int, int] = (640, 640)) -> np.ndarray:
+    """Generate anchor boxes for a given image size (RetinaFace specific).
 
     Args:
-        image_size (Tuple[int, int]): Input image size (width, height). Defaults to (640, 640).
+        image_size: Input image size as (width, height). Defaults to (640, 640).
 
     Returns:
-        np.ndarray: Anchor box coordinates as a NumPy array.
+        Anchor box coordinates as a numpy array with shape (num_anchors, 4).
     """
-    image_size = image_size
-
+    # RetinaFace FPN strides and corresponding anchor sizes per level
     steps = [8, 16, 32]
     min_sizes = [[16, 32], [64, 128], [256, 512]]
 
     anchors = []
-    feature_maps = [
-        [
-            math.ceil(image_size[0] / step),
-            math.ceil(image_size[1] / step)
-        ] for step in steps
-    ]
+    feature_maps = [[math.ceil(image_size[0] / step), math.ceil(image_size[1] / step)] for step in steps]
 
     for k, (map_height, map_width) in enumerate(feature_maps):
         step = steps[k]
@@ -82,16 +93,15 @@ def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> np.ndarray:
     return output
 
 
-def non_max_supression(dets: List[np.ndarray], threshold: float):
-    """
-    Apply Non-Maximum Suppression (NMS) to reduce overlapping bounding boxes based on a threshold.
+def non_max_suppression(dets: np.ndarray, threshold: float) -> list[int]:
+    """Apply Non-Maximum Suppression (NMS) to reduce overlapping bounding boxes.
 
     Args:
-        dets (numpy.ndarray): Array of detections with each row as [x1, y1, x2, y2, score].
-        threshold (float): IoU threshold for suppression.
+        dets: Array of detections with each row as [x1, y1, x2, y2, score].
+        threshold: IoU threshold for suppression.
 
     Returns:
-        list: Indices of bounding boxes retained after suppression.
+        Indices of bounding boxes retained after suppression.
     """
     x1 = dets[:, 0]
     y1 = dets[:, 1]
@@ -122,19 +132,25 @@ def non_max_supression(dets: List[np.ndarray], threshold: float):
     return keep
 
 
-def decode_boxes(loc, priors, variances=[0.1, 0.2]) -> np.ndarray:
-    """
-    Decode locations from predictions using priors to undo
-    the encoding done for offset regression at train time.
+def decode_boxes(
+    loc: np.ndarray,
+    priors: np.ndarray,
+    variances: list[float] | None = None,
+) -> np.ndarray:
+    """Decode locations from predictions using priors (RetinaFace specific).
+
+    Undoes the encoding done for offset regression at train time.
 
     Args:
-        loc (np.ndarray): Location predictions for loc layers, shape: [num_priors, 4]
-        priors (np.ndarray): Prior boxes in center-offset form, shape: [num_priors, 4]
-        variances (list[float]): Variances of prior boxes
+        loc: Location predictions for loc layers, shape: [num_priors, 4].
+        priors: Prior boxes in center-offset form, shape: [num_priors, 4].
+        variances: Variances of prior boxes. Defaults to [0.1, 0.2].
 
     Returns:
-        np.ndarray: Decoded bounding box predictions
+        Decoded bounding box predictions with shape [num_priors, 4].
     """
+    if variances is None:
+        variances = [0.1, 0.2]
     # Compute centers of predicted boxes
     cxcy = priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:]
 
@@ -149,18 +165,23 @@ def decode_boxes(loc, priors, variances=[0.1, 0.2]) -> np.ndarray:
     return boxes
 
 
-def decode_landmarks(predictions, priors, variances=[0.1, 0.2]) -> np.ndarray:
-    """
-    Decode landmark predictions using prior boxes.
+def decode_landmarks(
+    predictions: np.ndarray,
+    priors: np.ndarray,
+    variances: list[float] | None = None,
+) -> np.ndarray:
+    """Decode landmark predictions using prior boxes (RetinaFace specific).
 
     Args:
-        predictions (np.ndarray): Landmark predictions, shape: [num_priors, 10]
-        priors (np.ndarray): Prior boxes, shape: [num_priors, 4]
-        variances (list): Scaling factors for landmark offsets.
+        predictions: Landmark predictions, shape: [num_priors, 10].
+        priors: Prior boxes, shape: [num_priors, 4].
+        variances: Scaling factors for landmark offsets. Defaults to [0.1, 0.2].
 
     Returns:
-        np.ndarray: Decoded landmarks, shape: [num_priors, 10]
+        Decoded landmarks, shape: [num_priors, 10].
     """
+    if variances is None:
+        variances = [0.1, 0.2]
 
     # Reshape predictions to [num_priors, 5, 2] to process landmark points
     predictions = predictions.reshape(predictions.shape[0], 5, 2)
@@ -176,3 +197,65 @@ def decode_landmarks(predictions, priors, variances=[0.1, 0.2]) -> np.ndarray:
     landmarks = landmarks.reshape(landmarks.shape[0], -1)
 
     return landmarks
+
+
+def distance2bbox(
+    points: np.ndarray,
+    distance: np.ndarray,
+    max_shape: tuple[int, int] | None = None,
+) -> np.ndarray:
+    """Decode distance prediction to bounding box (SCRFD specific).
+
+    Args:
+        points: Anchor points with shape (n, 2), [x, y].
+        distance: Distance from the given point to 4 boundaries
+            (left, top, right, bottom) with shape (n, 4).
+        max_shape: Shape of the image (height, width) for clipping.
+
+    Returns:
+        Decoded bounding boxes with shape (n, 4) as [x1, y1, x2, y2].
+    """
+    x1 = points[:, 0] - distance[:, 0]
+    y1 = points[:, 1] - distance[:, 1]
+    x2 = points[:, 0] + distance[:, 2]
+    y2 = points[:, 1] + distance[:, 3]
+
+    if max_shape is not None:
+        x1 = np.clip(x1, 0, max_shape[1])
+        y1 = np.clip(y1, 0, max_shape[0])
+        x2 = np.clip(x2, 0, max_shape[1])
+        y2 = np.clip(y2, 0, max_shape[0])
+    else:
+        x1 = np.maximum(x1, 0)
+        y1 = np.maximum(y1, 0)
+        x2 = np.maximum(x2, 0)
+        y2 = np.maximum(y2, 0)
+
+    return np.stack([x1, y1, x2, y2], axis=-1)
+
+
+def distance2kps(
+    points: np.ndarray,
+    distance: np.ndarray,
+    max_shape: tuple[int, int] | None = None,
+) -> np.ndarray:
+    """Decode distance prediction to keypoints (SCRFD specific).
+
+    Args:
+        points: Anchor points with shape (n, 2), [x, y].
+        distance: Distance from the given point to keypoints with shape (n, 2k).
+        max_shape: Shape of the image (height, width) for clipping.
+
+    Returns:
+        Decoded keypoints with shape (n, 2k).
+    """
+    preds = []
+    for i in range(0, distance.shape[1], 2):
+        px = points[:, i % 2] + distance[:, i]
+        py = points[:, i % 2 + 1] + distance[:, i + 1]
+        if max_shape is not None:
+            px = np.clip(px, 0, max_shape[1])
+            py = np.clip(py, 0, max_shape[0])
+        preds.append(px)
+        preds.append(py)
+    return np.stack(preds, axis=-1)

uniface/constants.py

@@ -3,7 +3,7 @@
 # GitHub: https://github.com/yakhyo
 
 from enum import Enum
-from typing import Dict
+
 
 # fmt: off
 class SphereFaceWeights(str, Enum):
@@ -54,6 +54,22 @@ class SCRFDWeights(str, Enum):
     SCRFD_500M_KPS = "scrfd_500m"
 
 
+class YOLOv5FaceWeights(str, Enum):
+    """
+    Trained on WIDER FACE dataset.
+    Original implementation: https://github.com/deepcam-cn/yolov5-face
+    Exported to ONNX from: https://github.com/yakhyo/yolov5-face-onnx-inference
+
+    Model Performance (WIDER FACE):
+    - YOLOV5N: 11MB, 93.61% Easy / 91.52% Medium / 80.53% Hard
+    - YOLOV5S: 28MB, 94.33% Easy / 92.61% Medium / 83.15% Hard
+    - YOLOV5M: 82MB, 95.30% Easy / 93.76% Medium / 85.28% Hard
+    """
+    YOLOV5N = "yolov5n"
+    YOLOV5S = "yolov5s"
+    YOLOV5M = "yolov5m"
+
+
 class DDAMFNWeights(str, Enum):
     """
     Trained on AffectNet dataset.
@@ -71,6 +87,15 @@ class AgeGenderWeights(str, Enum):
     DEFAULT = "age_gender"
 
 
+class FairFaceWeights(str, Enum):
+    """
+    FairFace attribute prediction (race, gender, age).
+    Trained on FairFace dataset with balanced demographics.
+    https://github.com/yakhyo/fairface-onnx
+    """
+    DEFAULT = "fairface"
+
+
 class LandmarkWeights(str, Enum):
     """
     MobileNet 0.5 from Insightface
@@ -78,87 +103,140 @@ class LandmarkWeights(str, Enum):
     """
     DEFAULT = "2d_106"
 
-# fmt: on
+
+class GazeWeights(str, Enum):
+    """
+    MobileGaze: Real-Time Gaze Estimation models.
+    Trained on Gaze360 dataset.
+    https://github.com/yakhyo/gaze-estimation
+    """
+    RESNET18     = "gaze_resnet18"
+    RESNET34     = "gaze_resnet34"
+    RESNET50     = "gaze_resnet50"
+    MOBILENET_V2 = "gaze_mobilenetv2"
+    MOBILEONE_S0 = "gaze_mobileone_s0"
 
 
-MODEL_URLS: Dict[Enum, str] = {
+class ParsingWeights(str, Enum):
+    """
+    Face Parsing: Semantic Segmentation of Facial Components.
+    Trained on CelebAMask-HQ dataset.
+    https://github.com/yakhyo/face-parsing
+    """
+    RESNET18 = "parsing_resnet18"
+    RESNET34 = "parsing_resnet34"
 
+
+class MiniFASNetWeights(str, Enum):
+    """
+    MiniFASNet: Lightweight Face Anti-Spoofing models.
+    Trained on face anti-spoofing datasets.
+    https://github.com/yakhyo/face-anti-spoofing
+
+    Model Variants:
+    - V1SE: Uses scale=4.0 for face crop (squeese-and-excitation version)
+    - V2: Uses scale=2.7 for face crop (improved version)
+    """
+    V1SE = "minifasnet_v1se"
+    V2   = "minifasnet_v2"
+
+
+MODEL_URLS: dict[Enum, str] = {
     # RetinaFace
-    RetinaFaceWeights.MNET_025: 'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1_0.25.onnx',
-    RetinaFaceWeights.MNET_050: 'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1_0.50.onnx',
-    RetinaFaceWeights.MNET_V1:  'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1.onnx',
-    RetinaFaceWeights.MNET_V2:  'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv2.onnx',
-    RetinaFaceWeights.RESNET18: 'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_r18.onnx',
-    RetinaFaceWeights.RESNET34: 'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_r34.onnx',
-
+    RetinaFaceWeights.MNET_025:      'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1_0.25.onnx',
+    RetinaFaceWeights.MNET_050:      'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1_0.50.onnx',
+    RetinaFaceWeights.MNET_V1:       'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1.onnx',
+    RetinaFaceWeights.MNET_V2:       'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv2.onnx',
+    RetinaFaceWeights.RESNET18:      'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_r18.onnx',
+    RetinaFaceWeights.RESNET34:      'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_r34.onnx',
     # MobileFace
     MobileFaceWeights.MNET_025:      'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv1_0.25.onnx',
     MobileFaceWeights.MNET_V2:       'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv2.onnx',
     MobileFaceWeights.MNET_V3_SMALL: 'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv3_small.onnx',
     MobileFaceWeights.MNET_V3_LARGE: 'https://github.com/yakhyo/uniface/releases/download/weights/mobilenetv3_large.onnx',
-
     # SphereFace
-    SphereFaceWeights.SPHERE20: 'https://github.com/yakhyo/uniface/releases/download/weights/sphere20.onnx',
-    SphereFaceWeights.SPHERE36: 'https://github.com/yakhyo/uniface/releases/download/weights/sphere36.onnx',
-
-
+    SphereFaceWeights.SPHERE20:      'https://github.com/yakhyo/uniface/releases/download/weights/sphere20.onnx',
+    SphereFaceWeights.SPHERE36:      'https://github.com/yakhyo/uniface/releases/download/weights/sphere36.onnx',
     # ArcFace
-    ArcFaceWeights.MNET:   'https://github.com/yakhyo/uniface/releases/download/weights/w600k_mbf.onnx',
-    ArcFaceWeights.RESNET: 'https://github.com/yakhyo/uniface/releases/download/weights/w600k_r50.onnx',
-
+    ArcFaceWeights.MNET:             'https://github.com/yakhyo/uniface/releases/download/weights/w600k_mbf.onnx',
+    ArcFaceWeights.RESNET:           'https://github.com/yakhyo/uniface/releases/download/weights/w600k_r50.onnx',
     # SCRFD
-    SCRFDWeights.SCRFD_10G_KPS:  'https://github.com/yakhyo/uniface/releases/download/weights/scrfd_10g_kps.onnx',
-    SCRFDWeights.SCRFD_500M_KPS: 'https://github.com/yakhyo/uniface/releases/download/weights/scrfd_500m_kps.onnx',
-
-
+    SCRFDWeights.SCRFD_10G_KPS:      'https://github.com/yakhyo/uniface/releases/download/weights/scrfd_10g_kps.onnx',
+    SCRFDWeights.SCRFD_500M_KPS:     'https://github.com/yakhyo/uniface/releases/download/weights/scrfd_500m_kps.onnx',
+    # YOLOv5-Face
+    YOLOv5FaceWeights.YOLOV5N:       'https://github.com/yakhyo/yolov5-face-onnx-inference/releases/download/weights/yolov5n_face.onnx',
+    YOLOv5FaceWeights.YOLOV5S:       'https://github.com/yakhyo/yolov5-face-onnx-inference/releases/download/weights/yolov5s_face.onnx',
+    YOLOv5FaceWeights.YOLOV5M:       'https://github.com/yakhyo/yolov5-face-onnx-inference/releases/download/weights/yolov5m_face.onnx',
     # DDAFM
-    DDAMFNWeights.AFFECNET7: 'https://github.com/yakhyo/uniface/releases/download/weights/affecnet7.script',
-    DDAMFNWeights.AFFECNET8: 'https://github.com/yakhyo/uniface/releases/download/weights/affecnet8.script',
-
+    DDAMFNWeights.AFFECNET7:         'https://github.com/yakhyo/uniface/releases/download/weights/affecnet7.script',
+    DDAMFNWeights.AFFECNET8:         'https://github.com/yakhyo/uniface/releases/download/weights/affecnet8.script',
     # AgeGender
-    AgeGenderWeights.DEFAULT: 'https://github.com/yakhyo/uniface/releases/download/weights/genderage.onnx',
-
+    AgeGenderWeights.DEFAULT:        'https://github.com/yakhyo/uniface/releases/download/weights/genderage.onnx',
+    # FairFace
+    FairFaceWeights.DEFAULT:         'https://github.com/yakhyo/fairface-onnx/releases/download/weights/fairface.onnx',
     # Landmarks
-    LandmarkWeights.DEFAULT: 'https://github.com/yakhyo/uniface/releases/download/weights/2d106det.onnx',
+    LandmarkWeights.DEFAULT:         'https://github.com/yakhyo/uniface/releases/download/weights/2d106det.onnx',
+    # Gaze (MobileGaze)
+    GazeWeights.RESNET18:            'https://github.com/yakhyo/gaze-estimation/releases/download/weights/resnet18_gaze.onnx',
+    GazeWeights.RESNET34:            'https://github.com/yakhyo/gaze-estimation/releases/download/weights/resnet34_gaze.onnx',
+    GazeWeights.RESNET50:            'https://github.com/yakhyo/gaze-estimation/releases/download/weights/resnet50_gaze.onnx',
+    GazeWeights.MOBILENET_V2:        'https://github.com/yakhyo/gaze-estimation/releases/download/weights/mobilenetv2_gaze.onnx',
+    GazeWeights.MOBILEONE_S0:        'https://github.com/yakhyo/gaze-estimation/releases/download/weights/mobileone_s0_gaze.onnx',
+    # Parsing
+    ParsingWeights.RESNET18:         'https://github.com/yakhyo/face-parsing/releases/download/weights/resnet18.onnx',
+    ParsingWeights.RESNET34:         'https://github.com/yakhyo/face-parsing/releases/download/weights/resnet34.onnx',
+    # Anti-Spoofing (MiniFASNet)
+    MiniFASNetWeights.V1SE:          'https://github.com/yakhyo/face-anti-spoofing/releases/download/weights/MiniFASNetV1SE.onnx',
+    MiniFASNetWeights.V2:            'https://github.com/yakhyo/face-anti-spoofing/releases/download/weights/MiniFASNetV2.onnx',
 }
 
-MODEL_SHA256: Dict[Enum, str] = {
+MODEL_SHA256: dict[Enum, str] = {
     # RetinaFace
-    RetinaFaceWeights.MNET_025: 'b7a7acab55e104dce6f32cdfff929bd83946da5cd869b9e2e9bdffafd1b7e4a5',
-    RetinaFaceWeights.MNET_050: 'd8977186f6037999af5b4113d42ba77a84a6ab0c996b17c713cc3d53b88bfc37',
-    RetinaFaceWeights.MNET_V1:  '75c961aaf0aff03d13c074e9ec656e5510e174454dd4964a161aab4fe5f04153',
-    RetinaFaceWeights.MNET_V2:  '3ca44c045651cabeed1193a1fae8946ad1f3a55da8fa74b341feab5a8319f757',
-    RetinaFaceWeights.RESNET18: 'e8b5ddd7d2c3c8f7c942f9f10cec09d8e319f78f09725d3f709631de34fb649d',
-    RetinaFaceWeights.RESNET34: 'bd0263dc2a465d32859555cb1741f2d98991eb0053696e8ee33fec583d30e630',
-
+    RetinaFaceWeights.MNET_025:      'b7a7acab55e104dce6f32cdfff929bd83946da5cd869b9e2e9bdffafd1b7e4a5',
+    RetinaFaceWeights.MNET_050:      'd8977186f6037999af5b4113d42ba77a84a6ab0c996b17c713cc3d53b88bfc37',
+    RetinaFaceWeights.MNET_V1:       '75c961aaf0aff03d13c074e9ec656e5510e174454dd4964a161aab4fe5f04153',
+    RetinaFaceWeights.MNET_V2:       '3ca44c045651cabeed1193a1fae8946ad1f3a55da8fa74b341feab5a8319f757',
+    RetinaFaceWeights.RESNET18:      'e8b5ddd7d2c3c8f7c942f9f10cec09d8e319f78f09725d3f709631de34fb649d',
+    RetinaFaceWeights.RESNET34:      'bd0263dc2a465d32859555cb1741f2d98991eb0053696e8ee33fec583d30e630',
     # MobileFace
     MobileFaceWeights.MNET_025:      'eeda7d23d9c2b40cf77fa8da8e895b5697465192648852216074679657f8ee8b',
     MobileFaceWeights.MNET_V2:       '38b148284dd48cc898d5d4453104252fbdcbacc105fe3f0b80e78954d9d20d89',
     MobileFaceWeights.MNET_V3_SMALL: 'd4acafa1039a82957aa8a9a1dac278a401c353a749c39df43de0e29cc1c127c3',
     MobileFaceWeights.MNET_V3_LARGE: '0e48f8e11f070211716d03e5c65a3db35a5e917cfb5bc30552358629775a142a',
-
     # SphereFace
-    SphereFaceWeights.SPHERE20: 'c02878cf658eb1861f580b7e7144b0d27cc29c440bcaa6a99d466d2854f14c9d',
-    SphereFaceWeights.SPHERE36: '13b3890cd5d7dec2b63f7c36fd7ce07403e5a0bbb701d9647c0289e6cbe7bb20',
-
-
+    SphereFaceWeights.SPHERE20:      'c02878cf658eb1861f580b7e7144b0d27cc29c440bcaa6a99d466d2854f14c9d',
+    SphereFaceWeights.SPHERE36:      '13b3890cd5d7dec2b63f7c36fd7ce07403e5a0bbb701d9647c0289e6cbe7bb20',
     # ArcFace
-    ArcFaceWeights.MNET:   '9cc6e4a75f0e2bf0b1aed94578f144d15175f357bdc05e815e5c4a02b319eb4f',
-    ArcFaceWeights.RESNET: '4c06341c33c2ca1f86781dab0e829f88ad5b64be9fba56e56bc9ebdefc619e43',
-
+    ArcFaceWeights.MNET:             '9cc6e4a75f0e2bf0b1aed94578f144d15175f357bdc05e815e5c4a02b319eb4f',
+    ArcFaceWeights.RESNET:           '4c06341c33c2ca1f86781dab0e829f88ad5b64be9fba56e56bc9ebdefc619e43',
     # SCRFD
-    SCRFDWeights.SCRFD_10G_KPS:  '5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91',
-    SCRFDWeights.SCRFD_500M_KPS: '5e4447f50245bbd7966bd6c0fa52938c61474a04ec7def48753668a9d8b4ea3a',
-
+    SCRFDWeights.SCRFD_10G_KPS:      '5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91',
+    SCRFDWeights.SCRFD_500M_KPS:     '5e4447f50245bbd7966bd6c0fa52938c61474a04ec7def48753668a9d8b4ea3a',
+    # YOLOv5-Face
+    YOLOv5FaceWeights.YOLOV5N:       'eb244a06e36999db732b317c2b30fa113cd6cfc1a397eaf738f2d6f33c01f640',
+    YOLOv5FaceWeights.YOLOV5S:       'fc682801cd5880e1e296184a14aea0035486b5146ec1a1389d2e7149cb134bb2',
+    YOLOv5FaceWeights.YOLOV5M:       '04302ce27a15bde3e20945691b688e2dd018a10e92dd8932146bede6a49207b2',
     # DDAFM
-    DDAMFNWeights.AFFECNET7: '10535bf8b6afe8e9d6ae26cea6c3add9a93036e9addb6adebfd4a972171d015d',
-    DDAMFNWeights.AFFECNET8: '8c66963bc71db42796a14dfcbfcd181b268b65a3fc16e87147d6a3a3d7e0f487',
-
+    DDAMFNWeights.AFFECNET7:         '10535bf8b6afe8e9d6ae26cea6c3add9a93036e9addb6adebfd4a972171d015d',
+    DDAMFNWeights.AFFECNET8:         '8c66963bc71db42796a14dfcbfcd181b268b65a3fc16e87147d6a3a3d7e0f487',
     # AgeGender
-    AgeGenderWeights.DEFAULT: '4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb',
-
+    AgeGenderWeights.DEFAULT:        '4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb',
+    # FairFace
+    FairFaceWeights.DEFAULT:         '9c8c47d437cd310538d233f2465f9ed0524cb7fb51882a37f74e8bc22437fdbf',
     # Landmark
-    LandmarkWeights.DEFAULT: 'f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf',
+    LandmarkWeights.DEFAULT:         'f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf',
+    # MobileGaze (trained on Gaze360)
+    GazeWeights.RESNET18:            '23d5d7e4f6f40dce8c35274ce9d08b45b9e22cbaaf5af73182f473229d713d31',
+    GazeWeights.RESNET34:            '4457ee5f7acd1a5ab02da4b61f02fc3a0b17adbf3844dd0ba3cd4288f2b5e1de',
+    GazeWeights.RESNET50:            'e1eaf98f5ec7c89c6abe7cfe39f7be83e747163f98d1ff945c0603b3c521be22',
+    GazeWeights.MOBILENET_V2:        'fdcdb84e3e6421b5a79e8f95139f249fc258d7f387eed5ddac2b80a9a15ce076',
+    GazeWeights.MOBILEONE_S0:        'c0b5a4f4a0ffd24f76ab3c1452354bb2f60110899fd9a88b464c75bafec0fde8',
+    # Face Parsing
+    ParsingWeights.RESNET18:         '0d9bd318e46987c3bdbfacae9e2c0f461cae1c6ac6ea6d43bbe541a91727e33f',
+    ParsingWeights.RESNET34:         '5b805bba7b5660ab7070b5a381dcf75e5b3e04199f1e9387232a77a00095102e',
+    # Anti-Spoofing (MiniFASNet)
+    MiniFASNetWeights.V1SE:          'ebab7f90c7833fbccd46d3a555410e78d969db5438e169b6524be444862b3676',
+    MiniFASNetWeights.V2:            'b32929adc2d9c34b9486f8c4c7bc97c1b69bc0ea9befefc380e4faae4e463907',
 }
 
 CHUNK_SIZE = 8192

uniface/detection/__init__.py

@@ -2,45 +2,53 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from __future__ import annotations
+
+from typing import Any
 
 import numpy as np
-from typing import Tuple, Dict, Any, List
 
-from .scrfd import SCRFD
+from uniface.types import Face
+
 from .base import BaseDetector
 from .retinaface import RetinaFace
+from .scrfd import SCRFD
+from .yolov5 import YOLOv5Face
 
-# Global cache for detector instances
-_detector_cache: Dict[str, BaseDetector] = {}
+# Global cache for detector instances (keyed by method name + config hash)
+_detector_cache: dict[str, BaseDetector] = {}
 
 
-def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs) -> List[Dict[str, Any]]:
-    """
-    High-level face detection function.
+def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs: Any) -> list[Face]:
+    """High-level face detection function.
+
+    Detects faces in an image using the specified detection method.
+    Results are cached for repeated calls with the same configuration.
 
     Args:
-        image (np.ndarray): Input image as numpy array.
-        method (str): Detection method to use. Options: 'retinaface', 'scrfd'.
+        image: Input image as numpy array with shape (H, W, C) in BGR format.
+        method: Detection method to use. Options: 'retinaface', 'scrfd', 'yolov5face'.
         **kwargs: Additional arguments passed to the detector.
 
     Returns:
-        List[Dict[str, Any]]: A list of dictionaries, where each dictionary represents a detected face and contains:
-            - 'bbox' (List[float]): [x1, y1, x2, y2] bounding box coordinates.
-            - 'confidence' (float): The confidence score of the detection.
-            - 'landmarks' (List[List[float]]): 5-point facial landmarks.
+        A list of Face objects, each containing:
+            - bbox: [x1, y1, x2, y2] bounding box coordinates.
+            - confidence: The confidence score of the detection.
+            - landmarks: 5-point facial landmarks with shape (5, 2).
 
     Example:
         >>> from uniface import detect_faces
-        >>> image = cv2.imread("your_image.jpg")
-        >>> faces = detect_faces(image, method='retinaface', conf_thresh=0.8)
+        >>> import cv2
+        >>> image = cv2.imread('your_image.jpg')
+        >>> faces = detect_faces(image, method='retinaface', confidence_threshold=0.8)
         >>> for face in faces:
-        ...     print(f"Found face with confidence: {face['confidence']}")
-        ...     print(f"BBox: {face['bbox']}")
+        ...     print(f'Found face with confidence: {face.confidence}')
+        ...     print(f'BBox: {face.bbox}')
     """
     method_name = method.lower()
-    
+
     sorted_kwargs = sorted(kwargs.items())
-    cache_key = f"{method_name}_{str(sorted_kwargs)}"
+    cache_key = f'{method_name}_{sorted_kwargs!s}'
 
     if cache_key not in _detector_cache:
         # Pass kwargs to create the correctly configured detector
@@ -50,40 +58,36 @@ def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs) -> Lis
     return detector.detect(image)
 
 
-def create_detector(method: str = 'retinaface', **kwargs) -> BaseDetector:
-    """
-    Factory function to create face detectors.
+def create_detector(method: str = 'retinaface', **kwargs: Any) -> BaseDetector:
+    """Factory function to create face detectors.
 
     Args:
-        method (str): Detection method. Options:
+        method: Detection method. Options:
             - 'retinaface': RetinaFace detector (default)
             - 'scrfd': SCRFD detector (fast and accurate)
-        **kwargs: Detector-specific parameters
+            - 'yolov5face': YOLOv5-Face detector (accurate with landmarks)
+        **kwargs: Detector-specific parameters.
 
     Returns:
-        BaseDetector: Initialized detector instance
+        Initialized detector instance.
 
     Raises:
-        ValueError: If method is not supported
+        ValueError: If method is not supported.
 
-    Examples:
+    Example:
         >>> # Basic usage
         >>> detector = create_detector('retinaface')
 
         >>> # SCRFD detector with custom parameters
+        >>> from uniface.constants import SCRFDWeights
         >>> detector = create_detector(
-        ...     'scrfd',
-        ...     model_name=SCRFDWeights.SCRFD_10G_KPS,
-        ...     conf_thresh=0.8,
-        ...     input_size=(640, 640)
+        ...     'scrfd', model_name=SCRFDWeights.SCRFD_10G_KPS, confidence_threshold=0.8, input_size=(640, 640)
         ... )
 
         >>> # RetinaFace detector
+        >>> from uniface.constants import RetinaFaceWeights
         >>> detector = create_detector(
-        ...     'retinaface',
-        ...     model_name=RetinaFaceWeights.MNET_V2,
-        ...     conf_thresh=0.8,
-        ...     nms_thresh=0.4
+        ...     'retinaface', model_name=RetinaFaceWeights.MNET_V2, confidence_threshold=0.8, nms_threshold=0.4
         ... )
     """
     method = method.lower()
@@ -94,20 +98,20 @@ def create_detector(method: str = 'retinaface', **kwargs) -> BaseDetector:
     elif method == 'scrfd':
         return SCRFD(**kwargs)
 
+    elif method == 'yolov5face':
+        return YOLOv5Face(**kwargs)
+
     else:
-        available_methods = ['retinaface', 'scrfd']
-        raise ValueError(
-            f"Unsupported detection method: '{method}'. "
-            f"Available methods: {available_methods}"
-        )
+        available_methods = ['retinaface', 'scrfd', 'yolov5face']
+        raise ValueError(f"Unsupported detection method: '{method}'. Available methods: {available_methods}")
 
 
-def list_available_detectors() -> Dict[str, Dict[str, Any]]:
-    """
-    List all available detection methods with their descriptions and parameters.
+def list_available_detectors() -> dict[str, dict[str, Any]]:
+    """List all available detection methods with their descriptions and parameters.
 
     Returns:
-        Dict[str, Dict[str, Any]]: Dictionary of detector information
+        Dictionary mapping detector names to their information including
+        description, landmark support, paper reference, and default parameters.
     """
     return {
         'retinaface': {
@@ -116,10 +120,10 @@ def list_available_detectors() -> Dict[str, Dict[str, Any]]:
             'paper': 'https://arxiv.org/abs/1905.00641',
             'default_params': {
                 'model_name': 'mnet_v2',
-                'conf_thresh': 0.5,
-                'nms_thresh': 0.4,
-                'input_size': (640, 640)
-            }
+                'confidence_threshold': 0.5,
+                'nms_threshold': 0.4,
+                'input_size': (640, 640),
+            },
         },
         'scrfd': {
             'description': 'SCRFD detector - fast and accurate with efficient architecture',
@@ -127,19 +131,31 @@ def list_available_detectors() -> Dict[str, Dict[str, Any]]:
             'paper': 'https://arxiv.org/abs/2105.04714',
             'default_params': {
                 'model_name': 'scrfd_10g_kps',
-                'conf_thresh': 0.5,
-                'nms_thresh': 0.4,
-                'input_size': (640, 640)
-            }
-        }
+                'confidence_threshold': 0.5,
+                'nms_threshold': 0.4,
+                'input_size': (640, 640),
+            },
+        },
+        'yolov5face': {
+            'description': 'YOLOv5-Face detector - accurate face detection with landmarks',
+            'supports_landmarks': True,
+            'paper': 'https://arxiv.org/abs/2105.12931',
+            'default_params': {
+                'model_name': 'yolov5s_face',
+                'confidence_threshold': 0.25,
+                'nms_threshold': 0.45,
+                'input_size': 640,
+            },
+        },
     }
 
 
 __all__ = [
-    'detect_faces',
-    'create_detector',
-    'list_available_detectors',
     'SCRFD',
-    'RetinaFace',
     'BaseDetector',
+    'RetinaFace',
+    'YOLOv5Face',
+    'create_detector',
+    'detect_faces',
+    'list_available_detectors',
 ]

uniface/detection/base.py

@@ -2,75 +2,86 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""
-Base classes for face detection.
-"""
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import Any
 
 import numpy as np
-from abc import ABC, abstractmethod
-from typing import Tuple, Dict, Any
+
+from uniface.types import Face
+
+__all__ = ['BaseDetector']
 
 
 class BaseDetector(ABC):
-    """
-    Abstract base class for all face detectors.
+    """Abstract base class for all face detectors.
 
     This class defines the interface that all face detectors must implement,
     ensuring consistency across different detection methods.
+
+    Attributes:
+        config: Dictionary containing detector configuration parameters.
+        _supports_landmarks: Flag indicating if detector supports landmark detection.
     """
 
-    def __init__(self, **kwargs):
-        """Initialize the detector with configuration parameters."""
-        self.config = kwargs
-
-    @abstractmethod
-    def detect(self, image: np.ndarray, **kwargs) -> Tuple[np.ndarray, np.ndarray]:
-        """
-        Detect faces in an image.
+    def __init__(self, **kwargs: Any) -> None:
+        """Initialize the detector with configuration parameters.
 
         Args:
-            image (np.ndarray): Input image as numpy array with shape (H, W, C)
-            **kwargs: Additional detection parameters
+            **kwargs: Detector-specific configuration parameters.
+        """
+        self.config: dict[str, Any] = kwargs
+        self._supports_landmarks: bool = False
+
+    @abstractmethod
+    def detect(self, image: np.ndarray, **kwargs: Any) -> list[Face]:
+        """Detect faces in an image.
+
+        Args:
+            image: Input image as numpy array with shape (H, W, C) in BGR format.
+            **kwargs: Additional detection parameters.
 
         Returns:
-            Tuple[np.ndarray, np.ndarray]: (detections, landmarks)
-                - detections: Bounding boxes with confidence scores, shape (N, 5)
-                  Format: [x_min, y_min, x_max, y_max, confidence]
-                - landmarks: Facial landmark points, shape (N, 5, 2) for 5-point landmarks
-                  or (N, 68, 2) for 68-point landmarks. Empty array if not supported.
+            List of detected Face objects, each containing:
+                - bbox: Bounding box coordinates with shape (4,) as [x1, y1, x2, y2].
+                - confidence: Detection confidence score (0.0 to 1.0).
+                - landmarks: Facial landmarks with shape (5, 2) for 5-point landmarks.
+
+        Example:
+            >>> faces = detector.detect(image)
+            >>> for face in faces:
+            ...     bbox = face.bbox  # np.ndarray with shape (4,)
+            ...     confidence = face.confidence  # float
+            ...     landmarks = face.landmarks  # np.ndarray with shape (5, 2)
         """
-        pass
 
     @abstractmethod
     def preprocess(self, image: np.ndarray) -> np.ndarray:
-        """
-        Preprocess input image for detection.
+        """Preprocess input image for detection.
 
         Args:
-            image (np.ndarray): Input image
+            image: Input image with shape (H, W, C).
 
         Returns:
-            np.ndarray: Preprocessed image tensor
+            Preprocessed image tensor ready for inference.
         """
-        pass
 
     @abstractmethod
-    def postprocess(self, outputs, **kwargs) -> Tuple[np.ndarray, np.ndarray]:
-        """
-        Postprocess model outputs to get final detections.
+    def postprocess(self, outputs: Any, **kwargs: Any) -> Any:
+        """Postprocess model outputs to get final detections.
 
         Args:
-            outputs: Raw model outputs
-            **kwargs: Additional postprocessing parameters
+            outputs: Raw model outputs.
+            **kwargs: Additional postprocessing parameters.
 
         Returns:
-            Tuple[np.ndarray, np.ndarray]: (detections, landmarks)
+            Processed outputs (implementation-specific format, typically tuple of arrays).
         """
-        pass
 
     def __str__(self) -> str:
         """String representation of the detector."""
-        return f"{self.__class__.__name__}({self.config})"
+        return f'{self.__class__.__name__}({self.config})'
 
     def __repr__(self) -> str:
         """Detailed string representation."""
@@ -78,23 +89,33 @@ class BaseDetector(ABC):
 
     @property
     def supports_landmarks(self) -> bool:
-        """
-        Whether this detector supports landmark detection.
+        """Whether this detector supports landmark detection.
 
         Returns:
-            bool: True if landmarks are supported, False otherwise
+            True if landmarks are supported, False otherwise.
         """
         return hasattr(self, '_supports_landmarks') and self._supports_landmarks
 
-    def get_info(self) -> Dict[str, Any]:
-        """
-        Get detector information and configuration.
+    def get_info(self) -> dict[str, Any]:
+        """Get detector information and configuration.
 
         Returns:
-            Dict[str, Any]: Detector information
+            Dictionary containing detector name, landmark support, and config.
         """
         return {
             'name': self.__class__.__name__,
             'supports_landmarks': self._supports_landmarks,
-            'config': self.config
+            'config': self.config,
         }
+
+    def __call__(self, image: np.ndarray, **kwargs: Any) -> list[Face]:
+        """Callable shortcut for the `detect` method.
+
+        Args:
+            image: Input image as numpy array with shape (H, W, C) in BGR format.
+            **kwargs: Additional detection parameters.
+
+        Returns:
+            List of detected Face objects.
+        """
+        return self.detect(image, **kwargs)

uniface/detection/retinaface.py

@@ -2,23 +2,26 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from __future__ import annotations
+
+from typing import Any, Literal
+
 import numpy as np
 
-from typing import Tuple, List, Literal, Dict, Any
-
+from uniface.common import (
+    decode_boxes,
+    decode_landmarks,
+    generate_anchors,
+    non_max_suppression,
+    resize_image,
+)
+from uniface.constants import RetinaFaceWeights
 from uniface.log import Logger
 from uniface.model_store import verify_model_weights
-from uniface.constants import RetinaFaceWeights
 from uniface.onnx_utils import create_onnx_session
+from uniface.types import Face
 
 from .base import BaseDetector
-from .utils import (
-    non_max_supression,
-    resize_image,
-    decode_boxes,
-    generate_anchors,
-    decode_landmarks
-)
 
 
 class RetinaFace(BaseDetector):
@@ -27,21 +30,24 @@ class RetinaFace(BaseDetector):
 
     Title: "RetinaFace: Single-stage Dense Face Localisation in the Wild"
     Paper: https://arxiv.org/abs/1905.00641
+    Code: https://github.com/yakhyo/retinaface-pytorch
 
     Args:
-        **kwargs: Keyword arguments passed to BaseDetector and RetinaFace. Supported keys include:
-            model_name (RetinaFaceWeights, optional): Model weights to use. Defaults to `RetinaFaceWeights.MNET_V2`.
-            conf_thresh (float, optional): Confidence threshold for filtering detections. Defaults to 0.5.
-            nms_thresh (float, optional): Non-maximum suppression (NMS) IoU threshold. Defaults to 0.4.
-            pre_nms_topk (int, optional): Number of top-scoring boxes considered before NMS. Defaults to 5000.
-            post_nms_topk (int, optional): Max number of detections kept after NMS. Defaults to 750.
-            dynamic_size (bool, optional): If True, generate anchors dynamically per input image. Defaults to False.
-            input_size (Tuple[int, int], optional): Fixed input size (width, height) if `dynamic_size=False`. Defaults to (640, 640).
+        model_name (RetinaFaceWeights): Model weights to use. Defaults to `RetinaFaceWeights.MNET_V2`.
+        confidence_threshold (float): Confidence threshold for filtering detections. Defaults to 0.5.
+        nms_threshold (float): Non-maximum suppression (NMS) IoU threshold. Defaults to 0.4.
+        input_size (Tuple[int, int]): Fixed input size (width, height) if `dynamic_size=False`.
+            Defaults to (640, 640).
+            Note: Non-default sizes may cause slower inference and CoreML compatibility issues.
+        **kwargs: Advanced options:
+            pre_nms_topk (int): Number of top-scoring boxes considered before NMS. Defaults to 5000.
+            post_nms_topk (int): Max number of detections kept after NMS. Defaults to 750.
+            dynamic_size (bool): If True, generate anchors dynamically per input image. Defaults to False.
 
     Attributes:
         model_name (RetinaFaceWeights): Selected model variant.
-        conf_thresh (float): Threshold for confidence-based filtering.
-        nms_thresh (float): IoU threshold used for NMS.
+        confidence_threshold (float): Threshold for confidence-based filtering.
+        nms_threshold (float): IoU threshold used for NMS.
         pre_nms_topk (int): Limit on proposals before applying NMS.
         post_nms_topk (int): Limit on retained detections after NMS.
         dynamic_size (bool): Flag indicating dynamic or static input sizing.
@@ -55,50 +61,65 @@ class RetinaFace(BaseDetector):
         RuntimeError: If the ONNX model fails to load or initialize.
     """
 
-    def __init__(self, **kwargs) -> None:
-        super().__init__(**kwargs)
+    def __init__(
+        self,
+        *,
+        model_name: RetinaFaceWeights = RetinaFaceWeights.MNET_V2,
+        confidence_threshold: float = 0.5,
+        nms_threshold: float = 0.4,
+        input_size: tuple[int, int] = (640, 640),
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            model_name=model_name,
+            confidence_threshold=confidence_threshold,
+            nms_threshold=nms_threshold,
+            input_size=input_size,
+            **kwargs,
+        )
         self._supports_landmarks = True  # RetinaFace supports landmarks
 
-        self.model_name = kwargs.get('model_name', RetinaFaceWeights.MNET_V2)
-        self.conf_thresh = kwargs.get('conf_thresh', 0.5)
-        self.nms_thresh = kwargs.get('nms_thresh', 0.4)
+        self.model_name = model_name
+        self.confidence_threshold = confidence_threshold
+        self.nms_threshold = nms_threshold
+        self.input_size = input_size
+
+        # Advanced options from kwargs
         self.pre_nms_topk = kwargs.get('pre_nms_topk', 5000)
         self.post_nms_topk = kwargs.get('post_nms_topk', 750)
         self.dynamic_size = kwargs.get('dynamic_size', False)
-        self.input_size = kwargs.get('input_size', (640, 640))
 
         Logger.info(
-            f"Initializing RetinaFace with model={self.model_name}, conf_thresh={self.conf_thresh}, nms_thresh={self.nms_thresh}, "
-            f"input_size={self.input_size}"
+            f'Initializing RetinaFace with model={self.model_name}, confidence_threshold={self.confidence_threshold}, '
+            f'nms_threshold={self.nms_threshold}, input_size={self.input_size}'
         )
 
         # Get path to model weights
         self._model_path = verify_model_weights(self.model_name)
-        Logger.info(f"Verified model weights located at: {self._model_path}")
+        Logger.info(f'Verified model weights located at: {self._model_path}')
 
         # Precompute anchors if using static size
         if not self.dynamic_size and self.input_size is not None:
             self._priors = generate_anchors(image_size=self.input_size)
-            Logger.debug("Generated anchors for static input size.")
+            Logger.debug('Generated anchors for static input size.')
 
         # Initialize model
         self._initialize_model(self._model_path)
 
     def _initialize_model(self, model_path: str) -> None:
-        """
-        Initializes an ONNX model session from the given path.
+        """Initialize an ONNX model session from the given path.
 
         Args:
-            model_path (str): The file path to the ONNX model.
+            model_path: The file path to the ONNX model.
 
         Raises:
-            RuntimeError: If the model fails to load, logs an error and raises an exception.
+            RuntimeError: If the model fails to load.
         """
         try:
             self.session = create_onnx_session(model_path)
             self.input_names = self.session.get_inputs()[0].name
             self.output_names = [x.name for x in self.session.get_outputs()]
-            Logger.info(f"Successfully initialized the model from {model_path}")
+            Logger.info(f'Successfully initialized the model from {model_path}')
         except Exception as e:
             Logger.error(f"Failed to load model from '{model_path}': {e}", exc_info=True)
             raise RuntimeError(f"Failed to initialize model session for '{model_path}'") from e
@@ -117,24 +138,25 @@ class RetinaFace(BaseDetector):
         image = np.expand_dims(image, axis=0)  # Add batch dimension (1, C, H, W)
         return image
 
-    def inference(self, input_tensor: np.ndarray) -> List[np.ndarray]:
+    def inference(self, input_tensor: np.ndarray) -> list[np.ndarray]:
         """Perform model inference on the preprocessed image tensor.
 
         Args:
-            input_tensor (np.ndarray): Preprocessed input tensor.
+            input_tensor: Preprocessed input tensor with shape (1, C, H, W).
 
         Returns:
-            Tuple[np.ndarray, np.ndarray]: Raw model outputs.
+            List of raw model outputs (location, confidence, landmarks).
         """
         return self.session.run(self.output_names, {self.input_names: input_tensor})
 
     def detect(
         self,
         image: np.ndarray,
+        *,
         max_num: int = 0,
-        metric: Literal["default", "max"] = "max",
-        center_weight: float = 2.0
-    ) -> List[Dict[str, Any]]:
+        metric: Literal['default', 'max'] = 'max',
+        center_weight: float = 2.0,
+    ) -> list[Face]:
         """
         Perform face detection on an input image and return bounding boxes and facial landmarks.
 
@@ -148,10 +170,19 @@ class RetinaFace(BaseDetector):
                 when using the "default" metric. Defaults to 2.0.
 
         Returns:
-            List[Dict[str, Any]]: List of face detection dictionaries, each containing:
-                - 'bbox': [x1, y1, x2, y2] - Bounding box coordinates
-                - 'confidence': float - Detection confidence score
-                - 'landmarks': [[x1, y1], [x2, y2], [x3, y3], [x4, y4], [x5, y5]] - 5-point facial landmarks
+            List[Face]: List of Face objects, each containing:
+                - bbox (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - confidence (float): Detection confidence score (0.0 to 1.0)
+                - landmarks (np.ndarray): 5-point facial landmarks with shape (5, 2)
+
+        Example:
+            >>> faces = detector.detect(image)
+            >>> for face in faces:
+            ...     bbox = face.bbox  # np.ndarray with shape (4,)
+            ...     confidence = face.confidence  # float
+            ...     landmarks = face.landmarks  # np.ndarray with shape (5, 2)
+            ...     # Can pass landmarks directly to recognition
+            ...     embedding = recognizer.get_normalized_embedding(image, face.landmarks)
         """
 
         original_height, original_width = image.shape[:2]
@@ -178,10 +209,12 @@ class RetinaFace(BaseDetector):
 
             # Calculate offsets from image center
             center = (original_height // 2, original_width // 2)
-            offsets = np.vstack([
-                (detections[:, 0] + detections[:, 2]) / 2 - center[1],
-                (detections[:, 1] + detections[:, 3]) / 2 - center[0]
-            ])
+            offsets = np.vstack(
+                [
+                    (detections[:, 0] + detections[:, 2]) / 2 - center[1],
+                    (detections[:, 1] + detections[:, 3]) / 2 - center[0],
+                ]
+            )
             offset_dist_squared = np.sum(np.power(offsets, 2.0), axis=0)
 
             # Calculate scores based on the chosen metric
@@ -198,67 +231,84 @@ class RetinaFace(BaseDetector):
 
         faces = []
         for i in range(detections.shape[0]):
-            face_dict = {
-                'bbox': detections[i, :4].astype(float).tolist(),
-                'confidence': detections[i, 4].item(),
-                'landmarks': landmarks[i].astype(float).tolist()
-            }
-            faces.append(face_dict)
+            face = Face(
+                bbox=detections[i, :4],
+                confidence=float(detections[i, 4]),
+                landmarks=landmarks[i],
+            )
+            faces.append(face)
 
         return faces
 
-    def postprocess(self, outputs: List[np.ndarray], resize_factor: float, shape: Tuple[int, int]) -> Tuple[np.ndarray, np.ndarray]:
-        """
-        Process the model outputs into final detection results.
+    def postprocess(
+        self,
+        outputs: list[np.ndarray],
+        resize_factor: float,
+        shape: tuple[int, int],
+    ) -> tuple[np.ndarray, np.ndarray]:
+        """Process the model outputs into final detection results.
 
         Args:
-            outputs (List[np.ndarray]): Raw outputs from the detection model.
+            outputs: Raw outputs from the detection model containing:
                 - outputs[0]: Location predictions (bounding box coordinates).
                 - outputs[1]: Class confidence scores.
                 - outputs[2]: Landmark predictions.
-            resize_factor (float): Factor used to resize the input image during preprocessing.
-            shape (Tuple[int, int]): Original shape of the image as (height, width).
+            resize_factor: Factor used to resize the input image during preprocessing.
+            shape: Original shape of the image as (width, height).
 
         Returns:
-            Tuple[np.ndarray, np.ndarray]: Processed results containing:
-                - detections (np.ndarray): Array of detected bounding boxes with confidence scores.
-                Shape: (num_detections, 5), where each row is [x_min, y_min, x_max, y_max, score].
-                - landmarks (np.ndarray): Array of detected facial landmarks.
-                Shape: (num_detections, 5, 2), where each row contains 5 landmark points (x, y).
+            A tuple containing:
+                - detections: Array of detected bounding boxes with confidence scores,
+                  shape (num_detections, 5), each row is [x1, y1, x2, y2, score].
+                - landmarks: Array of detected facial landmarks,
+                  shape (num_detections, 5, 2), each row contains 5 landmark points (x, y).
         """
-        loc, conf, landmarks = outputs[0].squeeze(0), outputs[1].squeeze(0), outputs[2].squeeze(0)
+        location_predictions, confidence_scores, landmark_predictions = (
+            outputs[0].squeeze(0),
+            outputs[1].squeeze(0),
+            outputs[2].squeeze(0),
+        )
 
         # Decode boxes and landmarks
-        boxes = decode_boxes(loc, self._priors)
-        landmarks = decode_landmarks(landmarks, self._priors)
+        boxes = decode_boxes(location_predictions, self._priors)
+        landmarks = decode_landmarks(landmark_predictions, self._priors)
 
         boxes, landmarks = self._scale_detections(boxes, landmarks, resize_factor, shape=(shape[0], shape[1]))
 
         # Extract confidence scores for the face class
-        scores = conf[:, 1]
-        mask = scores > self.conf_thresh
+        scores = confidence_scores[:, 1]
+        mask = scores > self.confidence_threshold
 
         # Filter by confidence threshold
         boxes, landmarks, scores = boxes[mask], landmarks[mask], scores[mask]
 
         # Sort by scores
-        order = scores.argsort()[::-1][:self.pre_nms_topk]
+        order = scores.argsort()[::-1][: self.pre_nms_topk]
         boxes, landmarks, scores = boxes[order], landmarks[order], scores[order]
 
         # Apply NMS
         detections = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False)
-        keep = non_max_supression(detections, self.nms_thresh)
+        keep = non_max_suppression(detections, self.nms_threshold)
         detections, landmarks = detections[keep], landmarks[keep]
 
         # Keep top-k detections
-        detections, landmarks = detections[:self.post_nms_topk], landmarks[:self.post_nms_topk]
+        detections, landmarks = (
+            detections[: self.post_nms_topk],
+            landmarks[: self.post_nms_topk],
+        )
 
-        landmarks = landmarks.reshape(-1, 5, 2).astype(np.int32)
+        landmarks = landmarks.reshape(-1, 5, 2).astype(np.float32)
 
         return detections, landmarks
 
-    def _scale_detections(self, boxes: np.ndarray, landmarks: np.ndarray, resize_factor: float, shape: Tuple[int, int]) -> Tuple[np.ndarray, np.ndarray]:
-        # Scale bounding boxes and landmarks to the original image size.
+    def _scale_detections(
+        self,
+        boxes: np.ndarray,
+        landmarks: np.ndarray,
+        resize_factor: float,
+        shape: tuple[int, int],
+    ) -> tuple[np.ndarray, np.ndarray]:
+        """Scale bounding boxes and landmarks to the original image size."""
         bbox_scale = np.array([shape[0], shape[1]] * 2)
         boxes = boxes * bbox_scale / resize_factor
 
@@ -266,64 +316,3 @@ class RetinaFace(BaseDetector):
         landmarks = landmarks * landmark_scale / resize_factor
 
         return boxes, landmarks
-
-
-# TODO: below is only for testing, remove it later
-def draw_bbox(frame, bbox, score, color=(0, 255, 0), thickness=2):
-    x1, y1, x2, y2 = map(int, bbox)  # Unpack 4 bbox values
-    cv2.rectangle(frame, (x1, y1), (x2, y2), color, thickness)
-    cv2.putText(frame, f"{score:.2f}", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 1)
-
-
-def draw_keypoints(frame, points, color=(0, 0, 255), radius=2):
-    for (x, y) in points.astype(np.int32):
-        cv2.circle(frame, (int(x), int(y)), radius, color, -1)
-
-
-if __name__ == "__main__":
-    import cv2
-    detector = RetinaFace(model_name=RetinaFaceWeights.MNET_050)
-    print(detector.get_info())
-    cap = cv2.VideoCapture(0)
-
-    if not cap.isOpened():
-        print("Failed to open webcam.")
-        exit()
-
-    print("Webcam started. Press 'q' to exit.")
-
-    while True:
-        ret, frame = cap.read()
-        if not ret:
-            print("Failed to read frame.")
-            break
-
-        # Get face detections as list of dictionaries
-        faces = detector.detect(frame)
-
-        # Process each detected face
-        for face in faces:
-            # Extract bbox and landmarks from dictionary
-            bbox = face['bbox']  # [x1, y1, x2, y2]
-            landmarks = face['landmarks']  # [[x1, y1], [x2, y2], ...]
-            confidence = face['confidence']
-
-            # Pass bbox and confidence separately
-            draw_bbox(frame, bbox, confidence)
-
-            # Convert landmarks to numpy array format if needed
-            if landmarks is not None and len(landmarks) > 0:
-                # Convert list of [x, y] pairs to numpy array
-                points = np.array(landmarks, dtype=np.float32)  # Shape: (5, 2)
-                draw_keypoints(frame, points)
-
-        # Display face count
-        cv2.putText(frame, f"Faces: {len(faces)}", (10, 30),
-                    cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2)
-
-        cv2.imshow("FaceDetection", frame)
-        if cv2.waitKey(1) & 0xFF == ord("q"):
-            break
-
-    cap.release()
-    cv2.destroyAllWindows()

uniface/detection/scrfd.py

@@ -2,20 +2,22 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from typing import Any, Dict, List, Literal, Tuple
+from __future__ import annotations
+
+from typing import Any, Literal
 
-import cv2
 import numpy as np
 
+from uniface.common import distance2bbox, distance2kps, non_max_suppression, resize_image
 from uniface.constants import SCRFDWeights
 from uniface.log import Logger
 from uniface.model_store import verify_model_weights
 from uniface.onnx_utils import create_onnx_session
+from uniface.types import Face
 
 from .base import BaseDetector
-from .utils import distance2bbox, distance2kps, non_max_supression, resize_image
 
-__all__ = ["SCRFD"]
+__all__ = ['SCRFD']
 
 
 class SCRFD(BaseDetector):
@@ -24,20 +26,24 @@ class SCRFD(BaseDetector):
 
     Title: "Sample and Computation Redistribution for Efficient Face Detection"
     Paper: https://arxiv.org/abs/2105.04714
+    Code: https://github.com/insightface/insightface
 
     Args:
-        **kwargs: Keyword arguments passed to BaseDetector and SCRFD. Supported keys include:
-            model_name (SCRFDWeights, optional): Predefined model enum (e.g., `SCRFD_10G_KPS`).
-                Specifies the SCRFD variant to load. Defaults to SCRFD_10G_KPS.
-            conf_thresh (float, optional): Confidence threshold for filtering detections. Defaults to 0.5.
-            nms_thresh (float, optional): Non-Maximum Suppression threshold. Defaults to 0.4.
-            input_size (Tuple[int, int], optional): Input image size (width, height). Defaults to (640, 640).
+        model_name (SCRFDWeights): Predefined model enum (e.g., `SCRFD_10G_KPS`).
+            Specifies the SCRFD variant to load. Defaults to SCRFD_10G_KPS.
+        confidence_threshold (float): Confidence threshold for filtering detections. Defaults to 0.5.
+        nms_threshold (float): Non-Maximum Suppression threshold. Defaults to 0.4.
+        input_size (Tuple[int, int]): Input image size (width, height).
+            Defaults to (640, 640).
+            Note: Non-default sizes may cause slower inference and CoreML compatibility issues.
+        **kwargs: Reserved for future advanced options.
 
     Attributes:
-        conf_thresh (float): Threshold used to filter low-confidence detections.
-        nms_thresh (float): Threshold used during NMS to suppress overlapping boxes.
+        model_name (SCRFDWeights): Selected model variant.
+        confidence_threshold (float): Threshold used to filter low-confidence detections.
+        nms_threshold (float): Threshold used during NMS to suppress overlapping boxes.
         input_size (Tuple[int, int]): Image size to which inputs are resized before inference.
-        _fmc (int): Number of feature map levels used in the model.
+        _num_feature_maps (int): Number of feature map levels used in the model.
         _feat_stride_fpn (List[int]): Feature map strides corresponding to each detection level.
         _num_anchors (int): Number of anchors per feature location.
         _center_cache (Dict): Cached anchor centers for efficient forward passes.
@@ -48,65 +54,74 @@ class SCRFD(BaseDetector):
         RuntimeError: If the ONNX model fails to load or initialize.
     """
 
-    def __init__(self, **kwargs) -> None:
-        super().__init__(**kwargs)
+    def __init__(
+        self,
+        *,
+        model_name: SCRFDWeights = SCRFDWeights.SCRFD_10G_KPS,
+        confidence_threshold: float = 0.5,
+        nms_threshold: float = 0.4,
+        input_size: tuple[int, int] = (640, 640),
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            model_name=model_name,
+            confidence_threshold=confidence_threshold,
+            nms_threshold=nms_threshold,
+            input_size=input_size,
+            **kwargs,
+        )
         self._supports_landmarks = True  # SCRFD supports landmarks
 
-        model_name = kwargs.get("model_name", SCRFDWeights.SCRFD_10G_KPS)
-        conf_thresh = kwargs.get("conf_thresh", 0.5)
-        nms_thresh = kwargs.get("nms_thresh", 0.4)
-        input_size = kwargs.get("input_size", (640, 640))
-
-        self.conf_thresh = conf_thresh
-        self.nms_thresh = nms_thresh
+        self.model_name = model_name
+        self.confidence_threshold = confidence_threshold
+        self.nms_threshold = nms_threshold
         self.input_size = input_size
 
         # ------- SCRFD model params ------
-        self._fmc = 3
+        self._num_feature_maps = 3
         self._feat_stride_fpn = [8, 16, 32]
         self._num_anchors = 2
         self._center_cache = {}
         # ---------------------------------
 
         Logger.info(
-            f"Initializing SCRFD with model={model_name}, conf_thresh={conf_thresh}, nms_thresh={nms_thresh}, "
-            f"input_size={input_size}"
+            f'Initializing SCRFD with model={self.model_name}, confidence_threshold={self.confidence_threshold}, '
+            f'nms_threshold={self.nms_threshold}, input_size={self.input_size}'
         )
 
         # Get path to model weights
-        self._model_path = verify_model_weights(model_name)
-        Logger.info(f"Verified model weights located at: {self._model_path}")
+        self._model_path = verify_model_weights(self.model_name)
+        Logger.info(f'Verified model weights located at: {self._model_path}')
 
         # Initialize model
         self._initialize_model(self._model_path)
 
     def _initialize_model(self, model_path: str) -> None:
-        """
-        Initializes an ONNX model session from the given path.
+        """Initialize an ONNX model session from the given path.
 
         Args:
-            model_path (str): The file path to the ONNX model.
+            model_path: The file path to the ONNX model.
 
         Raises:
-            RuntimeError: If the model fails to load, logs an error and raises an exception.
+            RuntimeError: If the model fails to load.
         """
         try:
             self.session = create_onnx_session(model_path)
             self.input_names = self.session.get_inputs()[0].name
             self.output_names = [x.name for x in self.session.get_outputs()]
-            Logger.info(f"Successfully initialized the model from {model_path}")
+            Logger.info(f'Successfully initialized the model from {model_path}')
         except Exception as e:
             Logger.error(f"Failed to load model from '{model_path}': {e}", exc_info=True)
             raise RuntimeError(f"Failed to initialize model session for '{model_path}'") from e
 
-    def preprocess(self, image: np.ndarray) -> Tuple[np.ndarray, Tuple[int, int]]:
+    def preprocess(self, image: np.ndarray) -> np.ndarray:
         """Preprocess image for inference.
 
         Args:
-            image (np.ndarray): Input image
+            image: Input image with shape (H, W, C).
 
         Returns:
-            Tuple[np.ndarray, Tuple[int, int]]: Preprocessed blob and input size
+            Preprocessed image tensor with shape (1, C, H, W).
         """
         image = image.astype(np.float32)
         image = (image - 127.5) / 127.5
@@ -115,29 +130,42 @@ class SCRFD(BaseDetector):
 
         return image
 
-    def inference(self, input_tensor: np.ndarray) -> List[np.ndarray]:
+    def inference(self, input_tensor: np.ndarray) -> list[np.ndarray]:
         """Perform model inference on the preprocessed image tensor.
 
         Args:
-            input_tensor (np.ndarray): Preprocessed input tensor.
+            input_tensor: Preprocessed input tensor with shape (1, C, H, W).
 
         Returns:
-            Tuple[np.ndarray, np.ndarray]: Raw model outputs.
+            List of raw model outputs.
         """
         return self.session.run(self.output_names, {self.input_names: input_tensor})
 
-    def postprocess(self, outputs: List[np.ndarray], image_size: Tuple[int, int]):
-        scores_list = []
+    def postprocess(
+        self,
+        outputs: list[np.ndarray],
+        image_size: tuple[int, int],
+    ) -> tuple[list[np.ndarray], list[np.ndarray], list[np.ndarray]]:
+        """Process model outputs into detection results.
+
+        Args:
+            outputs: Raw outputs from the detection model.
+            image_size: Size of the input image as (height, width).
+
+        Returns:
+            Tuple of (scores_list, bboxes_list, landmarks_list).
+        """
+        scores_list: list[np.ndarray] = []
         bboxes_list = []
         kpss_list = []
 
         image_size = image_size
 
-        fmc = self._fmc
+        num_feature_maps = self._num_feature_maps
         for idx, stride in enumerate(self._feat_stride_fpn):
             scores = outputs[idx]
-            bbox_preds = outputs[fmc + idx] * stride
-            kps_preds = outputs[2 * fmc + idx] * stride
+            bbox_preds = outputs[num_feature_maps + idx] * stride
+            kps_preds = outputs[2 * num_feature_maps + idx] * stride
 
             # Generate anchors
             fm_height = image_size[0] // stride
@@ -157,7 +185,7 @@ class SCRFD(BaseDetector):
                 if len(self._center_cache) < 100:
                     self._center_cache[cache_key] = anchor_centers
 
-            pos_indices = np.where(scores >= self.conf_thresh)[0]
+            pos_indices = np.where(scores >= self.confidence_threshold)[0]
             if len(pos_indices) == 0:
                 continue
 
@@ -173,8 +201,13 @@ class SCRFD(BaseDetector):
         return scores_list, bboxes_list, kpss_list
 
     def detect(
-        self, image: np.ndarray, max_num: int = 0, metric: Literal["default", "max"] = "max", center_weight: float = 2
-    ) -> List[Dict[str, Any]]:
+        self,
+        image: np.ndarray,
+        *,
+        max_num: int = 0,
+        metric: Literal['default', 'max'] = 'max',
+        center_weight: float = 2.0,
+    ) -> list[Face]:
         """
         Perform face detection on an input image and return bounding boxes and facial landmarks.
 
@@ -188,10 +221,19 @@ class SCRFD(BaseDetector):
                 when using the "default" metric. Defaults to 2.0.
 
         Returns:
-            List[Dict[str, Any]]: List of face detection dictionaries, each containing:
-                - 'bbox': [x1, y1, x2, y2] - Bounding box coordinates
-                - 'confidence': float - Detection confidence score
-                - 'landmarks': [[x1, y1], [x2, y2], [x3, y3], [x4, y4], [x5, y5]] - 5-point facial landmarks
+            List[Face]: List of Face objects, each containing:
+                - bbox (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - confidence (float): Detection confidence score (0.0 to 1.0)
+                - landmarks (np.ndarray): 5-point facial landmarks with shape (5, 2)
+
+        Example:
+            >>> faces = detector.detect(image)
+            >>> for face in faces:
+            ...     bbox = face.bbox  # np.ndarray with shape (4,)
+            ...     confidence = face.confidence  # float
+            ...     landmarks = face.landmarks  # np.ndarray with shape (5, 2)
+            ...     # Can pass landmarks directly to recognition
+            ...     embedding = recognizer.get_normalized_embedding(image, face.landmarks)
         """
 
         original_height, original_width = image.shape[:2]
@@ -219,11 +261,11 @@ class SCRFD(BaseDetector):
         pre_det = np.hstack((bboxes, scores)).astype(np.float32, copy=False)
         pre_det = pre_det[order, :]
 
-        keep = non_max_supression(pre_det, threshold=self.nms_thresh)
+        keep = non_max_suppression(pre_det, threshold=self.nms_threshold)
 
         detections = pre_det[keep, :]
         landmarks = landmarks[order, :, :]
-        landmarks = landmarks[keep, :, :].astype(np.int32)
+        landmarks = landmarks[keep, :, :].astype(np.float32)
 
         if 0 < max_num < detections.shape[0]:
             # Calculate area of detections
@@ -240,7 +282,7 @@ class SCRFD(BaseDetector):
 
             # Calculate scores based on the chosen metric
             offset_dist_squared = np.sum(np.power(offsets, 2.0), axis=0)
-            if metric == "max":
+            if metric == 'max':
                 values = area
             else:
                 values = area - offset_dist_squared * center_weight
@@ -252,70 +294,11 @@ class SCRFD(BaseDetector):
 
         faces = []
         for i in range(detections.shape[0]):
-            face_dict = {
-                "bbox": detections[i, :4].astype(float).tolist(),
-                "confidence": detections[i, 4].item(),
-                "landmarks": landmarks[i].astype(float).tolist(),
-            }
-            faces.append(face_dict)
+            face = Face(
+                bbox=detections[i, :4],
+                confidence=float(detections[i, 4]),
+                landmarks=landmarks[i],
+            )
+            faces.append(face)
 
         return faces
-
-
-# TODO: below is only for testing, remove it later
-def draw_bbox(frame, bbox, score, color=(0, 255, 0), thickness=2):
-    x1, y1, x2, y2 = map(int, bbox)  # Unpack 4 bbox values
-    cv2.rectangle(frame, (x1, y1), (x2, y2), color, thickness)
-    cv2.putText(frame, f"{score:.2f}", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 1)
-
-
-def draw_keypoints(frame, points, color=(0, 0, 255), radius=2):
-    for x, y in points.astype(np.int32):
-        cv2.circle(frame, (int(x), int(y)), radius, color, -1)
-
-
-if __name__ == "__main__":
-    detector = SCRFD(model_name=SCRFDWeights.SCRFD_500M_KPS)
-    print(detector.get_info())
-    cap = cv2.VideoCapture(0)
-
-    if not cap.isOpened():
-        print("Failed to open webcam.")
-        exit()
-
-    print("Webcam started. Press 'q' to exit.")
-
-    while True:
-        ret, frame = cap.read()
-        if not ret:
-            print("Failed to read frame.")
-            break
-
-        # Get face detections as list of dictionaries
-        faces = detector.detect(frame)
-
-        # Process each detected face
-        for face in faces:
-            # Extract bbox and landmarks from dictionary
-            bbox = face["bbox"]  # [x1, y1, x2, y2]
-            landmarks = face["landmarks"]  # [[x1, y1], [x2, y2], ...]
-            confidence = face["confidence"]
-
-            # Pass bbox and confidence separately
-            draw_bbox(frame, bbox, confidence)
-
-            # Convert landmarks to numpy array format if needed
-            if landmarks is not None and len(landmarks) > 0:
-                # Convert list of [x, y] pairs to numpy array
-                points = np.array(landmarks, dtype=np.float32)  # Shape: (5, 2)
-                draw_keypoints(frame, points)
-
-        # Display face count
-        cv2.putText(frame, f"Faces: {len(faces)}", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2)
-
-        cv2.imshow("FaceDetection", frame)
-        if cv2.waitKey(1) & 0xFF == ord("q"):
-            break
-
-    cap.release()
-    cv2.destroyAllWindows()

uniface/detection/utils.py

@@ -1,232 +0,0 @@
-# Copyright 2025 Yakhyokhuja Valikhujaev
-# Author: Yakhyokhuja Valikhujaev
-# GitHub: https://github.com/yakhyo
-
-import cv2
-import math
-import itertools
-import numpy as np
-
-from typing import Tuple, List
-
-
-def resize_image(frame, target_shape: Tuple[int, int] = (640, 640)) -> Tuple[np.ndarray, float]:
-    """
-    Resize an image to fit within a target shape while keeping its aspect ratio.
-
-    Args:
-        frame (np.ndarray): Input image.
-        target_shape (Tuple[int, int]): Target size (width, height). Defaults to (640, 640).
-
-    Returns:
-        Tuple[np.ndarray, float]: Resized image on a blank canvas and the resize factor.
-    """
-    width, height = target_shape
-
-    # Aspect-ratio preserving resize
-    im_ratio = float(frame.shape[0]) / frame.shape[1]
-    model_ratio = height / width
-    if im_ratio > model_ratio:
-        new_height = height
-        new_width = int(new_height / im_ratio)
-    else:
-        new_width = width
-        new_height = int(new_width * im_ratio)
-
-    resize_factor = float(new_height) / frame.shape[0]
-    resized_frame = cv2.resize(frame, (new_width, new_height))
-
-    # Create blank image and place resized image on it
-    image = np.zeros((height, width, 3), dtype=np.uint8)
-    image[:new_height, :new_width, :] = resized_frame
-
-    return image, resize_factor
-
-
-def generate_anchors(image_size: Tuple[int, int] = (640, 640)) -> np.ndarray:
-    """
-    Generate anchor boxes for a given image size.
-
-    Args:
-        image_size (Tuple[int, int]): Input image size (width, height). Defaults to (640, 640).
-
-    Returns:
-        np.ndarray: Anchor box coordinates as a NumPy array.
-    """
-    image_size = image_size
-
-    steps = [8, 16, 32]
-    min_sizes = [[16, 32], [64, 128], [256, 512]]
-
-    anchors = []
-    feature_maps = [
-        [
-            math.ceil(image_size[0] / step),
-            math.ceil(image_size[1] / step)
-        ] for step in steps
-    ]
-
-    for k, (map_height, map_width) in enumerate(feature_maps):
-        step = steps[k]
-        for i, j in itertools.product(range(map_height), range(map_width)):
-            for min_size in min_sizes[k]:
-                s_kx = min_size / image_size[1]
-                s_ky = min_size / image_size[0]
-
-                dense_cx = [x * step / image_size[1] for x in [j + 0.5]]
-                dense_cy = [y * step / image_size[0] for y in [i + 0.5]]
-                for cy, cx in itertools.product(dense_cy, dense_cx):
-                    anchors += [cx, cy, s_kx, s_ky]
-
-    output = np.array(anchors, dtype=np.float32).reshape(-1, 4)
-    return output
-
-
-def non_max_supression(dets: List[np.ndarray], threshold: float):
-    """
-    Apply Non-Maximum Suppression (NMS) to reduce overlapping bounding boxes based on a threshold.
-
-    Args:
-        dets (numpy.ndarray): Array of detections with each row as [x1, y1, x2, y2, score].
-        threshold (float): IoU threshold for suppression.
-
-    Returns:
-        list: Indices of bounding boxes retained after suppression.
-    """
-    x1 = dets[:, 0]
-    y1 = dets[:, 1]
-    x2 = dets[:, 2]
-    y2 = dets[:, 3]
-    scores = dets[:, 4]
-
-    areas = (x2 - x1 + 1) * (y2 - y1 + 1)
-    order = scores.argsort()[::-1]
-
-    keep = []
-    while order.size > 0:
-        i = order[0]
-        keep.append(i)
-        xx1 = np.maximum(x1[i], x1[order[1:]])
-        yy1 = np.maximum(y1[i], y1[order[1:]])
-        xx2 = np.minimum(x2[i], x2[order[1:]])
-        yy2 = np.minimum(y2[i], y2[order[1:]])
-
-        w = np.maximum(0.0, xx2 - xx1 + 1)
-        h = np.maximum(0.0, yy2 - yy1 + 1)
-        inter = w * h
-        ovr = inter / (areas[i] + areas[order[1:]] - inter)
-
-        inds = np.where(ovr <= threshold)[0]
-        order = order[inds + 1]
-
-    return keep
-
-
-def decode_boxes(loc, priors, variances=[0.1, 0.2]) -> np.ndarray:
-    """
-    Decode locations from predictions using priors to undo
-    the encoding done for offset regression at train time.
-
-    Args:
-        loc (np.ndarray): Location predictions for loc layers, shape: [num_priors, 4]
-        priors (np.ndarray): Prior boxes in center-offset form, shape: [num_priors, 4]
-        variances (list[float]): Variances of prior boxes
-
-    Returns:
-        np.ndarray: Decoded bounding box predictions
-    """
-    # Compute centers of predicted boxes
-    cxcy = priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:]
-
-    # Compute widths and heights of predicted boxes
-    wh = priors[:, 2:] * np.exp(loc[:, 2:] * variances[1])
-
-    # Convert center, size to corner coordinates
-    boxes = np.zeros_like(loc)
-    boxes[:, :2] = cxcy - wh / 2  # xmin, ymin
-    boxes[:, 2:] = cxcy + wh / 2  # xmax, ymax
-
-    return boxes
-
-
-def decode_landmarks(predictions, priors, variances=[0.1, 0.2]) -> np.ndarray:
-    """
-    Decode landmark predictions using prior boxes.
-
-    Args:
-        predictions (np.ndarray): Landmark predictions, shape: [num_priors, 10]
-        priors (np.ndarray): Prior boxes, shape: [num_priors, 4]
-        variances (list): Scaling factors for landmark offsets.
-
-    Returns:
-        np.ndarray: Decoded landmarks, shape: [num_priors, 10]
-    """
-
-    # Reshape predictions to [num_priors, 5, 2] to process landmark points
-    predictions = predictions.reshape(predictions.shape[0], 5, 2)
-
-    # Expand priors to match (num_priors, 5, 2)
-    priors_xy = np.repeat(priors[:, :2][:, np.newaxis, :], 5, axis=1)  # (num_priors, 5, 2)
-    priors_wh = np.repeat(priors[:, 2:][:, np.newaxis, :], 5, axis=1)  # (num_priors, 5, 2)
-
-    # Compute absolute landmark positions
-    landmarks = priors_xy + predictions * variances[0] * priors_wh
-
-    # Flatten back to [num_priors, 10]
-    landmarks = landmarks.reshape(landmarks.shape[0], -1)
-
-    return landmarks
-
-
-def distance2bbox(points, distance, max_shape=None):
-    """Decode distance prediction to bounding box.
-
-    Args:
-        points (Tensor): Shape (n, 2), [x, y].
-        distance (Tensor): Distance from the given point to 4
-            boundaries (left, top, right, bottom).
-        max_shape (tuple): Shape of the image.
-
-    Returns:
-        Tensor: Decoded bounding boxes with shape (n, 4).
-    """
-    x1 = points[:, 0] - distance[:, 0]
-    y1 = points[:, 1] - distance[:, 1]
-    x2 = points[:, 0] + distance[:, 2]
-    y2 = points[:, 1] + distance[:, 3]
-    if max_shape is not None:
-        x1 = x1.clamp(min=0, max=max_shape[1])
-        y1 = y1.clamp(min=0, max=max_shape[0])
-        x2 = x2.clamp(min=0, max=max_shape[1])
-        y2 = y2.clamp(min=0, max=max_shape[0])
-    else:
-        x1 = np.maximum(x1, 0)
-        y1 = np.maximum(y1, 0)
-        x2 = np.maximum(x2, 0)
-        y2 = np.maximum(y2, 0)
-
-    return np.stack([x1, y1, x2, y2], axis=-1)
-
-
-def distance2kps(points, distance, max_shape=None):
-    """Decode distance prediction to keypoints.
-
-    Args:
-        points (Tensor): Shape (n, 2), [x, y].
-        distance (Tensor): Distance from the given point to 4
-            boundaries (left, top, right, bottom).
-        max_shape (tuple): Shape of the image.
-
-    Returns:
-        Tensor: Decoded keypoints with shape (n, 2k).
-    """
-    preds = []
-    for i in range(0, distance.shape[1], 2):
-        px = points[:, i % 2] + distance[:, i]
-        py = points[:, i % 2 + 1] + distance[:, i + 1]
-        if max_shape is not None:
-            px = px.clamp(min=0, max=max_shape[1])
-            py = py.clamp(min=0, max=max_shape[0])
-        preds.append(px)
-        preds.append(py)
-    return np.stack(preds, axis=-1)

uniface/detection/yolov5.py

@@ -0,0 +1,341 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from typing import Any, Literal
+
+import cv2
+import numpy as np
+
+from uniface.common import non_max_suppression
+from uniface.constants import YOLOv5FaceWeights
+from uniface.log import Logger
+from uniface.model_store import verify_model_weights
+from uniface.onnx_utils import create_onnx_session
+from uniface.types import Face
+
+from .base import BaseDetector
+
+__all__ = ['YOLOv5Face']
+
+
+class YOLOv5Face(BaseDetector):
+    """
+    Face detector based on the YOLOv5-Face architecture.
+
+    Title: "YOLO5Face: Why Reinventing a Face Detector"
+    Paper: https://arxiv.org/abs/2105.12931
+    Code: https://github.com/yakhyo/yolov5-face-onnx-inference (ONNX inference implementation)
+
+    Args:
+        model_name (YOLOv5FaceWeights): Predefined model enum (e.g., `YOLOV5S`).
+            Specifies the YOLOv5-Face variant to load. Defaults to YOLOV5S.
+        confidence_threshold (float): Confidence threshold for filtering detections. Defaults to 0.6.
+        nms_threshold (float): Non-Maximum Suppression threshold. Defaults to 0.5.
+        input_size (int): Input image size. Defaults to 640.
+            Note: ONNX model is fixed at 640. Changing this will cause inference errors.
+        **kwargs: Advanced options:
+            max_det (int): Maximum number of detections to return. Defaults to 750.
+
+    Attributes:
+        model_name (YOLOv5FaceWeights): Selected model variant.
+        confidence_threshold (float): Threshold used to filter low-confidence detections.
+        nms_threshold (float): Threshold used during NMS to suppress overlapping boxes.
+        input_size (int): Image size to which inputs are resized before inference.
+        max_det (int): Maximum number of detections to return.
+        _model_path (str): Absolute path to the downloaded/verified model weights.
+
+    Raises:
+        ValueError: If the model weights are invalid or not found.
+        RuntimeError: If the ONNX model fails to load or initialize.
+    """
+
+    def __init__(
+        self,
+        *,
+        model_name: YOLOv5FaceWeights = YOLOv5FaceWeights.YOLOV5S,
+        confidence_threshold: float = 0.6,
+        nms_threshold: float = 0.5,
+        input_size: int = 640,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            model_name=model_name,
+            confidence_threshold=confidence_threshold,
+            nms_threshold=nms_threshold,
+            input_size=input_size,
+            **kwargs,
+        )
+        self._supports_landmarks = True  # YOLOv5-Face supports landmarks
+
+        # Validate input size
+        if input_size != 640:
+            raise ValueError(
+                f'YOLOv5Face only supports input_size=640 (got {input_size}). The ONNX model has a fixed input shape.'
+            )
+
+        self.model_name = model_name
+        self.confidence_threshold = confidence_threshold
+        self.nms_threshold = nms_threshold
+        self.input_size = input_size
+
+        # Advanced options from kwargs
+        self.max_det = kwargs.get('max_det', 750)
+
+        Logger.info(
+            f'Initializing YOLOv5Face with model={self.model_name}, confidence_threshold={self.confidence_threshold}, '
+            f'nms_threshold={self.nms_threshold}, input_size={self.input_size}'
+        )
+
+        # Get path to model weights
+        self._model_path = verify_model_weights(self.model_name)
+        Logger.info(f'Verified model weights located at: {self._model_path}')
+
+        # Initialize model
+        self._initialize_model(self._model_path)
+
+    def _initialize_model(self, model_path: str) -> None:
+        """
+        Initializes an ONNX model session from the given path.
+
+        Args:
+            model_path (str): The file path to the ONNX model.
+
+        Raises:
+            RuntimeError: If the model fails to load, logs an error and raises an exception.
+        """
+        try:
+            self.session = create_onnx_session(model_path)
+            self.input_names = self.session.get_inputs()[0].name
+            self.output_names = [x.name for x in self.session.get_outputs()]
+            Logger.info(f'Successfully initialized the model from {model_path}')
+        except Exception as e:
+            Logger.error(f"Failed to load model from '{model_path}': {e}", exc_info=True)
+            raise RuntimeError(f"Failed to initialize model session for '{model_path}'") from e
+
+    def preprocess(self, image: np.ndarray) -> tuple[np.ndarray, float, tuple[int, int]]:
+        """
+        Preprocess image for inference.
+
+        Args:
+            image (np.ndarray): Input image (BGR format)
+
+        Returns:
+            Tuple[np.ndarray, float, Tuple[int, int]]: Preprocessed image, scale ratio, and padding
+        """
+        # Get original image shape
+        img_h, img_w = image.shape[:2]
+
+        # Calculate scale ratio
+        scale = min(self.input_size / img_h, self.input_size / img_w)
+        new_h, new_w = int(img_h * scale), int(img_w * scale)
+
+        # Resize image
+        img_resized = cv2.resize(image, (new_w, new_h), interpolation=cv2.INTER_LINEAR)
+
+        # Create padded image
+        img_padded = np.full((self.input_size, self.input_size, 3), 114, dtype=np.uint8)
+
+        # Calculate padding
+        pad_h = (self.input_size - new_h) // 2
+        pad_w = (self.input_size - new_w) // 2
+
+        # Place resized image in center
+        img_padded[pad_h : pad_h + new_h, pad_w : pad_w + new_w] = img_resized
+
+        # Convert to RGB and normalize
+        img_rgb = cv2.cvtColor(img_padded, cv2.COLOR_BGR2RGB)
+        img_normalized = img_rgb.astype(np.float32) / 255.0
+
+        # Transpose to CHW format (HWC -> CHW) and add batch dimension
+        img_transposed = np.transpose(img_normalized, (2, 0, 1))
+        img_batch = np.expand_dims(img_transposed, axis=0)
+        img_batch = np.ascontiguousarray(img_batch)
+
+        return img_batch, scale, (pad_w, pad_h)
+
+    def inference(self, input_tensor: np.ndarray) -> list[np.ndarray]:
+        """Perform model inference on the preprocessed image tensor.
+
+        Args:
+            input_tensor (np.ndarray): Preprocessed input tensor.
+
+        Returns:
+            List[np.ndarray]: Raw model outputs.
+        """
+        return self.session.run(self.output_names, {self.input_names: input_tensor})
+
+    def postprocess(
+        self,
+        predictions: np.ndarray,
+        scale: float,
+        padding: tuple[int, int],
+    ) -> tuple[np.ndarray, np.ndarray]:
+        """
+        Postprocess model predictions.
+
+        Args:
+            predictions (np.ndarray): Raw model output
+            scale (float): Scale ratio used in preprocessing
+            padding (Tuple[int, int]): Padding used in preprocessing
+
+        Returns:
+            Tuple[np.ndarray, np.ndarray]: Filtered detections and landmarks
+                - detections: [x1, y1, x2, y2, conf]
+                - landmarks: [5, 2] for each detection
+        """
+        # predictions shape: (1, 25200, 16)
+        # 16 = [x, y, w, h, obj_conf, cls_conf, 10 landmarks (5 points * 2 coords)]
+
+        predictions = predictions[0]  # Remove batch dimension
+
+        # Filter by confidence
+        mask = predictions[:, 4] >= self.confidence_threshold
+        predictions = predictions[mask]
+
+        if len(predictions) == 0:
+            return np.array([]), np.array([])
+
+        # Convert from xywh to xyxy
+        boxes = self._xywh2xyxy(predictions[:, :4])
+
+        # Get confidence scores
+        scores = predictions[:, 4]
+
+        # Get landmarks (5 points, 10 coordinates)
+        landmarks = predictions[:, 5:15].copy()
+
+        # Apply NMS
+        detections_for_nms = np.hstack((boxes, scores[:, None])).astype(np.float32, copy=False)
+        keep = non_max_suppression(detections_for_nms, self.nms_threshold)
+
+        if len(keep) == 0:
+            return np.array([]), np.array([])
+
+        # Filter detections and limit to max_det
+        keep = keep[: self.max_det]
+        boxes = boxes[keep]
+        scores = scores[keep]
+        landmarks = landmarks[keep]
+
+        # Scale back to original image coordinates
+        pad_w, pad_h = padding
+        boxes[:, [0, 2]] = (boxes[:, [0, 2]] - pad_w) / scale
+        boxes[:, [1, 3]] = (boxes[:, [1, 3]] - pad_h) / scale
+
+        # Scale landmarks
+        for i in range(5):
+            landmarks[:, i * 2] = (landmarks[:, i * 2] - pad_w) / scale
+            landmarks[:, i * 2 + 1] = (landmarks[:, i * 2 + 1] - pad_h) / scale
+
+        # Reshape landmarks to (N, 5, 2)
+        landmarks = landmarks.reshape(-1, 5, 2)
+
+        # Combine results
+        detections = np.concatenate([boxes, scores[:, None]], axis=1)
+
+        return detections, landmarks
+
+    def _xywh2xyxy(self, x: np.ndarray) -> np.ndarray:
+        """
+        Convert bounding box format from xywh to xyxy.
+
+        Args:
+            x (np.ndarray): Boxes in [x, y, w, h] format
+
+        Returns:
+            np.ndarray: Boxes in [x1, y1, x2, y2] format
+        """
+        y = np.copy(x)
+        y[..., 0] = x[..., 0] - x[..., 2] / 2  # x1
+        y[..., 1] = x[..., 1] - x[..., 3] / 2  # y1
+        y[..., 2] = x[..., 0] + x[..., 2] / 2  # x2
+        y[..., 3] = x[..., 1] + x[..., 3] / 2  # y2
+        return y
+
+    def detect(
+        self,
+        image: np.ndarray,
+        *,
+        max_num: int = 0,
+        metric: Literal['default', 'max'] = 'max',
+        center_weight: float = 2.0,
+    ) -> list[Face]:
+        """
+        Perform face detection on an input image and return bounding boxes and facial landmarks.
+
+        Args:
+            image (np.ndarray): Input image as a NumPy array of shape (H, W, C).
+            max_num (int): Maximum number of detections to return. Use 0 to return all detections. Defaults to 0.
+            metric (Literal["default", "max"]): Metric for ranking detections when `max_num` is limited.
+                - "default": Prioritize detections closer to the image center.
+                - "max": Prioritize detections with larger bounding box areas.
+            center_weight (float): Weight for penalizing detections farther from the image center
+                when using the "default" metric. Defaults to 2.0.
+
+        Returns:
+            List[Face]: List of Face objects, each containing:
+                - bbox (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - confidence (float): Detection confidence score (0.0 to 1.0)
+                - landmarks (np.ndarray): 5-point facial landmarks with shape (5, 2)
+
+        Example:
+            >>> faces = detector.detect(image)
+            >>> for face in faces:
+            ...     bbox = face.bbox  # np.ndarray with shape (4,)
+            ...     confidence = face.confidence  # float
+            ...     landmarks = face.landmarks  # np.ndarray with shape (5, 2)
+            ...     # Can pass landmarks directly to recognition
+            ...     embedding = recognizer.get_normalized_embedding(image, face.landmarks)
+        """
+
+        original_height, original_width = image.shape[:2]
+
+        # Preprocess
+        image_tensor, scale, padding = self.preprocess(image)
+
+        # ONNXRuntime inference
+        outputs = self.inference(image_tensor)
+
+        # Postprocess
+        detections, landmarks = self.postprocess(outputs[0], scale, padding)
+
+        # Handle case when no faces are detected
+        if len(detections) == 0:
+            return []
+
+        if 0 < max_num < detections.shape[0]:
+            # Calculate area of detections
+            area = (detections[:, 2] - detections[:, 0]) * (detections[:, 3] - detections[:, 1])
+
+            # Calculate offsets from image center
+            center = (original_height // 2, original_width // 2)
+            offsets = np.vstack(
+                [
+                    (detections[:, 0] + detections[:, 2]) / 2 - center[1],
+                    (detections[:, 1] + detections[:, 3]) / 2 - center[0],
+                ]
+            )
+
+            # Calculate scores based on the chosen metric
+            offset_dist_squared = np.sum(np.power(offsets, 2.0), axis=0)
+            if metric == 'max':
+                values = area
+            else:
+                values = area - offset_dist_squared * center_weight
+
+            # Sort by scores and select top `max_num`
+            sorted_indices = np.argsort(values)[::-1][:max_num]
+            detections = detections[sorted_indices]
+            landmarks = landmarks[sorted_indices]
+
+        faces = []
+        for i in range(detections.shape[0]):
+            face = Face(
+                bbox=detections[i, :4],
+                confidence=float(detections[i, 4]),
+                landmarks=landmarks[i],
+            )
+            faces.append(face)
+
+        return faces

uniface/face_utils.py

@@ -2,46 +2,54 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from __future__ import annotations
+
 import cv2
 import numpy as np
 from skimage.transform import SimilarityTransform
-from typing import Tuple, Union
+
+__all__ = [
+    'bbox_center_alignment',
+    'compute_similarity',
+    'face_alignment',
+    'transform_points_2d',
+]
 
 
-__all__ = ["face_alignment", "compute_similarity", "bbox_center_alignment", "transform_points_2d"]
-
-
-# Reference alignment for facial landmarks (ArcFace)
+# Standard 5-point facial landmark reference for ArcFace alignment (112x112)
 reference_alignment: np.ndarray = np.array(
     [
         [38.2946, 51.6963],
         [73.5318, 51.5014],
         [56.0252, 71.7366],
         [41.5493, 92.3655],
-        [70.7299, 92.2041]
+        [70.7299, 92.2041],
     ],
-    dtype=np.float32
+    dtype=np.float32,
 )
 
 
-def estimate_norm(landmark: np.ndarray, image_size: Union[int, Tuple[int, int]] = 112) -> Tuple[np.ndarray, np.ndarray]:
-    """
-    Estimate the normalization transformation matrix for facial landmarks.
+def estimate_norm(
+    landmark: np.ndarray,
+    image_size: int | tuple[int, int] = 112,
+) -> tuple[np.ndarray, np.ndarray]:
+    """Estimate the normalization transformation matrix for facial landmarks.
 
     Args:
-        landmark (np.ndarray): Array of shape (5, 2) representing the coordinates of the facial landmarks.
-        image_size (Union[int, Tuple[int, int]], optional): The size of the output image.
-            Can be an integer (for square images) or a tuple (width, height). Default is 112.
+        landmark: Array of shape (5, 2) representing the coordinates of the facial landmarks.
+        image_size: The size of the output image. Can be an integer (for square images)
+            or a tuple (width, height). Default is 112.
 
     Returns:
-        np.ndarray: The 2x3 transformation matrix for aligning the landmarks.
-        np.ndarray: The 2x3 inverse transformation matrix for aligning the landmarks.
+        A tuple containing:
+            - The 2x3 transformation matrix for aligning the landmarks.
+            - The 2x3 inverse transformation matrix.
 
     Raises:
         AssertionError: If the input landmark array does not have the shape (5, 2)
-                        or if image_size is not a multiple of 112 or 128.
+            or if image_size is not a multiple of 112 or 128.
     """
-    assert landmark.shape == (5, 2), "Landmark array must have shape (5, 2)."
+    assert landmark.shape == (5, 2), 'Landmark array must have shape (5, 2).'
 
     # Handle both int and tuple inputs
     if isinstance(image_size, tuple):
@@ -49,7 +57,7 @@ def estimate_norm(landmark: np.ndarray, image_size: Union[int, Tuple[int, int]]
     else:
         size = image_size
 
-    assert size % 112 == 0 or size % 128 == 0, "Image size must be a multiple of 112 or 128."
+    assert size % 112 == 0 or size % 128 == 0, 'Image size must be a multiple of 112 or 128.'
 
     if size % 112 == 0:
         ratio = float(size) / 112.0
@@ -72,22 +80,26 @@ def estimate_norm(landmark: np.ndarray, image_size: Union[int, Tuple[int, int]]
     return matrix, inverse_matrix
 
 
-def face_alignment(image: np.ndarray, landmark: np.ndarray, image_size: Union[int, Tuple[int, int]] = 112) -> Tuple[np.ndarray, np.ndarray]:
-    """
-    Align the face in the input image based on the given facial landmarks.
+def face_alignment(
+    image: np.ndarray,
+    landmark: np.ndarray,
+    image_size: int | tuple[int, int] = 112,
+) -> tuple[np.ndarray, np.ndarray]:
+    """Align the face in the input image based on the given facial landmarks.
 
     Args:
-        image (np.ndarray): Input image as a NumPy array.
-        landmark (np.ndarray): Array of shape (5, 2) representing the coordinates of the facial landmarks.
-        image_size (Union[int, Tuple[int, int]], optional): The size of the aligned output image.
-            Can be an integer (for square images) or a tuple (width, height). Default is 112.
+        image: Input image as a NumPy array with shape (H, W, C).
+        landmark: Array of shape (5, 2) representing the facial landmark coordinates.
+        image_size: The size of the aligned output image. Can be an integer
+            (for square images) or a tuple (width, height). Default is 112.
 
     Returns:
-        np.ndarray: The aligned face as a NumPy array.
-        np.ndarray: The 2x3 transformation matrix used for alignment.
+        A tuple containing:
+            - The aligned face as a NumPy array.
+            - The 2x3 inverse transformation matrix used for alignment.
     """
     # Get the transformation matrix
-    M, M_inv = estimate_norm(landmark, image_size)
+    transform_matrix, inverse_transform = estimate_norm(landmark, image_size)
 
     # Handle both int and tuple for warpAffine output size
     if isinstance(image_size, int):
@@ -96,44 +108,50 @@ def face_alignment(image: np.ndarray, landmark: np.ndarray, image_size: Union[in
         output_size = image_size
 
     # Warp the input image to align the face
-    warped = cv2.warpAffine(image, M, output_size, borderValue=0.0)
+    warped = cv2.warpAffine(image, transform_matrix, output_size, borderValue=0.0)
 
-    return warped, M_inv
+    return warped, inverse_transform
 
 
 def compute_similarity(feat1: np.ndarray, feat2: np.ndarray, normalized: bool = False) -> np.float32:
-    """Computing Similarity between two faces.
+    """Compute cosine similarity between two face embeddings.
 
     Args:
-        feat1 (np.ndarray): First embedding.
-        feat2 (np.ndarray): Second embedding.
-        normalized (bool): Set True if the embeddings are already L2 normalized.
+        feat1: First embedding vector.
+        feat2: Second embedding vector.
+        normalized: Set True if the embeddings are already L2 normalized.
 
     Returns:
-        np.float32: Cosine similarity.
+        Cosine similarity score in range [-1, 1].
     """
     feat1 = feat1.ravel()
     feat2 = feat2.ravel()
     if normalized:
         return np.dot(feat1, feat2)
-    else:
-        return np.dot(feat1, feat2) / (np.linalg.norm(feat1) * np.linalg.norm(feat2) + 1e-5)
+    # Add small epsilon to prevent division by zero
+    return np.dot(feat1, feat2) / (np.linalg.norm(feat1) * np.linalg.norm(feat2) + 1e-5)
 
 
-def bbox_center_alignment(image, center, output_size, scale, rotation):
-    """
-    Apply center-based alignment, scaling, and rotation to an image.
+def bbox_center_alignment(
+    image: np.ndarray,
+    center: tuple[float, float],
+    output_size: int,
+    scale: float,
+    rotation: float,
+) -> tuple[np.ndarray, np.ndarray]:
+    """Apply center-based alignment, scaling, and rotation to an image.
 
     Args:
-        image (np.ndarray): Input image.
-        center (Tuple[float, float]): Center point (e.g., face center from bbox).
-        output_size (int): Desired output image size (square).
-        scale (float): Scaling factor to zoom in/out.
-        rotation (float): Rotation angle in degrees (clockwise).
+        image: Input image with shape (H, W, C).
+        center: Center point (x, y), e.g., face center from bbox.
+        output_size: Desired output image size (square).
+        scale: Scaling factor to zoom in/out.
+        rotation: Rotation angle in degrees (clockwise).
 
     Returns:
-        cropped (np.ndarray): Aligned and cropped image.
-        M (np.ndarray): 2x3 affine transform matrix used.
+        A tuple containing:
+            - Aligned and cropped image with shape (output_size, output_size, C).
+            - 2x3 affine transform matrix used.
     """
 
     # Convert rotation from degrees to radians
@@ -166,15 +184,14 @@ def bbox_center_alignment(image, center, output_size, scale, rotation):
 
 
 def transform_points_2d(points: np.ndarray, transform: np.ndarray) -> np.ndarray:
-    """
-    Apply a 2D affine transformation to an array of 2D points.
+    """Apply a 2D affine transformation to an array of 2D points.
 
     Args:
-        points (np.ndarray): An (N, 2) array of 2D points.
-        transform (np.ndarray): A (2, 3) affine transformation matrix.
+        points: An (N, 2) array of 2D points.
+        transform: A (2, 3) affine transformation matrix.
 
     Returns:
-        np.ndarray: Transformed (N, 2) array of points.
+        Transformed (N, 2) array of points.
     """
     transformed = np.zeros_like(points, dtype=np.float32)
     for i in range(points.shape[0]):

uniface/gaze/__init__.py

@@ -0,0 +1,54 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from uniface.types import GazeResult
+
+from .base import BaseGazeEstimator
+from .models import MobileGaze
+
+
+def create_gaze_estimator(method: str = 'mobilegaze', **kwargs) -> BaseGazeEstimator:
+    """
+    Factory function to create gaze estimators.
+
+    This function initializes and returns a gaze estimator instance based on the
+    specified method. It acts as a high-level interface to the underlying
+    model classes.
+
+    Args:
+        method (str): The gaze estimation method to use.
+            Options: 'mobilegaze' (default).
+        **kwargs: Model-specific parameters passed to the estimator's constructor.
+            For example, `model_name` can be used to select a specific
+            backbone from `GazeWeights` enum (RESNET18, RESNET34, RESNET50,
+            MOBILENET_V2, MOBILEONE_S0).
+
+    Returns:
+        BaseGazeEstimator: An initialized gaze estimator instance ready for use.
+
+    Raises:
+        ValueError: If the specified `method` is not supported.
+
+    Examples:
+        >>> # Create the default MobileGaze estimator (ResNet18 backbone)
+        >>> estimator = create_gaze_estimator()
+
+        >>> # Create with MobileNetV2 backbone
+        >>> from uniface.constants import GazeWeights
+        >>> estimator = create_gaze_estimator('mobilegaze', model_name=GazeWeights.MOBILENET_V2)
+
+        >>> # Use the estimator
+        >>> result = estimator.estimate(face_crop)
+        >>> print(f'Pitch: {result.pitch}, Yaw: {result.yaw}')
+    """
+    method = method.lower()
+
+    if method in ('mobilegaze', 'mobile_gaze', 'gaze'):
+        return MobileGaze(**kwargs)
+    else:
+        available = ['mobilegaze']
+        raise ValueError(f"Unsupported gaze estimation method: '{method}'. Available: {available}")
+
+
+__all__ = ['BaseGazeEstimator', 'GazeResult', 'MobileGaze', 'create_gaze_estimator']

uniface/gaze/base.py

@@ -0,0 +1,113 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+import numpy as np
+
+from uniface.types import GazeResult
+
+__all__ = ['BaseGazeEstimator', 'GazeResult']
+
+
+class BaseGazeEstimator(ABC):
+    """
+    Abstract base class for all gaze estimation models.
+
+    This class defines the common interface that all gaze estimators must implement,
+    ensuring consistency across different gaze estimation methods. Gaze estimation
+    predicts the direction a person is looking based on their face image.
+
+    The gaze direction is represented as pitch and yaw angles in radians:
+    - Pitch: Vertical angle (positive = looking up, negative = looking down)
+    - Yaw: Horizontal angle (positive = looking right, negative = looking left)
+    """
+
+    @abstractmethod
+    def _initialize_model(self) -> None:
+        """
+        Initialize the underlying model for inference.
+
+        This method should handle loading model weights, creating the
+        inference session (e.g., ONNX Runtime), and any necessary
+        setup procedures to prepare the model for prediction.
+
+        Raises:
+            RuntimeError: If the model fails to load or initialize.
+        """
+        raise NotImplementedError('Subclasses must implement the _initialize_model method.')
+
+    @abstractmethod
+    def preprocess(self, face_image: np.ndarray) -> np.ndarray:
+        """
+        Preprocess the input face image for model inference.
+
+        This method should take a raw face crop and convert it into the format
+        expected by the model's inference engine (e.g., normalized tensor).
+
+        Args:
+            face_image (np.ndarray): A cropped face image in BGR format with
+                                     shape (H, W, C).
+
+        Returns:
+            np.ndarray: The preprocessed image tensor ready for inference,
+                        typically with shape (1, C, H, W).
+        """
+        raise NotImplementedError('Subclasses must implement the preprocess method.')
+
+    @abstractmethod
+    def postprocess(self, outputs: tuple[np.ndarray, np.ndarray]) -> GazeResult:
+        """
+        Postprocess raw model outputs into gaze angles.
+
+        This method takes the raw output from the model's inference and
+        converts it into pitch and yaw angles in radians.
+
+        Args:
+            outputs: Raw outputs from the model inference. The format depends
+                     on the specific model architecture.
+
+        Returns:
+            GazeResult: Result containing pitch and yaw angles in radians.
+        """
+        raise NotImplementedError('Subclasses must implement the postprocess method.')
+
+    @abstractmethod
+    def estimate(self, face_image: np.ndarray) -> GazeResult:
+        """
+        Perform end-to-end gaze estimation on a face image.
+
+        This method orchestrates the full pipeline: preprocessing the input,
+        running inference, and postprocessing to return the gaze direction.
+
+        Args:
+            face_image (np.ndarray): A cropped face image in BGR format.
+                                     The face should be roughly centered and
+                                     well-framed within the image.
+
+        Returns:
+            GazeResult: Result containing pitch and yaw angles in radians:
+                - pitch: Vertical gaze angle (positive = up, negative = down)
+                - yaw: Horizontal gaze angle (positive = right, negative = left)
+
+        Example:
+            >>> estimator = create_gaze_estimator()
+            >>> result = estimator.estimate(face_crop)
+            >>> print(f'Looking: pitch={np.degrees(result.pitch):.1f}°, yaw={np.degrees(result.yaw):.1f}°')
+        """
+        raise NotImplementedError('Subclasses must implement the estimate method.')
+
+    def __call__(self, face_image: np.ndarray) -> GazeResult:
+        """
+        Provides a convenient, callable shortcut for the `estimate` method.
+
+        Args:
+            face_image (np.ndarray): A cropped face image in BGR format.
+
+        Returns:
+            GazeResult: Result containing pitch and yaw angles in radians.
+        """
+        return self.estimate(face_image)

uniface/gaze/models.py

@@ -0,0 +1,186 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+import cv2
+import numpy as np
+
+from uniface.constants import GazeWeights
+from uniface.log import Logger
+from uniface.model_store import verify_model_weights
+from uniface.onnx_utils import create_onnx_session
+from uniface.types import GazeResult
+
+from .base import BaseGazeEstimator
+
+__all__ = ['MobileGaze']
+
+
+class MobileGaze(BaseGazeEstimator):
+    """
+    MobileGaze: Real-Time Gaze Estimation with ONNX Runtime.
+
+    MobileGaze is a gaze estimation model that predicts gaze direction from a single
+    face image. It supports multiple backbone architectures including ResNet 18/34/50,
+    MobileNetV2, and MobileOne S0. The model uses a classification approach with binned
+    angles, which are then decoded to continuous pitch and yaw values.
+
+    The model outputs gaze direction as pitch (vertical) and yaw (horizontal) angles
+    in radians.
+
+    Reference:
+        https://github.com/yakhyo/gaze-estimation
+
+    Args:
+        model_name (GazeWeights): The enum specifying the gaze model backbone to load.
+            Options: RESNET18, RESNET34, RESNET50, MOBILENET_V2, MOBILEONE_S0.
+            Defaults to `GazeWeights.RESNET18`.
+        input_size (Tuple[int, int]): The resolution (width, height) for the model's
+            input. Defaults to (448, 448).
+
+    Attributes:
+        input_size (Tuple[int, int]): Model input dimensions.
+        input_mean (list): Per-channel mean values for normalization (ImageNet).
+        input_std (list): Per-channel std values for normalization (ImageNet).
+
+    Example:
+        >>> from uniface.gaze import MobileGaze
+        >>> from uniface import RetinaFace
+        >>>
+        >>> detector = RetinaFace()
+        >>> gaze_estimator = MobileGaze()
+        >>>
+        >>> # Detect faces and estimate gaze for each
+        >>> faces = detector.detect(image)
+        >>> for face in faces:
+        ...     bbox = face.bbox
+        ...     x1, y1, x2, y2 = map(int, bbox[:4])
+        ...     face_crop = image[y1:y2, x1:x2]
+        ...     result = gaze_estimator.estimate(face_crop)
+        ...     print(f'Gaze: pitch={np.degrees(result.pitch):.1f}°, yaw={np.degrees(result.yaw):.1f}°')
+    """
+
+    def __init__(
+        self,
+        model_name: GazeWeights = GazeWeights.RESNET34,
+        input_size: tuple[int, int] = (448, 448),
+    ) -> None:
+        Logger.info(f'Initializing MobileGaze with model={model_name}, input_size={input_size}')
+
+        self.input_size = input_size
+        self.input_mean = [0.485, 0.456, 0.406]
+        self.input_std = [0.229, 0.224, 0.225]
+
+        # Model specific parameters for bin-based classification (Gaze360 config)
+        self._bins = 90
+        self._binwidth = 4
+        self._angle_offset = 180
+        self._idx_tensor = np.arange(self._bins, dtype=np.float32)
+
+        self.model_path = verify_model_weights(model_name)
+        self._initialize_model()
+
+    def _initialize_model(self) -> None:
+        """
+        Initialize the ONNX model from the stored model path.
+
+        Raises:
+            RuntimeError: If the model fails to load or initialize.
+        """
+        try:
+            self.session = create_onnx_session(self.model_path)
+
+            # Get input configuration
+            input_cfg = self.session.get_inputs()[0]
+            input_shape = input_cfg.shape
+            self.input_name = input_cfg.name
+            self.input_size = tuple(input_shape[2:4][::-1])  # Update from model
+
+            # Get output configuration
+            outputs = self.session.get_outputs()
+            self.output_names = [output.name for output in outputs]
+
+            if len(self.output_names) != 2:
+                raise ValueError(f'Expected 2 output nodes (pitch, yaw), got {len(self.output_names)}')
+
+            Logger.info(f'MobileGaze initialized with input size {self.input_size}')
+
+        except Exception as e:
+            Logger.error(f"Failed to load gaze model from '{self.model_path}'", exc_info=True)
+            raise RuntimeError(f'Failed to initialize gaze model: {e}') from e
+
+    def preprocess(self, face_image: np.ndarray) -> np.ndarray:
+        """
+        Preprocess a face crop for gaze estimation.
+
+        Args:
+            face_image (np.ndarray): A cropped face image in BGR format.
+
+        Returns:
+            np.ndarray: Preprocessed image tensor with shape (1, 3, H, W).
+        """
+        # Convert BGR to RGB
+        image = cv2.cvtColor(face_image, cv2.COLOR_BGR2RGB)
+
+        # Resize to model input size
+        image = cv2.resize(image, self.input_size)
+
+        # Normalize to [0, 1] and apply normalization
+        image = image.astype(np.float32) / 255.0
+        mean = np.array(self.input_mean, dtype=np.float32)
+        std = np.array(self.input_std, dtype=np.float32)
+        image = (image - mean) / std
+
+        # HWC -> CHW -> NCHW
+        image = np.transpose(image, (2, 0, 1))
+        image = np.expand_dims(image, axis=0).astype(np.float32)
+
+        return image
+
+    def _softmax(self, x: np.ndarray) -> np.ndarray:
+        """Apply softmax along axis 1."""
+        e_x = np.exp(x - np.max(x, axis=1, keepdims=True))
+        return e_x / e_x.sum(axis=1, keepdims=True)
+
+    def postprocess(self, outputs: tuple[np.ndarray, np.ndarray]) -> GazeResult:
+        """
+        Postprocess raw model outputs into gaze angles.
+
+        This method takes the raw output from the model's inference and
+        converts it into pitch and yaw angles in radians.
+
+        Args:
+            outputs: Raw outputs from the model inference. The format depends
+                     on the specific model architecture.
+
+        Returns:
+            GazeResult: Result containing pitch and yaw angles in radians.
+        """
+        pitch_logits, yaw_logits = outputs
+
+        # Convert logits to probabilities
+        pitch_probs = self._softmax(pitch_logits)
+        yaw_probs = self._softmax(yaw_logits)
+
+        # Compute expected bin index (soft-argmax)
+        pitch_deg = np.sum(pitch_probs * self._idx_tensor, axis=1) * self._binwidth - self._angle_offset
+        yaw_deg = np.sum(yaw_probs * self._idx_tensor, axis=1) * self._binwidth - self._angle_offset
+
+        # Convert degrees to radians
+        pitch = float(np.radians(pitch_deg[0]))
+        yaw = float(np.radians(yaw_deg[0]))
+
+        return GazeResult(pitch=pitch, yaw=yaw)
+
+    def estimate(self, face_image: np.ndarray) -> GazeResult:
+        """
+        Perform end-to-end gaze estimation on a face image.
+
+        This method orchestrates the full pipeline: preprocessing the input,
+        running inference, and postprocessing to return the gaze direction.
+        """
+        input_tensor = self.preprocess(face_image)
+        outputs = self.session.run(self.output_names, {self.input_name: input_tensor})
+
+        return self.postprocess((outputs[0], outputs[1]))

uniface/landmark/__init__.py

@@ -2,8 +2,8 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from .models import Landmark106
 from .base import BaseLandmarker
+from .models import Landmark106
 
 
 def create_landmarker(method: str = '2d106det', **kwargs) -> BaseLandmarker:
@@ -25,8 +25,4 @@ def create_landmarker(method: str = '2d106det', **kwargs) -> BaseLandmarker:
         raise ValueError(f"Unsupported method: '{method}'. Available: {available}")
 
 
-__all__ = [
-    "create_landmarker",
-    "Landmark106",
-    "BaseLandmarker"
-]
+__all__ = ['BaseLandmarker', 'Landmark106', 'create_landmarker']

uniface/landmark/base.py

@@ -3,6 +3,7 @@
 # GitHub: https://github.com/yakhyo
 
 from abc import ABC, abstractmethod
+
 import numpy as np
 
 
@@ -10,6 +11,7 @@ class BaseLandmarker(ABC):
     """
     Abstract Base Class for all facial landmark models.
     """
+
     @abstractmethod
     def get_landmarks(self, image: np.ndarray, bbox: np.ndarray) -> np.ndarray:
         """
@@ -28,3 +30,15 @@ class BaseLandmarker(ABC):
                         where N is the number of landmarks.
         """
         raise NotImplementedError
+
+    def __call__(self, image: np.ndarray, bbox: np.ndarray) -> np.ndarray:
+        """Callable shortcut for the `get_landmarks` method.
+
+        Args:
+            image (np.ndarray): The full source image in BGR format.
+            bbox (np.ndarray): A bounding box of a face [x1, y1, x2, y2].
+
+        Returns:
+            np.ndarray: An array of predicted landmark points with shape (N, 2).
+        """
+        return self.get_landmarks(image, bbox)

uniface/landmark/models.py

@@ -2,18 +2,19 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+
 import cv2
 import numpy as np
-from typing import Tuple
 
-from uniface.log import Logger
 from uniface.constants import LandmarkWeights
-from uniface.model_store import verify_model_weights
 from uniface.face_utils import bbox_center_alignment, transform_points_2d
+from uniface.log import Logger
+from uniface.model_store import verify_model_weights
 from uniface.onnx_utils import create_onnx_session
+
 from .base import BaseLandmarker
 
-__all__ = ['Landmark']
+__all__ = ['Landmark106']
 
 
 class Landmark106(BaseLandmarker):
@@ -40,15 +41,13 @@ class Landmark106(BaseLandmarker):
         >>> print(landmarks.shape)
         (106, 2)
     """
+
     def __init__(
         self,
         model_name: LandmarkWeights = LandmarkWeights.DEFAULT,
-        input_size: Tuple[int, int] = (192, 192)
+        input_size: tuple[int, int] = (192, 192),
     ) -> None:
-        Logger.info(
-            f"Initializing Facial Landmark with model={model_name}, "
-            f"input_size={input_size}"
-        )
+        Logger.info(f'Initializing Facial Landmark with model={model_name}, input_size={input_size}')
         self.input_size = input_size
         self.input_std = 1.0
         self.input_mean = 0.0
@@ -79,13 +78,13 @@ class Landmark106(BaseLandmarker):
             self.lmk_dim = 2  # x,y coordinates
             self.lmk_num = output_shape[1] // self.lmk_dim  # Number of landmarks
 
-            Logger.info(f"Model initialized with {self.lmk_num} landmarks")
+            Logger.info(f'Model initialized with {self.lmk_num} landmarks')
 
         except Exception as e:
             Logger.error(f"Failed to load landmark model from '{self.model_path}'", exc_info=True)
-            raise RuntimeError(f"Failed to initialize landmark model: {e}")
+            raise RuntimeError(f'Failed to initialize landmark model: {e}') from e
 
-    def preprocess(self, image: np.ndarray, bbox: np.ndarray) -> Tuple[np.ndarray, np.ndarray]:
+    def preprocess(self, image: np.ndarray, bbox: np.ndarray) -> tuple[np.ndarray, np.ndarray]:
         """Prepares a face crop for inference.
 
         This method takes a face bounding box, performs a center alignment to
@@ -108,8 +107,11 @@ class Landmark106(BaseLandmarker):
         aligned_face, transform_matrix = bbox_center_alignment(image, center, self.input_size[0], scale, 0.0)
 
         face_blob = cv2.dnn.blobFromImage(
-            aligned_face, 1.0 / self.input_std, self.input_size,
-            (self.input_mean, self.input_mean, self.input_mean), swapRB=True
+            aligned_face,
+            1.0 / self.input_std,
+            self.input_size,
+            (self.input_mean, self.input_mean, self.input_mean),
+            swapRB=True,
         )
         return face_blob, transform_matrix
 
@@ -129,7 +131,7 @@ class Landmark106(BaseLandmarker):
         """
         landmarks = predictions.reshape((-1, 2))
         landmarks[:, 0:2] += 1
-        landmarks[:, 0:2] *= (self.input_size[0] // 2)
+        landmarks[:, 0:2] *= self.input_size[0] // 2
 
         inverse_matrix = cv2.invertAffineTransform(transform_matrix)
         landmarks = transform_points_2d(landmarks, inverse_matrix)
@@ -149,64 +151,6 @@ class Landmark106(BaseLandmarker):
             np.ndarray: An array of predicted landmark points with shape (106, 2).
         """
         face_blob, transform_matrix = self.preprocess(image, bbox)
-        raw_predictions = self.session.run(
-            self.output_names, {self.input_names[0]: face_blob}
-        )[0][0]
+        raw_predictions = self.session.run(self.output_names, {self.input_names[0]: face_blob})[0][0]
         landmarks = self.postprocess(raw_predictions, transform_matrix)
         return landmarks
-
-
-
-# Testing code
-if __name__ == "__main__":
-    from uniface.detection import RetinaFace
-    from uniface.landmark import Landmark106
-
-    face_detector = RetinaFace()
-    landmarker = Landmark106()
-
-    cap = cv2.VideoCapture(0)
-    if not cap.isOpened():
-        print("Webcam not available.")
-        exit()
-
-    print("Press 'q' to quit.")
-
-    while True:
-        ret, frame = cap.read()
-        if not ret:
-            print("Frame capture failed.")
-            break
-
-        # 2. The detect method returns a list of dictionaries
-        faces = face_detector.detect(frame)
-
-        if not faces:
-            cv2.imshow("Facial Landmark Detection", frame)
-            if cv2.waitKey(1) & 0xFF == ord('q'):
-                break
-            continue
-
-        # 3. Loop through the list of face dictionaries
-        for face in faces:
-            # Extract the bounding box
-            bbox = face['bbox']
-
-            # 4. Get landmarks for the current face using its bounding box
-            landmarks = landmarker.get_landmarks(frame, bbox)
-
-            # --- Drawing Logic ---
-            # Draw the landmarks
-            for (x, y) in landmarks.astype(int):
-                cv2.circle(frame, (x, y), 2, (0, 255, 0), -1)
-
-            # Draw the bounding box
-            x1, y1, x2, y2 = map(int, bbox)
-            cv2.rectangle(frame, (x1, y1), (x2, y2), (255, 0, 0), 2)
-
-        cv2.imshow("Facial Landmark Detection", frame)
-        if cv2.waitKey(1) & 0xFF == ord('q'):
-            break
-
-    cap.release()
-    cv2.destroyAllWindows()

uniface/log.py

@@ -1,28 +1,45 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Logging utilities for UniFace.
+
+This module provides a centralized logger for the UniFace library,
+allowing users to enable verbose logging when debugging or developing.
+"""
+
+from __future__ import annotations
+
 import logging
 
+__all__ = ['Logger', 'enable_logging']
+
 # Create logger for uniface
-Logger = logging.getLogger("uniface")
+Logger = logging.getLogger('uniface')
 Logger.setLevel(logging.WARNING)  # Only show warnings/errors by default
 Logger.addHandler(logging.NullHandler())
 
 
-def enable_logging(level=logging.INFO):
-    """
-    Enable verbose logging for uniface.
+def enable_logging(level: int = logging.INFO) -> None:
+    """Enable verbose logging for uniface.
+
+    Configures the logger to output messages to stdout with timestamps.
+    Call this function to see informational messages during model loading
+    and inference.
 
     Args:
-        level: Logging level (logging.DEBUG, logging.INFO, etc.)
+        level: Logging level. Defaults to logging.INFO.
+            Common values: logging.DEBUG, logging.INFO, logging.WARNING.
 
     Example:
         >>> from uniface import enable_logging
+        >>> import logging
         >>> enable_logging()  # Show INFO logs
+        >>> enable_logging(level=logging.DEBUG)  # Show DEBUG logs
     """
     Logger.handlers.clear()
     handler = logging.StreamHandler()
-    handler.setFormatter(logging.Formatter(
-        "%(asctime)s - %(levelname)s - %(message)s",
-        datefmt="%Y-%m-%d %H:%M:%S"
-    ))
+    handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s', datefmt='%Y-%m-%d %H:%M:%S'))
     Logger.addHandler(handler)
     Logger.setLevel(level)
     Logger.propagate = False

uniface/model_store.py

@@ -2,45 +2,53 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-import os
+"""Model weight management for UniFace.
+
+This module handles downloading, caching, and verifying model weights
+using SHA-256 checksums for integrity validation.
+"""
+
+from __future__ import annotations
+
+from enum import Enum
 import hashlib
+import os
+
 import requests
 from tqdm import tqdm
 
-from uniface.log import Logger
 import uniface.constants as const
-
+from uniface.log import Logger
 
 __all__ = ['verify_model_weights']
 
 
-def verify_model_weights(model_name: str, root: str = '~/.uniface/models') -> str:
-    """
-    Ensure model weights are present, downloading and verifying them using SHA-256 if necessary.
+def verify_model_weights(model_name: Enum, root: str = '~/.uniface/models') -> str:
+    """Ensure model weights are present, downloading and verifying them if necessary.
 
-    Given a model identifier from an Enum class (e.g., `RetinaFaceWeights.MNET_V2`), this function checks if
-    the corresponding `.onnx` weight file exists locally. If not, it downloads the file from a predefined URL.
-    After download, the file’s integrity is verified using a SHA-256 hash. If verification fails, the file is deleted
-    and an error is raised.
+    Given a model identifier from an Enum class (e.g., `RetinaFaceWeights.MNET_V2`),
+    this function checks if the corresponding weight file exists locally. If not,
+    it downloads the file from a predefined URL and verifies its integrity using
+    a SHA-256 hash.
 
     Args:
-        model_name (Enum): Model weight identifier (e.g., `RetinaFaceWeights.MNET_V2`, `ArcFaceWeights.RESNET`, etc.).
-        root (str, optional): Directory to store or locate the model weights. Defaults to '~/.uniface/models'.
+        model_name: Model weight identifier enum (e.g., `RetinaFaceWeights.MNET_V2`).
+        root: Directory to store or locate the model weights.
+            Defaults to '~/.uniface/models'.
 
     Returns:
-        str: Absolute path to the verified model weights file.
+        Absolute path to the verified model weights file.
 
     Raises:
         ValueError: If the model is unknown or SHA-256 verification fails.
         ConnectionError: If downloading the file fails.
 
-    Examples:
-        >>> from uniface.models import RetinaFaceWeights, verify_model_weights
-        >>> verify_model_weights(RetinaFaceWeights.MNET_V2)
+    Example:
+        >>> from uniface.constants import RetinaFaceWeights
+        >>> from uniface.model_store import verify_model_weights
+        >>> path = verify_model_weights(RetinaFaceWeights.MNET_V2)
+        >>> print(path)
         '/home/user/.uniface/models/retinaface_mnet_v2.onnx'
-
-        >>> verify_model_weights(RetinaFaceWeights.RESNET34, root='/custom/dir')
-        '/custom/dir/retinaface_r34.onnx'
     """
 
     root = os.path.expanduser(root)
@@ -62,49 +70,58 @@ def verify_model_weights(model_name: str, root: str = '~/.uniface/models') -> st
             Logger.info(f"Successfully downloaded '{model_name}' to {model_path}")
         except Exception as e:
             Logger.error(f"Failed to download model '{model_name}': {e}")
-            raise ConnectionError(f"Download failed for '{model_name}'")
+            raise ConnectionError(f"Download failed for '{model_name}'") from e
 
     expected_hash = const.MODEL_SHA256.get(model_name)
     if expected_hash and not verify_file_hash(model_path, expected_hash):
         os.remove(model_path)  # Remove corrupted file
-        Logger.warning("Corrupted weight detected. Removing...")
+        Logger.warning('Corrupted weight detected. Removing...')
         raise ValueError(f"Hash mismatch for '{model_name}'. The file may be corrupted; please try downloading again.")
 
     return model_path
 
 
-def download_file(url: str, dest_path: str) -> None:
-    """Download a file from a URL in chunks and save it to the destination path."""
+def download_file(url: str, dest_path: str, timeout: int = 30) -> None:
+    """Download a file from a URL in chunks and save it to the destination path.
+
+    Args:
+        url: URL to download from.
+        dest_path: Local file path to save to.
+        timeout: Connection timeout in seconds. Defaults to 30.
+    """
     try:
-        response = requests.get(url, stream=True)
+        response = requests.get(url, stream=True, timeout=timeout)
         response.raise_for_status()
-        with open(dest_path, "wb") as file, tqdm(
-            desc=f"Downloading {dest_path}",
-            unit='B',
-            unit_scale=True,
-            unit_divisor=1024
-        ) as progress:
+        with (
+            open(dest_path, 'wb') as file,
+            tqdm(
+                desc=f'Downloading {dest_path}',
+                unit='B',
+                unit_scale=True,
+                unit_divisor=1024,
+            ) as progress,
+        ):
             for chunk in response.iter_content(chunk_size=const.CHUNK_SIZE):
                 if chunk:
                     file.write(chunk)
                     progress.update(len(chunk))
     except requests.RequestException as e:
-        raise ConnectionError(f"Failed to download file from {url}. Error: {e}")
+        raise ConnectionError(f'Failed to download file from {url}. Error: {e}') from e
 
 
 def verify_file_hash(file_path: str, expected_hash: str) -> bool:
     """Compute the SHA-256 hash of the file and compare it with the expected hash."""
     file_hash = hashlib.sha256()
-    with open(file_path, "rb") as f:
-        for chunk in iter(lambda: f.read(const.CHUNK_SIZE), b""):
+    with open(file_path, 'rb') as f:
+        for chunk in iter(lambda: f.read(const.CHUNK_SIZE), b''):
             file_hash.update(chunk)
     actual_hash = file_hash.hexdigest()
     if actual_hash != expected_hash:
-        Logger.warning(f"Expected hash: {expected_hash}, but got: {actual_hash}")
+        Logger.warning(f'Expected hash: {expected_hash}, but got: {actual_hash}')
     return actual_hash == expected_hash
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     model_names = [model.value for model in const.RetinaFaceWeights]
 
     # Download each model in the list

uniface/onnx_utils.py

@@ -2,20 +2,23 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""
-Utilities for ONNX Runtime configuration and provider selection.
+"""ONNX Runtime utilities for UniFace.
+
+This module provides helper functions for creating and managing ONNX Runtime
+inference sessions with automatic hardware acceleration detection.
 """
 
-from typing import List
+from __future__ import annotations
 
 import onnxruntime as ort
 
 from uniface.log import Logger
 
+__all__ = ['create_onnx_session', 'get_available_providers']
 
-def get_available_providers() -> List[str]:
-    """
-    Get list of available ONNX Runtime execution providers for the current platform.
+
+def get_available_providers() -> list[str]:
+    """Get list of available ONNX Runtime execution providers.
 
     Automatically detects and prioritizes hardware acceleration:
     - CoreML on Apple Silicon (M1/M2/M3/M4)
@@ -23,65 +26,81 @@ def get_available_providers() -> List[str]:
     - CPU as fallback (always available)
 
     Returns:
-        List[str]: Ordered list of execution providers to use
+        Ordered list of execution providers to use.
 
-    Examples:
+    Example:
         >>> providers = get_available_providers()
         >>> # On M4 Mac: ['CoreMLExecutionProvider', 'CPUExecutionProvider']
         >>> # On Linux with CUDA: ['CUDAExecutionProvider', 'CPUExecutionProvider']
-        >>> # On CPU-only: ['CPUExecutionProvider']
     """
     available = ort.get_available_providers()
     providers = []
 
     # Priority order: CoreML > CUDA > CPU
-    if "CoreMLExecutionProvider" in available:
-        providers.append("CoreMLExecutionProvider")
-        Logger.info("CoreML acceleration enabled (Apple Silicon)")
+    if 'CoreMLExecutionProvider' in available:
+        providers.append('CoreMLExecutionProvider')
+        Logger.info('CoreML acceleration enabled (Apple Silicon)')
 
-    if "CUDAExecutionProvider" in available:
-        providers.append("CUDAExecutionProvider")
-        Logger.info("CUDA acceleration enabled (NVIDIA GPU)")
+    if 'CUDAExecutionProvider' in available:
+        providers.append('CUDAExecutionProvider')
+        Logger.info('CUDA acceleration enabled (NVIDIA GPU)')
 
     # CPU is always available as fallback
-    providers.append("CPUExecutionProvider")
+    providers.append('CPUExecutionProvider')
 
     if len(providers) == 1:
-        Logger.info("Using CPU execution (no hardware acceleration detected)")
+        Logger.info('Using CPU execution (no hardware acceleration detected)')
 
     return providers
 
 
-def create_onnx_session(model_path: str, providers: List[str] = None) -> ort.InferenceSession:
-    """
-    Create an ONNX Runtime inference session with optimal provider selection.
+def create_onnx_session(
+    model_path: str,
+    providers: list[str] | None = None,
+) -> ort.InferenceSession:
+    """Create an ONNX Runtime inference session with optimal provider selection.
 
     Args:
-        model_path (str): Path to the ONNX model file
-        providers (List[str], optional): List of providers to use.
-            If None, automatically detects best available providers.
+        model_path: Path to the ONNX model file.
+        providers: List of execution providers to use. If None, automatically
+            detects best available providers.
 
     Returns:
-        ort.InferenceSession: Configured ONNX Runtime session
+        Configured ONNX Runtime session.
 
     Raises:
-        RuntimeError: If session creation fails
+        RuntimeError: If session creation fails.
 
-    Examples:
-        >>> session = create_onnx_session("model.onnx")
+    Example:
+        >>> session = create_onnx_session('model.onnx')
         >>> # Automatically uses best available providers
 
-        >>> session = create_onnx_session("model.onnx", providers=["CPUExecutionProvider"])
+        >>> session = create_onnx_session('model.onnx', providers=['CPUExecutionProvider'])
         >>> # Force CPU-only execution
     """
     if providers is None:
         providers = get_available_providers()
 
+    # Suppress ONNX Runtime warnings (e.g., CoreML partition warnings)
+    # Log levels: 0=VERBOSE, 1=INFO, 2=WARNING, 3=ERROR, 4=FATAL
+    sess_options = ort.SessionOptions()
+    sess_options.log_severity_level = 3  # Only show ERROR and FATAL
+
     try:
-        session = ort.InferenceSession(model_path, providers=providers)
+        session = ort.InferenceSession(model_path, sess_options=sess_options, providers=providers)
         active_provider = session.get_providers()[0]
-        Logger.debug(f"Session created with provider: {active_provider}")
+        Logger.debug(f'Session created with provider: {active_provider}')
+
+        # Show user-friendly message about which provider is being used
+        provider_names = {
+            'CoreMLExecutionProvider': 'CoreML (Apple Silicon)',
+            'CUDAExecutionProvider': 'CUDA (NVIDIA GPU)',
+            'CPUExecutionProvider': 'CPU',
+        }
+        provider_display = provider_names.get(active_provider, active_provider)
+        Logger.info(f'✓ Model loaded ({provider_display})')
+
         return session
     except Exception as e:
-        Logger.error(f"Failed to create ONNX session: {e}", exc_info=True)
-        raise RuntimeError(f"Failed to initialize ONNX Runtime session: {e}") from e
+        Logger.error(f'Failed to create ONNX session: {e}', exc_info=True)
+        raise RuntimeError(f'Failed to initialize ONNX Runtime session: {e}') from e

uniface/parsing/__init__.py

@@ -0,0 +1,52 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+from uniface.constants import ParsingWeights
+
+from .base import BaseFaceParser
+from .bisenet import BiSeNet
+
+__all__ = ['BaseFaceParser', 'BiSeNet', 'create_face_parser']
+
+
+def create_face_parser(
+    model_name: str | ParsingWeights = ParsingWeights.RESNET18,
+) -> BaseFaceParser:
+    """Factory function to create a face parsing model instance.
+
+    This function provides a convenient way to instantiate face parsing models
+    without directly importing the specific model classes.
+
+    Args:
+        model_name: The face parsing model to create. Can be either a string
+            or a ParsingWeights enum value. Available options:
+            - 'parsing_resnet18' or ParsingWeights.RESNET18 (default)
+            - 'parsing_resnet34' or ParsingWeights.RESNET34
+
+    Returns:
+        An instance of the requested face parsing model.
+
+    Raises:
+        ValueError: If the model_name is not recognized.
+
+    Example:
+        >>> from uniface.parsing import create_face_parser
+        >>> from uniface.constants import ParsingWeights
+        >>> parser = create_face_parser(ParsingWeights.RESNET18)
+        >>> mask = parser.parse(face_crop)
+    """
+    # Convert string to enum if necessary
+    if isinstance(model_name, str):
+        try:
+            model_name = ParsingWeights(model_name)
+        except ValueError as e:
+            valid_models = [e.value for e in ParsingWeights]
+            raise ValueError(
+                f"Unknown face parsing model: '{model_name}'. Valid options are: {', '.join(valid_models)}"
+            ) from e
+
+    # All parsing models use the same BiSeNet class
+    return BiSeNet(model_name=model_name)

uniface/parsing/base.py

@@ -0,0 +1,105 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from abc import ABC, abstractmethod
+
+import numpy as np
+
+
+class BaseFaceParser(ABC):
+    """
+    Abstract base class for all face parsing models.
+
+    This class defines the common interface that all face parsing models must implement,
+    ensuring consistency across different parsing methods. Face parsing segments a face
+    image into semantic regions such as skin, eyes, nose, mouth, hair, etc.
+
+    The output is a segmentation mask where each pixel is assigned a class label
+    representing a facial component.
+    """
+
+    @abstractmethod
+    def _initialize_model(self) -> None:
+        """
+        Initialize the underlying model for inference.
+
+        This method should handle loading model weights, creating the
+        inference session (e.g., ONNX Runtime), and any necessary
+        setup procedures to prepare the model for prediction.
+
+        Raises:
+            RuntimeError: If the model fails to load or initialize.
+        """
+        raise NotImplementedError('Subclasses must implement the _initialize_model method.')
+
+    @abstractmethod
+    def preprocess(self, face_image: np.ndarray) -> np.ndarray:
+        """
+        Preprocess the input face image for model inference.
+
+        This method should take a raw face crop and convert it into the format
+        expected by the model's inference engine (e.g., normalized tensor).
+
+        Args:
+            face_image (np.ndarray): A face image in BGR format with
+                                     shape (H, W, C).
+
+        Returns:
+            np.ndarray: The preprocessed image tensor ready for inference,
+                        typically with shape (1, C, H, W).
+        """
+        raise NotImplementedError('Subclasses must implement the preprocess method.')
+
+    @abstractmethod
+    def postprocess(self, outputs: np.ndarray, original_size: tuple[int, int]) -> np.ndarray:
+        """
+        Postprocess raw model outputs into a segmentation mask.
+
+        This method takes the raw output from the model's inference and
+        converts it into a segmentation mask at the original image size.
+
+        Args:
+            outputs (np.ndarray): Raw outputs from the model inference.
+            original_size (Tuple[int, int]): Original image size (width, height).
+
+        Returns:
+            np.ndarray: Segmentation mask with the same size as the original image.
+        """
+        raise NotImplementedError('Subclasses must implement the postprocess method.')
+
+    @abstractmethod
+    def parse(self, face_image: np.ndarray) -> np.ndarray:
+        """
+        Perform end-to-end face parsing on a face image.
+
+        This method orchestrates the full pipeline: preprocessing the input,
+        running inference, and postprocessing to return the segmentation mask.
+
+        Args:
+            face_image (np.ndarray): A face image in BGR format.
+                                     The face should be roughly centered and
+                                     well-framed within the image.
+
+        Returns:
+            np.ndarray: Segmentation mask with the same size as input image,
+                       where each pixel value represents a facial component class.
+
+        Example:
+            >>> parser = create_face_parser()
+            >>> mask = parser.parse(face_crop)
+            >>> print(f'Mask shape: {mask.shape}, unique classes: {np.unique(mask)}')
+        """
+        raise NotImplementedError('Subclasses must implement the parse method.')
+
+    def __call__(self, face_image: np.ndarray) -> np.ndarray:
+        """
+        Provides a convenient, callable shortcut for the `parse` method.
+
+        Args:
+            face_image (np.ndarray): A face image in BGR format.
+
+        Returns:
+            np.ndarray: Segmentation mask with the same size as input image.
+        """
+        return self.parse(face_image)

uniface/parsing/bisenet.py

@@ -0,0 +1,165 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+import cv2
+import numpy as np
+
+from uniface.constants import ParsingWeights
+from uniface.log import Logger
+from uniface.model_store import verify_model_weights
+from uniface.onnx_utils import create_onnx_session
+
+from .base import BaseFaceParser
+
+__all__ = ['BiSeNet']
+
+
+class BiSeNet(BaseFaceParser):
+    """
+    BiSeNet: Bilateral Segmentation Network for Face Parsing with ONNX Runtime.
+
+    BiSeNet is a semantic segmentation model that segments a face image into
+    different facial components such as skin, eyes, nose, mouth, hair, etc. The model
+    uses a BiSeNet architecture with ResNet backbone and outputs a segmentation mask
+    where each pixel is assigned a class label.
+
+    The model supports 19 facial component classes including:
+    - Background, skin, eyebrows, eyes, nose, mouth, lips, ears, hair, etc.
+
+    Reference:
+        https://github.com/yakhyo/face-parsing
+
+    Args:
+        model_name (ParsingWeights): The enum specifying the parsing model to load.
+            Options: RESNET18, RESNET34.
+            Defaults to `ParsingWeights.RESNET18`.
+        input_size (Tuple[int, int]): The resolution (width, height) for the model's
+            input. Defaults to (512, 512).
+
+    Attributes:
+        input_size (Tuple[int, int]): Model input dimensions.
+        input_mean (np.ndarray): Per-channel mean values for normalization (ImageNet).
+        input_std (np.ndarray): Per-channel std values for normalization (ImageNet).
+
+    Example:
+        >>> from uniface.parsing import BiSeNet
+        >>> from uniface import RetinaFace
+        >>>
+        >>> detector = RetinaFace()
+        >>> parser = BiSeNet()
+        >>>
+        >>> # Detect faces and parse each face
+        >>> faces = detector.detect(image)
+        >>> for face in faces:
+        ...     bbox = face.bbox
+        ...     x1, y1, x2, y2 = map(int, bbox[:4])
+        ...     face_crop = image[y1:y2, x1:x2]
+        ...     mask = parser.parse(face_crop)
+        ...     print(f'Mask shape: {mask.shape}, unique classes: {np.unique(mask)}')
+    """
+
+    def __init__(
+        self,
+        model_name: ParsingWeights = ParsingWeights.RESNET18,
+        input_size: tuple[int, int] = (512, 512),
+    ) -> None:
+        Logger.info(f'Initializing BiSeNet with model={model_name}, input_size={input_size}')
+
+        self.input_size = input_size
+        self.input_mean = np.array([0.485, 0.456, 0.406], dtype=np.float32)
+        self.input_std = np.array([0.229, 0.224, 0.225], dtype=np.float32)
+
+        self.model_path = verify_model_weights(model_name)
+        self._initialize_model()
+
+    def _initialize_model(self) -> None:
+        """
+        Initialize the ONNX model from the stored model path.
+
+        Raises:
+            RuntimeError: If the model fails to load or initialize.
+        """
+        try:
+            self.session = create_onnx_session(self.model_path)
+
+            # Get input configuration
+            input_cfg = self.session.get_inputs()[0]
+            input_shape = input_cfg.shape
+            self.input_name = input_cfg.name
+            self.input_size = tuple(input_shape[2:4][::-1])  # Update from model
+
+            # Get output configuration
+            outputs = self.session.get_outputs()
+            self.output_names = [output.name for output in outputs]
+
+            Logger.info(f'BiSeNet initialized with input size {self.input_size}')
+
+        except Exception as e:
+            Logger.error(f"Failed to load parsing model from '{self.model_path}'", exc_info=True)
+            raise RuntimeError(f'Failed to initialize parsing model: {e}') from e
+
+    def preprocess(self, face_image: np.ndarray) -> np.ndarray:
+        """
+        Preprocess a face image for parsing.
+
+        Args:
+            face_image (np.ndarray): A face image in BGR format.
+
+        Returns:
+            np.ndarray: Preprocessed image tensor with shape (1, 3, H, W).
+        """
+        # Convert BGR to RGB
+        image = cv2.cvtColor(face_image, cv2.COLOR_BGR2RGB)
+
+        # Resize to model input size
+        image = cv2.resize(image, self.input_size, interpolation=cv2.INTER_LINEAR)
+
+        # Normalize to [0, 1] and apply normalization
+        image = image.astype(np.float32) / 255.0
+        image = (image - self.input_mean) / self.input_std
+
+        # HWC -> CHW -> NCHW
+        image = np.transpose(image, (2, 0, 1))
+        image = np.expand_dims(image, axis=0).astype(np.float32)
+
+        return image
+
+    def postprocess(self, outputs: np.ndarray, original_size: tuple[int, int]) -> np.ndarray:
+        """
+        Postprocess model output to segmentation mask.
+
+        Args:
+            outputs (np.ndarray): Raw model output.
+            original_size (Tuple[int, int]): Original image size (width, height).
+
+        Returns:
+            np.ndarray: Segmentation mask resized to original dimensions.
+        """
+        # Get the class with highest probability for each pixel
+        predicted_mask = outputs.squeeze(0).argmax(0).astype(np.uint8)
+
+        # Resize back to original size
+        restored_mask = cv2.resize(predicted_mask, original_size, interpolation=cv2.INTER_NEAREST)
+
+        return restored_mask
+
+    def parse(self, face_image: np.ndarray) -> np.ndarray:
+        """
+        Perform end-to-end face parsing on a face image.
+
+        This method orchestrates the full pipeline: preprocessing the input,
+        running inference, and postprocessing to return the segmentation mask.
+
+        Args:
+            face_image (np.ndarray): A face image in BGR format.
+
+        Returns:
+            np.ndarray: Segmentation mask with the same size as input image.
+        """
+        original_size = (face_image.shape[1], face_image.shape[0])  # (width, height)
+        input_tensor = self.preprocess(face_image)
+        outputs = self.session.run(self.output_names, {self.input_name: input_tensor})
+
+        return self.postprocess(outputs[0], original_size)

uniface/privacy/__init__.py

@@ -0,0 +1,52 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+import numpy as np
+
+from .blur import BlurFace
+
+
+def anonymize_faces(
+    image: np.ndarray,
+    detector: object | None = None,
+    method: str = 'pixelate',
+    blur_strength: float = 3.0,
+    pixel_blocks: int = 10,
+    confidence_threshold: float = 0.5,
+    **kwargs,
+) -> np.ndarray:
+    """One-line face anonymization with automatic detection.
+
+    Args:
+        image (np.ndarray): Input image (BGR format).
+        detector: Face detector instance. Creates RetinaFace if None.
+        method (str): Blur method name. Defaults to 'pixelate'.
+        blur_strength (float): Blur intensity. Defaults to 3.0.
+        pixel_blocks (int): Block count for pixelate. Defaults to 10.
+        confidence_threshold (float): Detection confidence threshold. Defaults to 0.5.
+        **kwargs: Additional detector arguments.
+
+    Returns:
+        np.ndarray: Anonymized image.
+
+    Example:
+        >>> from uniface.privacy import anonymize_faces
+        >>> anonymized = anonymize_faces(image, method='pixelate')
+    """
+    if detector is None:
+        try:
+            from uniface import RetinaFace
+
+            detector = RetinaFace(confidence_threshold=confidence_threshold, **kwargs)
+        except ImportError as err:
+            raise ImportError('Could not import RetinaFace. Please ensure UniFace is properly installed.') from err
+
+    faces = detector.detect(image)
+    blurrer = BlurFace(method=method, blur_strength=blur_strength, pixel_blocks=pixel_blocks)
+    return blurrer.anonymize(image, faces)
+
+
+__all__ = ['BlurFace', 'anonymize_faces']

uniface/privacy/blur.py

@@ -0,0 +1,200 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, ClassVar
+
+import cv2
+import numpy as np
+
+if TYPE_CHECKING:
+    pass
+
+__all__ = ['BlurFace', 'EllipticalBlur']
+
+
+def _gaussian_blur(region: np.ndarray, strength: float = 3.0) -> np.ndarray:
+    """Apply Gaussian blur to a region."""
+    h, w = region.shape[:2]
+    kernel_size = max(3, int((min(h, w) / 7) * strength)) | 1
+    return cv2.GaussianBlur(region, (kernel_size, kernel_size), 0)
+
+
+def _median_blur(region: np.ndarray, strength: float = 3.0) -> np.ndarray:
+    """Apply median blur to a region."""
+    h, w = region.shape[:2]
+    kernel_size = max(3, int((min(h, w) / 7) * strength)) | 1
+    return cv2.medianBlur(region, kernel_size)
+
+
+def _pixelate_blur(region: np.ndarray, blocks: int = 10) -> np.ndarray:
+    """Apply pixelation to a region."""
+    h, w = region.shape[:2]
+    temp_h, temp_w = max(1, h // blocks), max(1, w // blocks)
+    temp = cv2.resize(region, (temp_w, temp_h), interpolation=cv2.INTER_LINEAR)
+    return cv2.resize(temp, (w, h), interpolation=cv2.INTER_NEAREST)
+
+
+def _blackout_blur(region: np.ndarray, color: tuple[int, int, int] = (0, 0, 0)) -> np.ndarray:
+    """Replace region with solid color."""
+    return np.full_like(region, color)
+
+
+class EllipticalBlur:
+    """Elliptical blur with soft, feathered edges.
+
+    This blur applies Gaussian blur within an elliptical mask that follows
+    the natural oval shape of faces, requiring full image context for proper blending.
+
+    Args:
+        blur_strength (float): Blur intensity multiplier. Defaults to 3.0.
+        margin (int): Extra pixels to extend ellipse beyond bbox. Defaults to 20.
+    """
+
+    def __init__(self, blur_strength: float = 3.0, margin: int = 20):
+        self.blur_strength = blur_strength
+        self.margin = margin
+
+    def __call__(
+        self,
+        image: np.ndarray,
+        bboxes: list[tuple | list],
+        inplace: bool = False,
+    ) -> np.ndarray:
+        if not inplace:
+            image = image.copy()
+
+        h, w = image.shape[:2]
+
+        for bbox in bboxes:
+            x1, y1, x2, y2 = map(int, bbox)
+            center_x, center_y = (x1 + x2) // 2, (y1 + y2) // 2
+            axes_x = (x2 - x1) // 2 + self.margin
+            axes_y = (y2 - y1) // 2 + self.margin
+
+            # Create soft elliptical mask
+            mask = np.zeros((h, w), dtype=np.float32)
+            cv2.ellipse(mask, (center_x, center_y), (axes_x, axes_y), 0, 0, 360, 255, -1)
+            mask = cv2.GaussianBlur(mask, (51, 51), 0) / 255.0
+            mask = mask[:, :, np.newaxis]
+
+            kernel_size = max(3, int((min(axes_y, axes_x) * 2 / 7) * self.blur_strength)) | 1
+            blurred = cv2.GaussianBlur(image, (kernel_size, kernel_size), 0)
+            image = (blurred * mask + image * (1 - mask)).astype(np.uint8)
+
+        return image
+
+
+class BlurFace:
+    """Face blurring with multiple anonymization methods.
+
+    Args:
+        method (str): Blur method - 'gaussian', 'pixelate', 'blackout', 'elliptical', or 'median'.
+            Defaults to 'pixelate'.
+        blur_strength (float): Intensity for gaussian/elliptical/median. Defaults to 3.0.
+        pixel_blocks (int): Block count for pixelate. Defaults to 10.
+        color (Tuple[int, int, int]): Fill color (BGR) for blackout. Defaults to (0, 0, 0).
+        margin (int): Edge margin for elliptical. Defaults to 20.
+
+    Example:
+        >>> blurrer = BlurFace(method='pixelate')
+        >>> anonymized = blurrer.anonymize(image, faces)
+    """
+
+    VALID_METHODS: ClassVar[set[str]] = {'gaussian', 'pixelate', 'blackout', 'elliptical', 'median'}
+
+    def __init__(
+        self,
+        method: str = 'pixelate',
+        blur_strength: float = 3.0,
+        pixel_blocks: int = 15,
+        color: tuple[int, int, int] = (0, 0, 0),
+        margin: int = 20,
+    ):
+        self.method = method.lower()
+        self._blur_strength = blur_strength
+        self._pixel_blocks = pixel_blocks
+        self._color = color
+        self._margin = margin
+
+        if self.method not in self.VALID_METHODS:
+            raise ValueError(f"Invalid blur method: '{method}'. Choose from: {sorted(self.VALID_METHODS)}")
+
+        if self.method == 'elliptical':
+            self._elliptical = EllipticalBlur(blur_strength, margin)
+
+    def _blur_region(self, region: np.ndarray) -> np.ndarray:
+        """Apply blur to a single region based on the configured method."""
+        if self.method == 'gaussian':
+            return _gaussian_blur(region, self._blur_strength)
+        elif self.method == 'median':
+            return _median_blur(region, self._blur_strength)
+        elif self.method == 'pixelate':
+            return _pixelate_blur(region, self._pixel_blocks)
+        elif self.method == 'blackout':
+            return _blackout_blur(region, self._color)
+        return region  # Fallback (should not reach here)
+
+    def anonymize(
+        self,
+        image: np.ndarray,
+        faces: list,
+        inplace: bool = False,
+    ) -> np.ndarray:
+        """Anonymize faces in an image.
+
+        Args:
+            image (np.ndarray): Input image (BGR format).
+            faces (List[Dict]): Face detections with 'bbox' key containing [x1, y1, x2, y2].
+            inplace (bool): Modify image in-place if True. Defaults to False.
+
+        Returns:
+            np.ndarray: Image with anonymized faces.
+        """
+        if not faces:
+            return image if inplace else image.copy()
+
+        bboxes = [face.bbox for face in faces]
+        return self.blur_regions(image, bboxes, inplace)
+
+    def blur_regions(
+        self,
+        image: np.ndarray,
+        bboxes: list[tuple | list],
+        inplace: bool = False,
+    ) -> np.ndarray:
+        """Blur specific rectangular regions in an image.
+
+        Args:
+            image (np.ndarray): Input image (BGR format).
+            bboxes (List): Bounding boxes as [x1, y1, x2, y2].
+            inplace (bool): Modify image in-place if True. Defaults to False.
+
+        Returns:
+            np.ndarray: Image with blurred regions.
+        """
+        if not bboxes:
+            return image if inplace else image.copy()
+
+        if self.method == 'elliptical':
+            return self._elliptical(image, bboxes, inplace)
+
+        if not inplace:
+            image = image.copy()
+
+        h, w = image.shape[:2]
+
+        for bbox in bboxes:
+            x1, y1, x2, y2 = map(int, bbox)
+            x1, y1 = max(0, x1), max(0, y1)
+            x2, y2 = min(w, x2), min(h, y2)
+
+            if x2 > x1 and y2 > y1:
+                image[y1:y2, x1:x2] = self._blur_region(image[y1:y2, x1:x2])
+
+        return image
+
+    def __repr__(self) -> str:
+        return f"BlurFace(method='{self.method}')"

uniface/recognition/__init__.py

@@ -2,10 +2,10 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from typing import Dict
-from .models import ArcFace, MobileFace, SphereFace
+
 from .base import BaseRecognizer
-from uniface.constants import ArcFaceWeights, MobileFaceWeights, SphereFaceWeights
+from .models import ArcFace, MobileFace, SphereFace
+
 
 def create_recognizer(method: str = 'arcface', **kwargs) -> BaseRecognizer:
     """
@@ -34,10 +34,7 @@ def create_recognizer(method: str = 'arcface', **kwargs) -> BaseRecognizer:
 
         >>> # Create a specific MobileFace recognizer
         >>> from uniface.constants import MobileFaceWeights
-        >>> recognizer = create_recognizer(
-        ...     'mobileface',
-        ...     model_name=MobileFaceWeights.MNET_V2
-        ... )
+        >>> recognizer = create_recognizer('mobileface', model_name=MobileFaceWeights.MNET_V2)
 
         >>> # Create a SphereFace recognizer
         >>> recognizer = create_recognizer('sphereface')
@@ -54,10 +51,5 @@ def create_recognizer(method: str = 'arcface', **kwargs) -> BaseRecognizer:
         available = ['arcface', 'mobileface', 'sphereface']
         raise ValueError(f"Unsupported method: '{method}'. Available: {available}")
 
-__all__ = [
-    "create_recognizer",
-    "ArcFace",
-    "MobileFace",
-    "SphereFace",
-    "BaseRecognizer",
-]
+
+__all__ = ['ArcFace', 'BaseRecognizer', 'MobileFace', 'SphereFace', 'create_recognizer']

uniface/recognition/base.py

@@ -2,25 +2,34 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from __future__ import annotations
+
 from abc import ABC, abstractmethod
+from dataclasses import dataclass
+
 import cv2
 import numpy as np
-from dataclasses import dataclass
-from typing import Tuple, Union, List
 
-from uniface.log import Logger
 from uniface.face_utils import face_alignment
+from uniface.log import Logger
 from uniface.onnx_utils import create_onnx_session
 
+__all__ = ['BaseRecognizer', 'PreprocessConfig']
+
 
 @dataclass
 class PreprocessConfig:
+    """Configuration for preprocessing images before feeding them into the model.
+
+    Attributes:
+        input_mean: Mean value(s) for normalization.
+        input_std: Standard deviation value(s) for normalization.
+        input_size: Target image size as (height, width).
     """
-    Configuration for preprocessing images before feeding them into the model.
-    """
-    input_mean: Union[float, List[float]] = 127.5
-    input_std: Union[float, List[float]] = 127.5
-    input_size: Tuple[int, int] = (112, 112)
+
+    input_mean: float | list[float] = 127.5
+    input_std: float | list[float] = 127.5
+    input_size: tuple[int, int] = (112, 112)
 
 
 class BaseRecognizer(ABC):
@@ -28,6 +37,7 @@ class BaseRecognizer(ABC):
     Abstract Base Class for all face recognition models.
     It provides the core functionality for preprocessing, inference, and embedding extraction.
     """
+
     @abstractmethod
     def __init__(self, model_path: str, preprocessing: PreprocessConfig) -> None:
         """
@@ -63,17 +73,20 @@ class BaseRecognizer(ABC):
             input_shape = input_cfg.shape
             model_input_size = tuple(input_shape[2:4][::-1])  # (width, height)
             if model_input_size != self.input_size:
-                Logger.warning(f"Model input size {model_input_size} differs from configured size {self.input_size}")
+                Logger.warning(f'Model input size {model_input_size} differs from configured size {self.input_size}')
 
             # Extract output configuration
             self.output_names = [output.name for output in self.session.get_outputs()]
             self.output_shape = self.session.get_outputs()[0].shape
 
-            assert len(self.output_names) == 1, "Expected only one output node."
-            Logger.info(f"Successfully initialized face encoder from {self.model_path}")
+            assert len(self.output_names) == 1, 'Expected only one output node.'
+            Logger.info(f'Successfully initialized face encoder from {self.model_path}')
 
         except Exception as e:
-            Logger.error(f"Failed to load face encoder model from '{self.model_path}'", exc_info=True)
+            Logger.error(
+                f"Failed to load face encoder model from '{self.model_path}'",
+                exc_info=True,
+            )
             raise RuntimeError(f"Failed to initialize model session for '{self.model_path}'") from e
 
     def preprocess(self, face_img: np.ndarray) -> np.ndarray:
@@ -88,11 +101,12 @@ class BaseRecognizer(ABC):
         """
         resized_img = cv2.resize(face_img, self.input_size)
 
-        if isinstance(self.input_std, (list, tuple)):
+        if isinstance(self.input_std, list | tuple):
             # Per-channel normalization
             rgb_img = cv2.cvtColor(resized_img, cv2.COLOR_BGR2RGB).astype(np.float32)
-            normalized_img = (rgb_img - np.array(self.input_mean, dtype=np.float32)) / \
-                np.array(self.input_std, dtype=np.float32)
+            normalized_img = (rgb_img - np.array(self.input_mean, dtype=np.float32)) / np.array(
+                self.input_std, dtype=np.float32
+            )
 
             # Change to NCHW (batch, channels, height, width)
             blob = np.transpose(normalized_img, (2, 0, 1))  # CHW
@@ -104,18 +118,19 @@ class BaseRecognizer(ABC):
                 scalefactor=1.0 / self.input_std,
                 size=self.input_size,
                 mean=(self.input_mean, self.input_mean, self.input_mean),
-                swapRB=True  # Convert BGR to RGB
+                swapRB=True,  # Convert BGR to RGB
             )
 
         return blob
 
-    def get_embedding(self, image: np.ndarray, landmarks: np.ndarray = None) -> np.ndarray:
-        """
-        Extracts face embedding from an image.
+    def get_embedding(self, image: np.ndarray, landmarks: np.ndarray | None = None) -> np.ndarray:
+        """Extract face embedding from an image.
 
         Args:
-            image: Input face image (BGR format). If already aligned (112x112), landmarks can be None.
-            landmarks: Facial landmarks (5 points for alignment). Optional if image is already aligned.
+            image: Input face image in BGR format. If already aligned (112x112),
+                landmarks can be None.
+            landmarks: Facial landmarks (5 points for alignment). Optional if
+                image is already aligned.
 
         Returns:
             Face embedding vector (typically 512-dimensional).
@@ -134,16 +149,27 @@ class BaseRecognizer(ABC):
         return embedding
 
     def get_normalized_embedding(self, image: np.ndarray, landmarks: np.ndarray) -> np.ndarray:
-        """
-        Extracts a l2 normalized face embedding vector from an image.
+        """Extract an L2-normalized face embedding vector from an image.
 
         Args:
-            image: Input face image (BGR format).
+            image: Input face image in BGR format.
             landmarks: Facial landmarks (5 points for alignment).
 
         Returns:
-            Normalized face embedding vector (typically 512-dimensional).
+            L2-normalized face embedding vector (typically 512-dimensional).
         """
         embedding = self.get_embedding(image, landmarks)
         norm = np.linalg.norm(embedding)
         return embedding / norm if norm > 0 else embedding
+
+    def __call__(self, image: np.ndarray, landmarks: np.ndarray) -> np.ndarray:
+        """Callable shortcut for the `get_normalized_embedding` method.
+
+        Args:
+            image: Input face image in BGR format.
+            landmarks: Facial landmarks (5 points for alignment).
+
+        Returns:
+            L2-normalized face embedding vector (typically 512-dimensional).
+        """
+        return self.get_normalized_embedding(image, landmarks)

uniface/recognition/models.py

@@ -2,13 +2,14 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from typing import Optional
+from __future__ import annotations
 
 from uniface.constants import ArcFaceWeights, MobileFaceWeights, SphereFaceWeights
 from uniface.model_store import verify_model_weights
+
 from .base import BaseRecognizer, PreprocessConfig
 
-__all__ = ["ArcFace", "MobileFace", "SphereFace"]
+__all__ = ['ArcFace', 'MobileFace', 'SphereFace']
 
 
 class ArcFace(BaseRecognizer):
@@ -33,14 +34,10 @@ class ArcFace(BaseRecognizer):
     def __init__(
         self,
         model_name: ArcFaceWeights = ArcFaceWeights.MNET,
-        preprocessing: Optional[PreprocessConfig] = None
+        preprocessing: PreprocessConfig | None = None,
     ) -> None:
         if preprocessing is None:
-            preprocessing = PreprocessConfig(
-                input_mean=127.5,
-                input_std=127.5,
-                input_size=(112, 112)
-            )
+            preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
         model_path = verify_model_weights(model_name)
         super().__init__(model_path=model_path, preprocessing=preprocessing)
 
@@ -67,14 +64,10 @@ class MobileFace(BaseRecognizer):
     def __init__(
         self,
         model_name: MobileFaceWeights = MobileFaceWeights.MNET_V2,
-        preprocessing: Optional[PreprocessConfig] = None
+        preprocessing: PreprocessConfig | None = None,
     ) -> None:
         if preprocessing is None:
-            preprocessing = PreprocessConfig(
-                input_mean=127.5,
-                input_std=127.5,
-                input_size=(112, 112)
-            )
+            preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
         model_path = verify_model_weights(model_name)
         super().__init__(model_path=model_path, preprocessing=preprocessing)
 
@@ -101,14 +94,10 @@ class SphereFace(BaseRecognizer):
     def __init__(
         self,
         model_name: SphereFaceWeights = SphereFaceWeights.SPHERE20,
-        preprocessing: Optional[PreprocessConfig] = None
+        preprocessing: PreprocessConfig | None = None,
     ) -> None:
         if preprocessing is None:
-            preprocessing = PreprocessConfig(
-                input_mean=127.5,
-                input_std=127.5,
-                input_size=(112, 112)
-            )
+            preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
 
         model_path = verify_model_weights(model_name)
         super().__init__(model_path=model_path, preprocessing=preprocessing)

uniface/spoofing/__init__.py

@@ -0,0 +1,47 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+from uniface.constants import MiniFASNetWeights
+from uniface.types import SpoofingResult
+
+from .base import BaseSpoofer
+from .minifasnet import MiniFASNet
+
+__all__ = [
+    'BaseSpoofer',
+    'MiniFASNet',
+    'MiniFASNetWeights',
+    'SpoofingResult',
+    'create_spoofer',
+]
+
+
+def create_spoofer(
+    model_name: MiniFASNetWeights = MiniFASNetWeights.V2,
+    scale: float | None = None,
+) -> MiniFASNet:
+    """Factory function to create a face anti-spoofing model.
+
+    This is a convenience function that creates a MiniFASNet instance
+    with the specified model variant and optional custom scale.
+
+    Args:
+        model_name: The model variant to use. Options:
+            - MiniFASNetWeights.V2: Improved version (default), uses scale=2.7
+            - MiniFASNetWeights.V1SE: Squeeze-and-excitation version, uses scale=4.0
+        scale: Custom crop scale factor for face region. If None, uses the
+            default scale for the selected model variant.
+
+    Returns:
+        An initialized face anti-spoofing model.
+
+    Example:
+        >>> from uniface.spoofing import create_spoofer, MiniFASNetWeights
+        >>> spoofer = create_spoofer()
+        >>> result = spoofer.predict(image, face.bbox)
+        >>> print(f'Is real: {result.is_real}, Confidence: {result.confidence:.2%}')
+    """
+    return MiniFASNet(model_name=model_name, scale=scale)

uniface/spoofing/base.py

@@ -0,0 +1,112 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+import numpy as np
+
+from uniface.types import SpoofingResult
+
+__all__ = ['BaseSpoofer', 'SpoofingResult']
+
+
+class BaseSpoofer(ABC):
+    """
+    Abstract base class for all face anti-spoofing models.
+
+    This class defines the common interface that all anti-spoofing models must implement,
+    ensuring consistency across different spoofing detection methods. Anti-spoofing models
+    detect whether a face is real (live person) or fake (photo, video, mask, etc.).
+    """
+
+    @abstractmethod
+    def _initialize_model(self) -> None:
+        """
+        Initialize the underlying model for inference.
+
+        This method should handle loading model weights, creating the
+        inference session (e.g., ONNX Runtime), and any necessary
+        setup procedures to prepare the model for prediction.
+
+        Raises:
+            RuntimeError: If the model fails to load or initialize.
+        """
+        raise NotImplementedError('Subclasses must implement the _initialize_model method.')
+
+    @abstractmethod
+    def preprocess(self, image: np.ndarray, bbox: list | np.ndarray) -> np.ndarray:
+        """
+        Preprocess the input image for model inference.
+
+        This method should crop the face region using the bounding box,
+        resize it to the model's expected input size, and normalize
+        the pixel values as required by the model.
+
+        Args:
+            image (np.ndarray): Input image in BGR format with shape (H, W, C).
+            bbox (Union[List, np.ndarray]): Face bounding box in [x1, y1, x2, y2] format.
+
+        Returns:
+            np.ndarray: The preprocessed image tensor ready for inference,
+                        typically with shape (1, C, H, W).
+        """
+        raise NotImplementedError('Subclasses must implement the preprocess method.')
+
+    @abstractmethod
+    def postprocess(self, outputs: np.ndarray) -> SpoofingResult:
+        """
+        Postprocess raw model outputs into prediction result.
+
+        This method takes the raw output from the model's inference and
+        converts it into a SpoofingResult.
+
+        Args:
+            outputs (np.ndarray): Raw outputs from the model inference (logits).
+
+        Returns:
+            SpoofingResult: Result containing is_real flag and confidence score.
+        """
+        raise NotImplementedError('Subclasses must implement the postprocess method.')
+
+    @abstractmethod
+    def predict(self, image: np.ndarray, bbox: list | np.ndarray) -> SpoofingResult:
+        """
+        Perform end-to-end anti-spoofing prediction on a face.
+
+        This method orchestrates the full pipeline: preprocessing the input,
+        running inference, and postprocessing to return the prediction.
+
+        Args:
+            image (np.ndarray): Input image in BGR format containing the face.
+            bbox (Union[List, np.ndarray]): Face bounding box in [x1, y1, x2, y2] format.
+                This is typically obtained from a face detector.
+
+        Returns:
+            SpoofingResult: Result containing is_real flag and confidence score.
+
+        Example:
+            >>> spoofer = MiniFASNet()
+            >>> detector = RetinaFace()
+            >>> faces = detector.detect(image)
+            >>> for face in faces:
+            ...     result = spoofer.predict(image, face.bbox)
+            ...     label = 'Real' if result.is_real else 'Fake'
+            ...     print(f'{label}: {result.confidence:.2%}')
+        """
+        raise NotImplementedError('Subclasses must implement the predict method.')
+
+    def __call__(self, image: np.ndarray, bbox: list | np.ndarray) -> SpoofingResult:
+        """
+        Provides a convenient, callable shortcut for the `predict` method.
+
+        Args:
+            image (np.ndarray): Input image in BGR format.
+            bbox (Union[List, np.ndarray]): Face bounding box in [x1, y1, x2, y2] format.
+
+        Returns:
+            SpoofingResult: Result containing is_real flag and confidence score.
+        """
+        return self.predict(image, bbox)

uniface/spoofing/minifasnet.py

@@ -0,0 +1,220 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+import cv2
+import numpy as np
+
+from uniface.constants import MiniFASNetWeights
+from uniface.log import Logger
+from uniface.model_store import verify_model_weights
+from uniface.onnx_utils import create_onnx_session
+from uniface.types import SpoofingResult
+
+from .base import BaseSpoofer
+
+__all__ = ['MiniFASNet']
+
+# Default crop scales for each model variant
+DEFAULT_SCALES = {
+    MiniFASNetWeights.V1SE: 4.0,
+    MiniFASNetWeights.V2: 2.7,
+}
+
+
+class MiniFASNet(BaseSpoofer):
+    """
+    MiniFASNet: Lightweight Face Anti-Spoofing with ONNX Runtime.
+
+    MiniFASNet is a face anti-spoofing model that detects whether a face is real
+    (live person) or fake (photo, video replay, mask, etc.). It supports two model
+    variants: V1SE (with squeeze-and-excitation) and V2 (improved version).
+
+    The model takes a face region cropped from the image using a bounding box
+    and predicts whether it's a real or spoofed face.
+
+    Reference:
+        https://github.com/yakhyo/face-anti-spoofing
+
+    Args:
+        model_name (MiniFASNetWeights): The enum specifying the model variant to load.
+            Options: V1SE (scale=4.0), V2 (scale=2.7).
+            Defaults to `MiniFASNetWeights.V2`.
+        scale (Optional[float]): Custom crop scale factor for face region.
+            If None, uses the default scale for the selected model variant.
+            V1SE uses 4.0, V2 uses 2.7.
+
+    Attributes:
+        scale (float): Crop scale factor for face region extraction.
+        input_size (Tuple[int, int]): Model input dimensions (width, height).
+
+    Example:
+        >>> from uniface.spoofing import MiniFASNet
+        >>> from uniface import RetinaFace
+        >>>
+        >>> detector = RetinaFace()
+        >>> spoofer = MiniFASNet()
+        >>>
+        >>> # Detect faces and check if they are real
+        >>> faces = detector.detect(image)
+        >>> for face in faces:
+        ...     result = spoofer.predict(image, face.bbox)
+        ...     label = 'Real' if result.is_real else 'Fake'
+        ...     print(f'{label}: {result.confidence:.2%}')
+    """
+
+    def __init__(
+        self,
+        model_name: MiniFASNetWeights = MiniFASNetWeights.V2,
+        scale: float | None = None,
+    ) -> None:
+        Logger.info(f'Initializing MiniFASNet with model={model_name.name}')
+
+        # Use default scale for the model variant if not specified
+        self.scale = scale if scale is not None else DEFAULT_SCALES.get(model_name, 2.7)
+
+        self.model_path = verify_model_weights(model_name)
+        self._initialize_model()
+
+    def _initialize_model(self) -> None:
+        """
+        Initialize the ONNX model from the stored model path.
+
+        Raises:
+            RuntimeError: If the model fails to load or initialize.
+        """
+        try:
+            self.session = create_onnx_session(self.model_path)
+
+            # Get input configuration
+            input_cfg = self.session.get_inputs()[0]
+            self.input_name = input_cfg.name
+            # Input shape is (batch, channels, height, width) - we need (width, height)
+            self.input_size = tuple(input_cfg.shape[2:4][::-1])  # (width, height)
+
+            # Get output configuration
+            output_cfg = self.session.get_outputs()[0]
+            self.output_name = output_cfg.name
+
+            Logger.info(f'MiniFASNet initialized with input size {self.input_size}, scale={self.scale}')
+
+        except Exception as e:
+            Logger.error(f"Failed to load MiniFASNet model from '{self.model_path}'", exc_info=True)
+            raise RuntimeError(f'Failed to initialize MiniFASNet model: {e}') from e
+
+    def _xyxy_to_xywh(self, bbox: list | np.ndarray) -> list[int]:
+        """Convert bounding box from [x1, y1, x2, y2] to [x, y, w, h] format."""
+        x1, y1, x2, y2 = bbox[:4]
+        return [int(x1), int(y1), int(x2 - x1), int(y2 - y1)]
+
+    def _crop_face(self, image: np.ndarray, bbox_xywh: list[int]) -> np.ndarray:
+        """
+        Crop and resize face region from image using scale factor.
+
+        The crop is centered on the face bounding box and scaled to capture
+        more context around the face, which is important for anti-spoofing.
+
+        Args:
+            image: Input image in BGR format.
+            bbox_xywh: Face bounding box in [x, y, w, h] format.
+
+        Returns:
+            Cropped and resized face region.
+        """
+        src_h, src_w = image.shape[:2]
+        x, y, box_w, box_h = bbox_xywh
+
+        # Calculate the scale to apply based on image and face size
+        scale = min((src_h - 1) / box_h, (src_w - 1) / box_w, self.scale)
+        new_w = box_w * scale
+        new_h = box_h * scale
+
+        # Calculate center of the bounding box
+        center_x = x + box_w / 2
+        center_y = y + box_h / 2
+
+        # Calculate new bounding box coordinates
+        x1 = max(0, int(center_x - new_w / 2))
+        y1 = max(0, int(center_y - new_h / 2))
+        x2 = min(src_w - 1, int(center_x + new_w / 2))
+        y2 = min(src_h - 1, int(center_y + new_h / 2))
+
+        # Crop and resize
+        cropped = image[y1 : y2 + 1, x1 : x2 + 1]
+        resized = cv2.resize(cropped, self.input_size)
+
+        return resized
+
+    def preprocess(self, image: np.ndarray, bbox: list | np.ndarray) -> np.ndarray:
+        """
+        Preprocess the input image for model inference.
+
+        Crops the face region, converts to float32, and arranges
+        dimensions for the model (NCHW format).
+
+        Args:
+            image: Input image in BGR format with shape (H, W, C).
+            bbox: Face bounding box in [x1, y1, x2, y2] format.
+
+        Returns:
+            Preprocessed image tensor with shape (1, C, H, W).
+        """
+        # Convert bbox format
+        bbox_xywh = self._xyxy_to_xywh(bbox)
+
+        # Crop and resize face region
+        face = self._crop_face(image, bbox_xywh)
+
+        # Convert to float32 (no normalization needed for this model)
+        face = face.astype(np.float32)
+
+        # HWC -> CHW -> NCHW
+        face = np.transpose(face, (2, 0, 1))
+        face = np.expand_dims(face, axis=0)
+
+        return face
+
+    def _softmax(self, x: np.ndarray) -> np.ndarray:
+        """Apply softmax to logits along axis 1."""
+        e_x = np.exp(x - np.max(x, axis=1, keepdims=True))
+        return e_x / e_x.sum(axis=1, keepdims=True)
+
+    def postprocess(self, outputs: np.ndarray) -> SpoofingResult:
+        """
+        Postprocess raw model outputs into prediction result.
+
+        Applies softmax to convert logits to probabilities and
+        returns the SpoofingResult with is_real flag and confidence score.
+
+        Args:
+            outputs: Raw outputs from the model inference (logits).
+
+        Returns:
+            SpoofingResult: Result containing is_real flag and confidence score.
+        """
+        probs = self._softmax(outputs)
+        label_idx = int(np.argmax(probs))
+        confidence = float(probs[0, label_idx])
+
+        return SpoofingResult(is_real=(label_idx == 1), confidence=confidence)
+
+    def predict(self, image: np.ndarray, bbox: list | np.ndarray) -> SpoofingResult:
+        """
+        Perform end-to-end anti-spoofing prediction on a face.
+
+        Args:
+            image: Input image in BGR format containing the face.
+            bbox: Face bounding box in [x1, y1, x2, y2] format.
+
+        Returns:
+            SpoofingResult: Result containing is_real flag and confidence score.
+        """
+        # Preprocess
+        input_tensor = self.preprocess(image, bbox)
+
+        # Run inference
+        outputs = self.session.run([self.output_name], {self.input_name: input_tensor})[0]
+
+        # Postprocess and return
+        return self.postprocess(outputs)

uniface/types.py

@@ -0,0 +1,216 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Unified type definitions for UniFace.
+
+This module centralizes all result dataclasses used across the library,
+providing consistent and immutable return types for model predictions.
+
+Note on mutability:
+- Result dataclasses (GazeResult, SpoofingResult, EmotionResult, AttributeResult)
+  are frozen (immutable) since they represent computation outputs that shouldn't change.
+- Face dataclass is mutable because FaceAnalyzer enriches it with additional
+  attributes (embedding, age, gender, etc.) after initial detection.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, fields
+
+import numpy as np
+
+from uniface.face_utils import compute_similarity
+
+__all__ = [
+    'AttributeResult',
+    'EmotionResult',
+    'Face',
+    'GazeResult',
+    'SpoofingResult',
+]
+
+
+@dataclass(slots=True, frozen=True)
+class GazeResult:
+    """Result of gaze estimation.
+
+    Attributes:
+        pitch: Vertical gaze angle in radians (positive = up, negative = down).
+        yaw: Horizontal gaze angle in radians (positive = right, negative = left).
+    """
+
+    pitch: float
+    yaw: float
+
+    def __repr__(self) -> str:
+        return f'GazeResult(pitch={self.pitch:.4f}, yaw={self.yaw:.4f})'
+
+
+@dataclass(slots=True, frozen=True)
+class SpoofingResult:
+    """Result of face anti-spoofing detection.
+
+    Attributes:
+        is_real: True if the face is real/live, False if fake/spoof.
+        confidence: Confidence score for the prediction (0.0 to 1.0).
+    """
+
+    is_real: bool
+    confidence: float
+
+    def __repr__(self) -> str:
+        label = 'Real' if self.is_real else 'Fake'
+        return f'SpoofingResult({label}, confidence={self.confidence:.4f})'
+
+
+@dataclass(slots=True, frozen=True)
+class EmotionResult:
+    """Result of emotion recognition.
+
+    Attributes:
+        emotion: Predicted emotion label (e.g., 'Happy', 'Sad', 'Angry').
+        confidence: Confidence score for the prediction (0.0 to 1.0).
+    """
+
+    emotion: str
+    confidence: float
+
+    def __repr__(self) -> str:
+        return f"EmotionResult('{self.emotion}', confidence={self.confidence:.4f})"
+
+
+@dataclass(slots=True, frozen=True)
+class AttributeResult:
+    """Unified result structure for face attribute prediction.
+
+    This dataclass provides a consistent return type across different attribute
+    prediction models (e.g., AgeGender, FairFace), enabling interoperability
+    and unified handling of results.
+
+    Attributes:
+        gender: Predicted gender (0=Female, 1=Male).
+        age: Exact age in years. Provided by AgeGender model, None for FairFace.
+        age_group: Age range string like "20-29". Provided by FairFace, None for AgeGender.
+        race: Race/ethnicity label. Provided by FairFace only.
+
+    Properties:
+        sex: Gender as a human-readable string ("Female" or "Male").
+
+    Examples:
+        >>> # AgeGender result
+        >>> result = AttributeResult(gender=1, age=25)
+        >>> result.sex
+        'Male'
+
+        >>> # FairFace result
+        >>> result = AttributeResult(gender=0, age_group='20-29', race='East Asian')
+        >>> result.sex
+        'Female'
+    """
+
+    gender: int
+    age: int | None = None
+    age_group: str | None = None
+    race: str | None = None
+
+    @property
+    def sex(self) -> str:
+        """Get gender as a string label (Female or Male)."""
+        return 'Female' if self.gender == 0 else 'Male'
+
+    def __repr__(self) -> str:
+        parts = [f'gender={self.sex}']
+        if self.age is not None:
+            parts.append(f'age={self.age}')
+        if self.age_group is not None:
+            parts.append(f'age_group={self.age_group}')
+        if self.race is not None:
+            parts.append(f'race={self.race}')
+        return f'AttributeResult({", ".join(parts)})'
+
+
+@dataclass(slots=True)
+class Face:
+    """Detected face with analysis results.
+
+    This dataclass represents a single detected face along with optional
+    analysis results such as embeddings, age, gender, and race predictions.
+
+    Note: This dataclass is mutable (not frozen) because FaceAnalyzer enriches
+    Face objects with additional attributes after initial detection.
+
+    Attributes:
+        bbox: Bounding box coordinates [x1, y1, x2, y2].
+        confidence: Detection confidence score.
+        landmarks: Facial landmark coordinates (typically 5 points).
+        embedding: Face embedding vector for recognition (optional).
+        gender: Predicted gender, 0=Female, 1=Male (optional).
+        age: Predicted exact age in years (optional, from AgeGender model).
+        age_group: Predicted age range like "20-29" (optional, from FairFace).
+        race: Predicted race/ethnicity (optional, from FairFace).
+        emotion: Predicted emotion label (optional, from Emotion model).
+        emotion_confidence: Confidence score for emotion prediction (optional).
+
+    Properties:
+        sex: Gender as a human-readable string ("Female" or "Male").
+        bbox_xyxy: Bounding box in (x1, y1, x2, y2) format.
+        bbox_xywh: Bounding box in (x1, y1, width, height) format.
+    """
+
+    # Required attributes (from detection)
+    bbox: np.ndarray
+    confidence: float
+    landmarks: np.ndarray
+
+    # Optional attributes (enriched by analyzers)
+    embedding: np.ndarray | None = None
+    gender: int | None = None
+    age: int | None = None
+    age_group: str | None = None
+    race: str | None = None
+    emotion: str | None = None
+    emotion_confidence: float | None = None
+
+    def compute_similarity(self, other: Face) -> float:
+        """Compute cosine similarity with another face."""
+        if self.embedding is None or other.embedding is None:
+            raise ValueError('Both faces must have embeddings for similarity computation')
+        return float(compute_similarity(self.embedding, other.embedding))
+
+    def to_dict(self) -> dict:
+        """Convert to dictionary."""
+        return {f.name: getattr(self, f.name) for f in fields(self)}
+
+    @property
+    def sex(self) -> str | None:
+        """Get gender as a string label (Female or Male)."""
+        if self.gender is None:
+            return None
+        return 'Female' if self.gender == 0 else 'Male'
+
+    @property
+    def bbox_xyxy(self) -> np.ndarray:
+        """Get bounding box coordinates in (x1, y1, x2, y2) format."""
+        return self.bbox.copy()
+
+    @property
+    def bbox_xywh(self) -> np.ndarray:
+        """Get bounding box coordinates in (x1, y1, w, h) format."""
+        return np.array([self.bbox[0], self.bbox[1], self.bbox[2] - self.bbox[0], self.bbox[3] - self.bbox[1]])
+
+    def __repr__(self) -> str:
+        parts = [f'Face(confidence={self.confidence:.3f}']
+        if self.age is not None:
+            parts.append(f'age={self.age}')
+        if self.age_group is not None:
+            parts.append(f'age_group={self.age_group}')
+        if self.gender is not None:
+            parts.append(f'sex={self.sex}')
+        if self.race is not None:
+            parts.append(f'race={self.race}')
+        if self.emotion is not None:
+            parts.append(f'emotion={self.emotion}')
+        if self.embedding is not None:
+            parts.append(f'embedding_dim={self.embedding.shape[0]}')
+        return ', '.join(parts) + ')'

uniface/visualization.py

@@ -2,49 +2,340 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+"""Visualization utilities for UniFace.
+
+This module provides functions for drawing detection results, gaze directions,
+and face parsing segmentation maps on images.
+"""
+
+from __future__ import annotations
+
 import cv2
 import numpy as np
-from typing import List, Union
+
+__all__ = [
+    'FACE_PARSING_COLORS',
+    'FACE_PARSING_LABELS',
+    'draw_detections',
+    'draw_fancy_bbox',
+    'draw_gaze',
+    'vis_parsing_maps',
+]
+
+# Face parsing component names (19 classes)
+FACE_PARSING_LABELS = [
+    'background',
+    'skin',
+    'l_brow',
+    'r_brow',
+    'l_eye',
+    'r_eye',
+    'eye_g',
+    'l_ear',
+    'r_ear',
+    'ear_r',
+    'nose',
+    'mouth',
+    'u_lip',
+    'l_lip',
+    'neck',
+    'neck_l',
+    'cloth',
+    'hair',
+    'hat',
+]
+
+# Color palette for face parsing visualization
+FACE_PARSING_COLORS = [
+    [0, 0, 0],
+    [255, 85, 0],
+    [255, 170, 0],
+    [255, 0, 85],
+    [255, 0, 170],
+    [0, 255, 0],
+    [85, 255, 0],
+    [170, 255, 0],
+    [0, 255, 85],
+    [0, 255, 170],
+    [0, 0, 255],
+    [85, 0, 255],
+    [170, 0, 255],
+    [0, 85, 255],
+    [0, 170, 255],
+    [255, 255, 0],
+    [255, 255, 85],
+    [255, 255, 170],
+    [255, 0, 255],
+]
 
 
 def draw_detections(
+    *,
     image: np.ndarray,
-    bboxes: Union[np.ndarray, List[List[float]]],
-    scores: Union[np.ndarray, List[float]],
-    landmarks: Union[np.ndarray, List[List[List[float]]]],
-    vis_threshold: float = 0.6
-):
-    """
-    Draws bounding boxes, scores, and landmarks from separate lists onto an image.
+    bboxes: list[np.ndarray] | list[list[float]],
+    scores: np.ndarray | list[float],
+    landmarks: list[np.ndarray] | list[list[list[float]]],
+    vis_threshold: float = 0.6,
+    draw_score: bool = False,
+    fancy_bbox: bool = True,
+) -> None:
+    """Draw bounding boxes, landmarks, and optional scores on an image.
+
+    Modifies the image in-place.
 
     Args:
-        image (np.ndarray): The image to draw on.
-        bboxes (list or np.ndarray): A list of bounding boxes, e.g., [[x1,y1,x2,y2], ...].
-        scores (list or np.ndarray): A list of confidence scores.
-        landmarks (list or np.ndarray): A list of landmark sets, e.g., [[[x,y],...],...].
-        vis_threshold (float): Confidence threshold for filtering which detections to draw.
+        image: Input image to draw on (modified in-place).
+        bboxes: List of bounding boxes as [x1, y1, x2, y2].
+        scores: List of confidence scores.
+        landmarks: List of landmark sets with shape (5, 2).
+        vis_threshold: Confidence threshold for filtering. Defaults to 0.6.
+        draw_score: Whether to draw confidence scores. Defaults to False.
+        fancy_bbox: Use corner-style bounding boxes. Defaults to True.
     """
-    _colors = [(0, 0, 255), (0, 255, 255), (255, 0, 255), (0, 255, 0), (255, 0, 0)]
+    colors = [(0, 0, 255), (0, 255, 255), (255, 0, 255), (0, 255, 0), (255, 0, 0)]
 
-    # Filter detections by score
+    # Calculate line thickness based on image size
+    line_thickness = max(round(sum(image.shape[:2]) / 2 * 0.003), 2)
+
+    # Filter detections by confidence threshold
     keep_indices = [i for i, score in enumerate(scores) if score >= vis_threshold]
 
-    # Draw the filtered detections
     for i in keep_indices:
         bbox = np.array(bboxes[i], dtype=np.int32)
         score = scores[i]
         landmark_set = np.array(landmarks[i], dtype=np.int32)
 
-        # Calculate adaptive thickness
-        thickness = max(1, int(min(bbox[2] - bbox[0], bbox[3] - bbox[1]) / 100))
+        # Calculate dynamic font scale based on bbox height
+        bbox_h = bbox[3] - bbox[1]
+        font_scale = max(0.4, min(0.7, bbox_h / 200))
+        font_thickness = 2
 
         # Draw bounding box
-        cv2.rectangle(image, tuple(bbox[:2]), tuple(bbox[2:]), (0, 0, 255), thickness)
+        if fancy_bbox:
+            draw_fancy_bbox(image, bbox, color=(0, 255, 0), thickness=line_thickness, proportion=0.2)
+        else:
+            cv2.rectangle(image, tuple(bbox[:2]), tuple(bbox[2:]), (0, 255, 0), line_thickness)
 
-        # Draw score
-        cv2.putText(image, f"{score:.2f}", (bbox[0], bbox[1] - 10),
-                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), thickness)
+        # Draw confidence score with background
+        if draw_score:
+            text = f'{score:.2f}'
+            (text_width, text_height), baseline = cv2.getTextSize(
+                text, cv2.FONT_HERSHEY_SIMPLEX, font_scale, font_thickness
+            )
+
+            # Draw background rectangle
+            cv2.rectangle(
+                image,
+                (bbox[0], bbox[1] - text_height - baseline - 10),
+                (bbox[0] + text_width + 10, bbox[1]),
+                (0, 255, 0),
+                -1,
+            )
+
+            # Draw text
+            cv2.putText(
+                image,
+                text,
+                (bbox[0] + 5, bbox[1] - 5),
+                cv2.FONT_HERSHEY_SIMPLEX,
+                font_scale,
+                (0, 0, 0),
+                font_thickness,
+            )
 
         # Draw landmarks
         for j, point in enumerate(landmark_set):
-            cv2.circle(image, tuple(point), thickness + 1, _colors[j], -1)
+            cv2.circle(image, tuple(point), line_thickness + 1, colors[j], -1)
+
+
+def draw_fancy_bbox(
+    image: np.ndarray,
+    bbox: np.ndarray,
+    color: tuple[int, int, int] = (0, 255, 0),
+    thickness: int = 3,
+    proportion: float = 0.2,
+) -> None:
+    """Draw a bounding box with fancy corners on an image.
+
+    Args:
+        image: Input image to draw on (modified in-place).
+        bbox: Bounding box coordinates [x1, y1, x2, y2].
+        color: Color of the bounding box in BGR. Defaults to green.
+        thickness: Thickness of the corner lines. Defaults to 3.
+        proportion: Proportion of corner length to box dimensions. Defaults to 0.2.
+    """
+    x1, y1, x2, y2 = map(int, bbox)
+    width = x2 - x1
+    height = y2 - y1
+
+    corner_length = int(proportion * min(width, height))
+
+    # Draw the rectangle
+    cv2.rectangle(image, (x1, y1), (x2, y2), color, 1)
+
+    # Top-left corner
+    cv2.line(image, (x1, y1), (x1 + corner_length, y1), color, thickness)
+    cv2.line(image, (x1, y1), (x1, y1 + corner_length), color, thickness)
+
+    # Top-right corner
+    cv2.line(image, (x2, y1), (x2 - corner_length, y1), color, thickness)
+    cv2.line(image, (x2, y1), (x2, y1 + corner_length), color, thickness)
+
+    # Bottom-left corner
+    cv2.line(image, (x1, y2), (x1, y2 - corner_length), color, thickness)
+    cv2.line(image, (x1, y2), (x1 + corner_length, y2), color, thickness)
+
+    # Bottom-right corner
+    cv2.line(image, (x2, y2), (x2, y2 - corner_length), color, thickness)
+    cv2.line(image, (x2, y2), (x2 - corner_length, y2), color, thickness)
+
+
+def draw_gaze(
+    image: np.ndarray,
+    bbox: np.ndarray,
+    pitch: np.ndarray | float,
+    yaw: np.ndarray | float,
+    *,
+    draw_bbox: bool = True,
+    fancy_bbox: bool = True,
+    draw_angles: bool = True,
+) -> None:
+    """Draw gaze direction with optional bounding box on an image.
+
+    Args:
+        image: Input image to draw on (modified in-place).
+        bbox: Face bounding box [x1, y1, x2, y2].
+        pitch: Vertical gaze angle in radians.
+        yaw: Horizontal gaze angle in radians.
+        draw_bbox: Whether to draw the bounding box. Defaults to True.
+        fancy_bbox: Use fancy corner-style bbox. Defaults to True.
+        draw_angles: Whether to display pitch/yaw values as text. Defaults to True.
+    """
+    x_min, y_min, x_max, y_max = map(int, bbox[:4])
+
+    # Calculate dynamic line thickness based on image size (same as draw_detections)
+    line_thickness = max(round(sum(image.shape[:2]) / 2 * 0.003), 2)
+
+    # Calculate dynamic font scale based on bbox height (same as draw_detections)
+    bbox_h = y_max - y_min
+    font_scale = max(0.4, min(0.7, bbox_h / 200))
+    font_thickness = 2
+
+    # Draw bounding box if requested
+    if draw_bbox:
+        if fancy_bbox:
+            draw_fancy_bbox(image, bbox, color=(0, 255, 0), thickness=line_thickness)
+        else:
+            cv2.rectangle(image, (x_min, y_min), (x_max, y_max), (0, 255, 0), line_thickness)
+
+    # Calculate center of the bounding box
+    x_center = (x_min + x_max) // 2
+    y_center = (y_min + y_max) // 2
+
+    # Calculate the direction of the gaze
+    length = x_max - x_min
+    dx = int(-length * np.sin(pitch) * np.cos(yaw))
+    dy = int(-length * np.sin(yaw))
+
+    point1 = (x_center, y_center)
+    point2 = (x_center + dx, y_center + dy)
+
+    # Calculate dynamic center point radius based on line thickness
+    center_radius = max(line_thickness + 1, 4)
+
+    # Draw gaze direction
+    cv2.circle(image, (x_center, y_center), radius=center_radius, color=(0, 0, 255), thickness=-1)
+    cv2.arrowedLine(
+        image,
+        point1,
+        point2,
+        color=(0, 0, 255),
+        thickness=line_thickness,
+        line_type=cv2.LINE_AA,
+        tipLength=0.25,
+    )
+
+    # Draw angle values
+    if draw_angles:
+        text = f'P:{np.degrees(pitch):.0f}deg Y:{np.degrees(yaw):.0f}deg'
+        (text_width, text_height), baseline = cv2.getTextSize(
+            text, cv2.FONT_HERSHEY_SIMPLEX, font_scale, font_thickness
+        )
+
+        # Draw background rectangle for text
+        cv2.rectangle(
+            image,
+            (x_min, y_min - text_height - baseline - 10),
+            (x_min + text_width + 10, y_min),
+            (0, 0, 255),
+            -1,
+        )
+
+        # Draw text
+        cv2.putText(
+            image,
+            text,
+            (x_min + 5, y_min - 5),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            font_scale,
+            (255, 255, 255),
+            font_thickness,
+        )
+
+
+def vis_parsing_maps(
+    image: np.ndarray,
+    segmentation_mask: np.ndarray,
+    *,
+    save_image: bool = False,
+    save_path: str = 'result.png',
+) -> np.ndarray:
+    """Visualize face parsing segmentation mask by overlaying colored regions.
+
+    Args:
+        image: Input face image in RGB format with shape (H, W, 3).
+        segmentation_mask: Segmentation mask with shape (H, W) where each pixel
+            value represents a facial component class (0-18).
+        save_image: Whether to save the visualization to disk. Defaults to False.
+        save_path: Path to save the visualization if save_image is True.
+
+    Returns:
+        Blended image with segmentation overlay in BGR format.
+
+    Example:
+        >>> import cv2
+        >>> from uniface.parsing import BiSeNet
+        >>> from uniface.visualization import vis_parsing_maps
+        >>> parser = BiSeNet()
+        >>> face_image = cv2.imread('face.jpg')
+        >>> mask = parser.parse(face_image)
+        >>> face_rgb = cv2.cvtColor(face_image, cv2.COLOR_BGR2RGB)
+        >>> result = vis_parsing_maps(face_rgb, mask)
+        >>> cv2.imwrite('parsed_face.jpg', result)
+    """
+    # Create numpy arrays for image and segmentation mask
+    image = np.array(image).copy().astype(np.uint8)
+    segmentation_mask = segmentation_mask.copy().astype(np.uint8)
+
+    # Create a color mask
+    segmentation_mask_color = np.zeros((segmentation_mask.shape[0], segmentation_mask.shape[1], 3))
+
+    num_classes = np.max(segmentation_mask)
+
+    for class_index in range(1, num_classes + 1):
+        class_pixels = np.where(segmentation_mask == class_index)
+        segmentation_mask_color[class_pixels[0], class_pixels[1], :] = FACE_PARSING_COLORS[class_index]
+
+    segmentation_mask_color = segmentation_mask_color.astype(np.uint8)
+
+    # Convert image to BGR format for blending
+    bgr_image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+
+    # Blend the image with the segmentation mask
+    blended_image = cv2.addWeighted(bgr_image, 0.6, segmentation_mask_color, 0.4, 0)
+
+    # Save the result if required
+    if save_image:
+        cv2.imwrite(save_path, blended_image, [int(cv2.IMWRITE_JPEG_QUALITY), 100])
+
+    return blended_image