fix: Cleaning up excessive comments

* release: Release UniFace version v3.1.0

* docs: Change classifiers to stable from beta

.github/workflows/build.yml

@@ -1,64 +0,0 @@
-name: Build, Test, and Publish
-
-on:
-  push:
-    branches:
-      - main
-    tags:
-      - "v*.*.*"  # Trigger publish on version tags
-  pull_request:
-    branches:
-      - main
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-
-    strategy:
-      matrix:
-        python-version: ["3.8", "3.9", "3.10"]
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install .[dev] || pip install pytest  # Use extras_require if available
-
-      - name: Run Tests
-        run: |
-          pytest
-
-  publish:
-    runs-on: ubuntu-latest
-    needs: build  # Publish only if tests pass
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v3
-
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.10"  # Use a single Python version for publishing
-
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install build twine
-
-      - name: Build Package
-        run: python -m build
-
-      - name: Publish to PyPI
-        env:
-          TWINE_USERNAME: __token__
-          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
-        run: twine upload dist/*

.github/workflows/ci.yml

@@ -0,0 +1,103 @@
+name: Build
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+      - uses: pre-commit/action@v3.0.1
+
+  test:
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 15
+    needs: lint
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          # Full Python range on Linux (fastest runner)
+          - os: ubuntu-latest
+            python-version: "3.10"
+          - os: ubuntu-latest
+            python-version: "3.13"
+          - os: macos-latest
+            python-version: "3.13"
+          - os: windows-latest
+            python-version: "3.13"
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[dev]
+
+      - name: Check ONNX Runtime providers
+        run: |
+          python -c "import onnxruntime as ort; print('Available providers:', ort.get_available_providers())"
+
+      - name: Run tests
+        run: pytest -v --tb=short
+
+      - name: Test package imports
+        run: python -c "import uniface; print(f'uniface {uniface.__version__} loaded with {len(uniface.__all__)} exports')"
+
+  build:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    needs: test
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "pip"
+
+      - name: Install build tools
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install build
+
+      - name: Build package
+        run: python -m build
+
+      - name: Check package
+        run: |
+          python -m pip install twine
+          twine check dist/*
+
+      - name: Upload build artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist-python-${{ github.sha }}
+          path: dist/
+          retention-days: 7

.github/workflows/docs.yml

@@ -0,0 +1,38 @@
+name: Deploy docs
+
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # Fetch full history for git-committers and git-revision-date plugins
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install mkdocs-material pymdown-extensions mkdocs-git-committers-plugin-2 mkdocs-git-revision-date-localized-plugin
+
+      - name: Build docs
+        env:
+          MKDOCS_GIT_COMMITTERS_APIKEY: ${{ secrets.MKDOCS_GIT_COMMITTERS_APIKEY }}
+        run: mkdocs build --strict
+
+      - name: Deploy to GitHub Pages
+        uses: peaceiris/actions-gh-pages@v4
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: ./site
+          destination_dir: docs

.github/workflows/publish.yml

@@ -0,0 +1,119 @@
+name: Publish to PyPI
+
+on:
+  push:
+    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: ${{ steps.get_version.outputs.tag_version }}
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"  # Needs 3.11+ for tomllib
+
+      - name: Get version from tag and pyproject.toml
+        id: get_version
+        run: |
+          TAG_VERSION=${GITHUB_REF#refs/tags/v}
+          echo "tag_version=$TAG_VERSION" >> $GITHUB_OUTPUT
+
+          PYPROJECT_VERSION=$(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"
+          echo "pyproject.toml version: $PYPROJECT_VERSION"
+
+      - name: Verify version match
+        run: |
+          if [ "${{ steps.get_version.outputs.tag_version }}" != "${{ steps.get_version.outputs.version }}" ]; then
+            echo "Error: Tag version (${{ steps.get_version.outputs.tag_version }}) does not match pyproject.toml version (${{ steps.get_version.outputs.version }})"
+            exit 1
+          fi
+          echo "Version validation passed: ${{ steps.get_version.outputs.version }}"
+
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    needs: validate
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.13"]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[dev]
+
+      - name: Run tests
+        run: pytest -v
+
+  publish:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    needs: [validate, test]
+    permissions:
+      contents: write
+      id-token: write
+    environment:
+      name: pypi
+      url: https://pypi.org/project/uniface/
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+          cache: 'pip'
+
+      - name: Install build tools
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install build twine
+
+      - name: Build package
+        run: python -m build
+
+      - name: Check package
+        run: twine check dist/*
+
+      - name: Publish to PyPI
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_API_TOKEN }}
+        run: twine upload dist/*
+
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@v1
+        with:
+          files: dist/*
+          generate_release_notes: true

.gitignore

@@ -1,3 +1,7 @@
+tmp_*
+.vscode/
+*.onnx
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

.pre-commit-config.yaml

@@ -0,0 +1,41 @@
+# 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
+        exclude: ^mkdocs.yml$
+      - 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:** 3.10+ (use modern syntax)
+- **Quote style:** Single quotes for strings, double quotes for docstrings
+
+#### Type Hints
+
+Use modern Python 3.10+ 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 create_detector(method: str = 'retinaface', **kwargs: Any) -> BaseDetector:
+    """Factory function to create face detectors.
+
+    Args:
+        method: Detection method. Options: 'retinaface', 'scrfd', 'yolov5face', 'yolov8face'.
+        **kwargs: Detector-specific parameters.
+
+    Returns:
+        Initialized detector instance.
+
+    Raises:
+        ValueError: If method is not supported.
+
+    Example:
+        >>> from uniface import create_detector
+        >>> detector = create_detector('retinaface', confidence_threshold=0.8)
+        >>> faces = detector.detect(image)
+        >>> 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.

README.md

@@ -1,239 +1,259 @@
-# UniFace: All-in-One Face Analysis Library
+<h1 align="center">UniFace: All-in-One Face Analysis Library</h1>
 
 <div align="center">
 
+[![PyPI Version](https://img.shields.io/pypi/v/uniface.svg?label=Version)](https://pypi.org/project/uniface/)
+[![Python Version](https://img.shields.io/badge/Python-3.10%2B-blue)](https://www.python.org/)
 [![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
-![Python](https://img.shields.io/badge/Python-3.8%2B-blue)
-[![PyPI Version](https://img.shields.io/pypi/v/uniface.svg)](https://pypi.org/project/uniface/)
-[![Build Status](https://github.com/yakhyo/uniface/actions/workflows/build.yml/badge.svg)](https://github.com/yakhyo/uniface/actions)
-[![Downloads](https://pepy.tech/badge/uniface)](https://pepy.tech/project/uniface)
-[![Code Style: PEP8](https://img.shields.io/badge/code%20style-PEP8-green.svg)](https://www.python.org/dev/peps/pep-0008/)
-[![GitHub Release Downloads](https://img.shields.io/github/downloads/yakhyo/uniface/total.svg?label=Model%20Downloads)](https://github.com/yakhyo/uniface/releases)
+[![Github Build Status](https://github.com/yakhyo/uniface/actions/workflows/ci.yml/badge.svg)](https://github.com/yakhyo/uniface/actions)
+[![PyPI Downloads](https://static.pepy.tech/personalized-badge/uniface?period=total&units=INTERNATIONAL_SYSTEM&left_color=GRAY&right_color=BLUE&left_text=Downloads)](https://pepy.tech/projects/uniface)
+[![UniFace Documentation](https://img.shields.io/badge/Docs-UniFace-blue.svg)](https://yakhyo.github.io/uniface/)
+[![Kaggle Badge](https://img.shields.io/badge/Notebooks-Kaggle?label=Kaggle&color=blue)](https://www.kaggle.com/yakhyokhuja/code)
+[![Discord](https://img.shields.io/badge/Discord-Join%20Server-5865F2?logo=discord&logoColor=white)](https://discord.gg/wdzrjr7R5j)
 
 </div>
 
-**uniface** is a lightweight face detection library designed for high-performance face localization and landmark detection. The library supports ONNX models and provides utilities for bounding box visualization and landmark plotting. To train RetinaFace model, see https://github.com/yakhyo/retinaface-pytorch.
+<div align="center">
+    <img src="https://raw.githubusercontent.com/yakhyo/uniface/main/.github/logos/uniface_rounded_q80.webp" width="90%" alt="UniFace - All-in-One Open-Source Face Analysis Library">
+</div>
+
+---
+
+**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
-- [ ] Age and gender detection (Planned).
-- [ ] Face recognition (Planned).
-- [x] High-speed face detection using ONNX models (Added: 2024-11-20).
-- [x] Accurate facial landmark localization (e.g., eyes, nose, and mouth) (Added: 2024-11-20).
-- [x] Easy-to-use API for inference and visualization (Added: 2024-11-20).
+
+- **Face Detection** — RetinaFace, SCRFD, YOLOv5-Face, and YOLOv8-Face with 5-point landmarks
+- **Face Recognition** — ArcFace, MobileFace, and SphereFace embeddings
+- **Face Tracking** — Multi-object tracking with [BYTETracker](https://github.com/yakhyo/bytetrack-tracker) for persistent IDs across video frames
+- **Facial Landmarks** — 106-point landmark localization module (separate from 5-point detector landmarks)
+- **Face Parsing** — BiSeNet semantic segmentation (19 classes), XSeg face masking
+- **Gaze Estimation** — Real-time gaze direction with MobileGaze
+- **Attribute Analysis** — Age, gender, race (FairFace), and emotion
+- **Vector Indexing** — FAISS-backed embedding store for fast multi-identity search
+- **Anti-Spoofing** — Face liveness detection with MiniFASNet
+- **Face Anonymization** — 5 blur methods for privacy protection
+- **Hardware Acceleration** — ARM64 (Apple Silicon), CUDA (NVIDIA), CPU
 
 ---
 
 ## Installation
 
-### Using pip
+**Standard installation**
 
 ```bash
 pip install uniface
 ```
 
-### Local installation using pip
+**GPU support (CUDA)**
 
-**Clone the repository**
+```bash
+pip install uniface[gpu]
+```
+
+**From source (latest version)**
 
 ```bash
 git clone https://github.com/yakhyo/uniface.git
-cd uniface
+cd uniface && pip install -e .
 ```
 
-**Install using pip**
+**FAISS vector indexing**
 
 ```bash
-pip install .
+pip install faiss-cpu   # or faiss-gpu for CUDA
+```
+
+**Optional dependencies**
+- Emotion model uses TorchScript and requires `torch`:
+  `pip install torch` (choose the correct build for your OS/CUDA)
+- YOLOv5-Face and YOLOv8-Face support faster NMS with `torchvision`:
+  `pip install torch torchvision` then use `nms_mode='torchvision'`
+
+---
+
+## Model Downloads and Cache
+
+Models are downloaded automatically on first use and verified via SHA-256.
+
+Default cache location: `~/.uniface/models`
+
+Override with the programmatic API or environment variable:
+
+```python
+from uniface.model_store import get_cache_dir, set_cache_dir
+
+set_cache_dir('/data/models')
+print(get_cache_dir())  # /data/models
+```
+
+```bash
+export UNIFACE_CACHE_DIR=/data/models
 ```
 
 ---
 
-## Quick Start
-
-### Initialize the Model
-
-```python
-from uniface import RetinaFace
-
-# Initialize the RetinaFace model
-uniface_inference = RetinaFace(
-    model="retinaface_mnet_v2",  # Model name
-    conf_thresh=0.5,             # Confidence threshold
-    pre_nms_topk=5000,           # Pre-NMS Top-K detections
-    nms_thresh=0.4,              # NMS IoU threshold
-    post_nms_topk=750            # Post-NMS Top-K detections
-)
-```
-
-### Run Inference
-
-Inference on image:
+## Quick Example (Detection)
 
 ```python
 import cv2
-from uniface.visualization import draw_detections
+from uniface.detection import RetinaFace
 
-# Load an image
-image_path = "assets/test.jpg"
-original_image = cv2.imread(image_path)
+detector = RetinaFace()
 
-# Perform inference
-boxes, landmarks = uniface_inference.detect(original_image)
+image = cv2.imread("photo.jpg")
+if image is None:
+    raise ValueError("Failed to load image. Check the path to 'photo.jpg'.")
 
-# Visualize results
-draw_detections(original_image, (boxes, landmarks), vis_threshold=0.6)
+faces = detector.detect(image)
 
-# Save the output image
-output_path = "output.jpg"
-cv2.imwrite(output_path, original_image)
-print(f"Saved output image to {output_path}")
+for face in faces:
+    print(f"Confidence: {face.confidence:.2f}")
+    print(f"BBox: {face.bbox}")
+    print(f"Landmarks: {face.landmarks.shape}")
 ```
 
-Inference on video:
+<div align="center">
+    <img src="https://raw.githubusercontent.com/yakhyo/uniface/main/assets/test_result.png" width="90%">
+    <p>Face Detection Model Output</p>
+</div>
+
+---
+
+## Example (Face Analyzer)
 
 ```python
 import cv2
-from uniface.visualization import draw_detections
+from uniface.analyzer import FaceAnalyzer
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
 
-# Initialize the webcam
-cap = cv2.VideoCapture(0)
+detector = RetinaFace()
+recognizer = ArcFace()
 
-if not cap.isOpened():
-    print("Error: Unable to access the webcam.")
-    exit()
+analyzer = FaceAnalyzer(detector, recognizer=recognizer)
 
-while True:
-    # Capture a frame from the webcam
-    ret, frame = cap.read()
-    if not ret:
-        print("Error: Failed to read frame.")
-        break
+image = cv2.imread("photo.jpg")
+if image is None:
+    raise ValueError("Failed to load image. Check the path to 'photo.jpg'.")
 
-    # Perform inference
-    boxes, landmarks = uniface_inference.detect(frame)
+faces = analyzer.analyze(image)
 
-    # Draw detections on the frame
-    draw_detections(frame, (boxes, landmarks), vis_threshold=0.6)
-
-    # Display the output
-    cv2.imshow("Webcam Inference", frame)
-
-    # Exit if 'q' is pressed
-    if cv2.waitKey(1) & 0xFF == ord('q'):
-        break
-
-# Release the webcam and close all OpenCV windows
-cap.release()
-cv2.destroyAllWindows()
+for face in faces:
+    print(face.bbox, face.embedding.shape if face.embedding is not None else None)
 ```
 
 ---
 
-### Evaluation results of available models on WiderFace
+## Execution Providers (ONNX Runtime)
 
-| RetinaFace Models  | Easy       | Medium     | Hard       |
-| ------------------ | ---------- | ---------- | ---------- |
-| retinaface_mnet025 | 88.48%     | 87.02%     | 80.61%     |
-| retinaface_mnet050 | 89.42%     | 87.97%     | 82.40%     |
-| retinaface_mnet_v1 | 90.59%     | 89.14%     | 84.13%     |
-| retinaface_mnet_v2 | 91.70%     | 91.03%     | 86.60%     |
-| retinaface_r18     | 92.50%     | 91.02%     | 86.63%     |
-| retinaface_r34     | **94.16%** | **93.12%** | **88.90%** |
-
-## API Reference
-
-### `RetinaFace` Class
-
-#### Initialization
 ```python
-RetinaFace(
-    model: str,
-    conf_thresh: float = 0.5,
-    pre_nms_topk: int = 5000,
-    nms_thresh: float = 0.4,
-    post_nms_topk: int = 750
-)
+from uniface.detection import RetinaFace
+
+# Force CPU-only inference
+detector = RetinaFace(providers=["CPUExecutionProvider"])
 ```
 
-**Parameters**:
-- `model` *(str)*: Name of the model to use. Supported models:
-  - `retinaface_mnet025`, `retinaface_mnet050`, `retinaface_mnet_v1`, `retinaface_mnet_v2`
-  - `retinaface_r18`, `retinaface_r34`
-- `conf_thresh` *(float, default=0.5)*: Minimum confidence score for detections.
-- `pre_nms_topk` *(int, default=5000)*: Max detections to keep before NMS.
-- `nms_thresh` *(float, default=0.4)*: IoU threshold for Non-Maximum Suppression.
-- `post_nms_topk` *(int, default=750)*: Max detections to keep after NMS.
+See more in the docs:
+https://yakhyo.github.io/uniface/concepts/execution-providers/
 
 ---
 
-### `detect` Method
-```python
-detect(
-    image: np.ndarray,
-    max_num: int = 0,
-    metric: str = "default",
-    center_weight: float = 2.0
-) -> Tuple[np.ndarray, np.ndarray]
-```
+## Documentation
 
-**Description**:
-Detects faces in the given image and returns bounding boxes and landmarks.
+Full documentation: https://yakhyo.github.io/uniface/
 
-**Parameters**:
-- `image` *(np.ndarray)*: Input image in BGR format.
-- `max_num` *(int, default=0)*: Maximum number of faces to return. `0` means return all.
-- `metric` *(str, default="default")*: Metric for prioritizing detections:
-  - `"default"`: Prioritize detections closer to the image center.
-  - `"max"`: Prioritize larger bounding box areas.
-- `center_weight` *(float, default=2.0)*: Weight for prioritizing center-aligned faces.
-
-**Returns**:
-- `bounding_boxes` *(np.ndarray)*: Array of detections as `[x_min, y_min, x_max, y_max, confidence]`.
-- `landmarks` *(np.ndarray)*: Array of landmarks as `[(x1, y1), ..., (x5, y5)]`.
+| Resource | Description |
+|----------|-------------|
+| [Quickstart](https://yakhyo.github.io/uniface/quickstart/) | Get up and running in 5 minutes |
+| [Model Zoo](https://yakhyo.github.io/uniface/models/) | All models, benchmarks, and selection guide |
+| [API Reference](https://yakhyo.github.io/uniface/modules/detection/) | Detailed module documentation |
+| [Tutorials](https://yakhyo.github.io/uniface/recipes/image-pipeline/) | Step-by-step workflow examples |
+| [Guides](https://yakhyo.github.io/uniface/concepts/overview/) | Architecture and design principles |
+| [Datasets](https://yakhyo.github.io/uniface/datasets/) | Training data and evaluation benchmarks |
 
 ---
 
-### Visualization Utilities
+## Datasets
 
-#### `draw_detections`
-```python
-draw_detections(
-    image: np.ndarray,
-    detections: Tuple[np.ndarray, np.ndarray],
-    vis_threshold: float
-) -> None
-```
+| Task | Training Dataset | Models |
+|------|-----------------|--------|
+| Detection | WIDER FACE | RetinaFace, SCRFD, YOLOv5-Face, YOLOv8-Face |
+| Recognition | MS1MV2 | MobileFace, SphereFace |
+| Recognition | WebFace600K | ArcFace |
+| Recognition | WebFace4M / 12M | AdaFace |
+| Gaze | Gaze360 | MobileGaze |
+| Parsing | CelebAMask-HQ | BiSeNet |
+| Attributes | CelebA, FairFace, AffectNet | AgeGender, FairFace, Emotion |
 
-**Description**:
-Draws bounding boxes and landmarks on the given image.
+> See [Datasets documentation](https://yakhyo.github.io/uniface/datasets/) for download links, benchmarks, and details.
 
-**Parameters**:
-- `image` *(np.ndarray)*: The input image in BGR format.
-- `detections` *(Tuple[np.ndarray, np.ndarray])*: A tuple of bounding boxes and landmarks.
-- `vis_threshold` *(float)*: Minimum confidence score for visualization.
+---
+
+## Jupyter Notebooks
+
+| Example | Colab | Description |
+|---------|:-----:|-------------|
+| [01_face_detection.ipynb](examples/01_face_detection.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/01_face_detection.ipynb) | Face detection and landmarks |
+| [02_face_alignment.ipynb](examples/02_face_alignment.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/02_face_alignment.ipynb) | Face alignment for recognition |
+| [03_face_verification.ipynb](examples/03_face_verification.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/03_face_verification.ipynb) | Compare faces for identity |
+| [04_face_search.ipynb](examples/04_face_search.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/04_face_search.ipynb) | Find a person in group photos |
+| [05_face_analyzer.ipynb](examples/05_face_analyzer.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/05_face_analyzer.ipynb) | All-in-one analysis |
+| [06_face_parsing.ipynb](examples/06_face_parsing.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/06_face_parsing.ipynb) | Semantic face segmentation |
+| [07_face_anonymization.ipynb](examples/07_face_anonymization.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/07_face_anonymization.ipynb) | Privacy-preserving blur |
+| [08_gaze_estimation.ipynb](examples/08_gaze_estimation.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/08_gaze_estimation.ipynb) | Gaze direction estimation |
+| [09_face_segmentation.ipynb](examples/09_face_segmentation.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/09_face_segmentation.ipynb) | Face segmentation with XSeg |
+| [10_face_vector_store.ipynb](examples/10_face_vector_store.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/10_face_vector_store.ipynb) | FAISS-backed face database |
+
+---
+
+## Licensing and Model Usage
+
+UniFace is MIT-licensed, but several pretrained models carry their own licenses.
+Review: https://yakhyo.github.io/uniface/license-attribution/
+
+Notable examples:
+- YOLOv5-Face and YOLOv8-Face weights are GPL-3.0
+- FairFace weights are CC BY 4.0
+
+If you plan commercial use, verify model license compatibility.
+
+---
+
+## References
+
+| Feature | Repository | Training | Description |
+|---------|------------|:--------:|-------------|
+| Detection | [retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch) | ✓ | RetinaFace PyTorch Training & Export |
+| Detection | [yolov5-face-onnx-inference](https://github.com/yakhyo/yolov5-face-onnx-inference) | - | YOLOv5-Face ONNX Inference |
+| Detection | [yolov8-face-onnx-inference](https://github.com/yakhyo/yolov8-face-onnx-inference) | - | YOLOv8-Face ONNX Inference |
+| Tracking | [bytetrack-tracker](https://github.com/yakhyo/bytetrack-tracker) | - | BYTETracker Multi-Object Tracking |
+| Recognition | [face-recognition](https://github.com/yakhyo/face-recognition) | ✓ | MobileFace, SphereFace Training |
+| Parsing | [face-parsing](https://github.com/yakhyo/face-parsing) | ✓ | BiSeNet Face Parsing |
+| Parsing | [face-segmentation](https://github.com/yakhyo/face-segmentation) | - | XSeg Face Segmentation |
+| Gaze | [gaze-estimation](https://github.com/yakhyo/gaze-estimation) | ✓ | MobileGaze Training |
+| Anti-Spoofing | [face-anti-spoofing](https://github.com/yakhyo/face-anti-spoofing) | - | MiniFASNet Inference |
+| Attributes | [fairface-onnx](https://github.com/yakhyo/fairface-onnx) | - | FairFace ONNX Inference |
+
+*SCRFD and ArcFace models are from [InsightFace](https://github.com/deepinsight/insightface).
 
 ---
 
 ## Contributing
 
-We welcome contributions to enhance the library! Feel free to:
+Contributions are welcome. Please see [CONTRIBUTING.md](CONTRIBUTING.md).
 
-- Submit bug reports or feature requests.
-- Fork the repository and create a pull request.
+## Support
 
----
+If you find this project useful, consider giving it a ⭐ on GitHub — it helps others discover it!
+
+Questions or feedback:
+- Discord: https://discord.gg/wdzrjr7R5j
+- GitHub Issues: https://github.com/yakhyo/uniface/issues
+- DeepWiki Q&A: https://deepwiki.com/yakhyo/uniface
 
 ## License
 
-This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
-
----
-
-## Acknowledgments
-
-- Based on the RetinaFace model for face detection ([https://github.com/yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch)).
-- Inspired by InsightFace and other face detection projects.
-
----
+This project is licensed under the [MIT License](LICENSE).

docs/concepts/coordinate-systems.md

@@ -0,0 +1,191 @@
+# Coordinate Systems
+
+This page explains the coordinate formats used in UniFace.
+
+---
+
+## Image Coordinates
+
+All coordinates use **pixel-based, top-left origin**:
+
+```
+(0, 0) ────────────────► x (width)
+   │
+   │    Image
+   │
+   ▼
+   y (height)
+```
+
+---
+
+## Bounding Box Format
+
+Bounding boxes use `[x1, y1, x2, y2]` format (top-left and bottom-right corners):
+
+```
+(x1, y1) ─────────────────┐
+    │                     │
+    │      Face           │
+    │                     │
+    └─────────────────────┘ (x2, y2)
+```
+
+### Accessing Coordinates
+
+```python
+face = faces[0]
+
+# Direct access
+x1, y1, x2, y2 = face.bbox
+
+# As properties
+bbox_xyxy = face.bbox_xyxy  # [x1, y1, x2, y2]
+bbox_xywh = face.bbox_xywh  # [x1, y1, width, height]
+```
+
+### Conversion
+
+```python
+import numpy as np
+
+# xyxy → xywh
+def xyxy_to_xywh(bbox):
+    x1, y1, x2, y2 = bbox
+    return np.array([x1, y1, x2 - x1, y2 - y1])
+
+# xywh → xyxy
+def xywh_to_xyxy(bbox):
+    x, y, w, h = bbox
+    return np.array([x, y, x + w, y + h])
+```
+
+---
+
+## Landmarks
+
+### 5-Point Landmarks (Detection)
+
+Returned by all detection models:
+
+```python
+landmarks = face.landmarks  # Shape: (5, 2)
+```
+
+| Index | Point |
+|-------|-------|
+| 0 | Left Eye |
+| 1 | Right Eye |
+| 2 | Nose Tip |
+| 3 | Left Mouth Corner |
+| 4 | Right Mouth Corner |
+
+```
+      0 ●           ● 1
+
+            ● 2
+
+        3 ●     ● 4
+```
+
+### 106-Point Landmarks
+
+Returned by `Landmark106`:
+
+```python
+from uniface.landmark import Landmark106
+
+landmarker = Landmark106()
+landmarks = landmarker.get_landmarks(image, face.bbox)
+# Shape: (106, 2)
+```
+
+**Landmark Groups:**
+
+| Range | Group | Points |
+|-------|-------|--------|
+| 0-32 | Face Contour | 33 |
+| 33-50 | Eyebrows | 18 |
+| 51-62 | Nose | 12 |
+| 63-86 | Eyes | 24 |
+| 87-105 | Mouth | 19 |
+
+---
+
+## Face Crop
+
+To crop a face from an image:
+
+```python
+def crop_face(image, bbox, margin=0):
+    """Crop face with optional margin."""
+    h, w = image.shape[:2]
+    x1, y1, x2, y2 = map(int, bbox)
+
+    # Add margin
+    if margin > 0:
+        bw, bh = x2 - x1, y2 - y1
+        x1 = max(0, x1 - int(bw * margin))
+        y1 = max(0, y1 - int(bh * margin))
+        x2 = min(w, x2 + int(bw * margin))
+        y2 = min(h, y2 + int(bh * margin))
+
+    return image[y1:y2, x1:x2]
+
+# Usage
+face_crop = crop_face(image, face.bbox, margin=0.1)
+```
+
+---
+
+## Gaze Angles
+
+Gaze estimation returns pitch and yaw in **radians**:
+
+```python
+result = gaze_estimator.estimate(face_crop)
+
+# Angles in radians
+pitch = result.pitch  # Vertical: + = up, - = down
+yaw = result.yaw      # Horizontal: + = right, - = left
+
+# Convert to degrees
+import numpy as np
+pitch_deg = np.degrees(pitch)
+yaw_deg = np.degrees(yaw)
+```
+
+**Angle Reference:**
+
+```
+          pitch = +90° (up)
+               │
+               │
+yaw = -90° ────┼──── yaw = +90°
+(left)         │      (right)
+               │
+          pitch = -90° (down)
+```
+
+---
+
+## Face Alignment
+
+Face alignment uses 5-point landmarks to normalize face orientation:
+
+```python
+from uniface.face_utils import face_alignment
+
+# Align face to standard template
+aligned_face = face_alignment(image, face.landmarks)
+# Output: 112x112 aligned face image
+```
+
+The alignment transforms faces to a canonical pose for better recognition accuracy.
+
+---
+
+## Next Steps
+
+- [Inputs & Outputs](inputs-outputs.md) - Data types reference
+- [Recognition Module](../modules/recognition.md) - Face recognition details

docs/concepts/execution-providers.md

@@ -0,0 +1,232 @@
+# Execution Providers
+
+UniFace uses ONNX Runtime for model inference, which supports multiple hardware acceleration backends.
+
+---
+
+## Automatic Provider Selection
+
+UniFace automatically selects the optimal execution provider based on available hardware:
+
+```python
+from uniface.detection import RetinaFace
+
+# Automatically uses best available provider
+detector = RetinaFace()
+```
+
+**Priority order:**
+
+1. **CoreMLExecutionProvider** - Apple Silicon
+2. **CUDAExecutionProvider** - NVIDIA GPU
+3. **CPUExecutionProvider** - Fallback
+
+---
+
+## Explicit Provider Selection
+
+You can specify which execution provider to use by passing the `providers` parameter:
+
+```python
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+
+# Force CPU execution (even if GPU is available)
+detector = RetinaFace(providers=['CPUExecutionProvider'])
+recognizer = ArcFace(providers=['CPUExecutionProvider'])
+
+# Use CUDA with CPU fallback
+detector = RetinaFace(providers=['CUDAExecutionProvider', 'CPUExecutionProvider'])
+```
+
+All model classes accept the `providers` parameter:
+
+- Detection: `RetinaFace`, `SCRFD`, `YOLOv5Face`, `YOLOv8Face`
+- Recognition: `ArcFace`, `AdaFace`, `MobileFace`, `SphereFace`
+- Landmarks: `Landmark106`
+- Gaze: `MobileGaze`
+- Parsing: `BiSeNet`
+- Attributes: `AgeGender`, `FairFace`
+- Anti-Spoofing: `MiniFASNet`
+
+---
+
+## Check Available Providers
+
+```python
+import onnxruntime as ort
+
+providers = ort.get_available_providers()
+print("Available providers:", providers)
+```
+
+**Example outputs:**
+
+=== "macOS (Apple Silicon)"
+
+    ```
+    ['CoreMLExecutionProvider', 'CPUExecutionProvider']
+    ```
+
+=== "Linux (NVIDIA GPU)"
+
+    ```
+    ['CUDAExecutionProvider', 'CPUExecutionProvider']
+    ```
+
+=== "Windows (CPU)"
+
+    ```
+    ['CPUExecutionProvider']
+    ```
+
+---
+
+## Platform-Specific Setup
+
+### Apple Silicon (M1/M2/M3/M4)
+
+No additional setup required. ARM64 optimizations are built into `onnxruntime`:
+
+```bash
+pip install uniface
+```
+
+Verify ARM64:
+
+```bash
+python -c "import platform; print(platform.machine())"
+# Should show: arm64
+```
+
+!!! tip "Performance"
+    Apple Silicon Macs use CoreML acceleration automatically, providing excellent performance for face analysis tasks.
+
+---
+
+### NVIDIA GPU (CUDA)
+
+Install with GPU support:
+
+```bash
+pip install uniface[gpu]
+```
+
+**Requirements:**
+
+- CUDA 11.x or 12.x
+- cuDNN 8.x
+- Compatible NVIDIA driver
+
+Verify CUDA:
+
+```python
+import onnxruntime as ort
+
+if 'CUDAExecutionProvider' in ort.get_available_providers():
+    print("CUDA is available!")
+else:
+    print("CUDA not available, using CPU")
+```
+
+---
+
+### CPU Fallback
+
+CPU execution is always available:
+
+```bash
+pip install uniface
+```
+
+Works on all platforms without additional configuration.
+
+---
+
+## Internal API
+
+For advanced use cases, you can access the provider utilities:
+
+```python
+from uniface.onnx_utils import get_available_providers, create_onnx_session
+
+# Check available providers
+providers = get_available_providers()
+print(f"Available: {providers}")
+
+# Models use create_onnx_session() internally
+# which auto-selects the best provider
+```
+
+---
+
+## Performance Tips
+
+### 1. Use GPU When Available
+
+For batch processing or real-time applications, GPU acceleration provides significant speedups:
+
+```bash
+pip install uniface[gpu]
+```
+
+### 2. Optimize Input Size
+
+Smaller input sizes are faster but may reduce accuracy:
+
+```python
+from uniface.detection import RetinaFace
+
+# Faster, lower accuracy
+detector = RetinaFace(input_size=(320, 320))
+
+# Balanced (default)
+detector = RetinaFace(input_size=(640, 640))
+```
+
+### 3. Batch Processing
+
+Process multiple images to maximize GPU utilization:
+
+```python
+# Process images in batch (GPU-efficient)
+for image_path in image_paths:
+    image = cv2.imread(image_path)
+    faces = detector.detect(image)
+    # ...
+```
+
+---
+
+## Troubleshooting
+
+### CUDA Not Detected
+
+1. Verify CUDA installation:
+   ```bash
+   nvidia-smi
+   ```
+
+2. Check CUDA version compatibility with ONNX Runtime
+
+3. Reinstall with GPU support:
+   ```bash
+   pip uninstall onnxruntime onnxruntime-gpu
+   pip install uniface[gpu]
+   ```
+
+### Slow Performance on Mac
+
+Verify you're using ARM64 Python (not Rosetta):
+
+```bash
+python -c "import platform; print(platform.machine())"
+# Should show: arm64 (not x86_64)
+```
+
+---
+
+## Next Steps
+
+- [Model Cache & Offline](model-cache-offline.md) - Model management
+- [Thresholds & Calibration](thresholds-calibration.md) - Tuning parameters

docs/concepts/inputs-outputs.md

@@ -0,0 +1,219 @@
+# Inputs & Outputs
+
+This page describes the data types used throughout UniFace.
+
+---
+
+## Input: Images
+
+All models accept NumPy arrays in **BGR format** (OpenCV default):
+
+```python
+import cv2
+
+# Load image (BGR format)
+image = cv2.imread("photo.jpg")
+print(f"Shape: {image.shape}")  # (H, W, 3)
+print(f"Dtype: {image.dtype}")  # uint8
+```
+
+!!! warning "Color Format"
+    UniFace expects **BGR** format (OpenCV default). If using PIL or other libraries, convert first:
+
+    ```python
+    from PIL import Image
+    import numpy as np
+
+    pil_image = Image.open("photo.jpg")
+    bgr_image = np.array(pil_image)[:, :, ::-1]  # RGB → BGR
+    ```
+
+---
+
+## Output: Face Dataclass
+
+Detection returns a list of `Face` objects:
+
+```python
+from dataclasses import dataclass
+import numpy as np
+
+@dataclass
+class Face:
+    # Required (from detection)
+    bbox: np.ndarray        # [x1, y1, x2, y2]
+    confidence: float       # 0.0 to 1.0
+    landmarks: np.ndarray   # (5, 2) or (106, 2)
+
+    # Optional (enriched by analyzers)
+    embedding: np.ndarray | None = None
+    gender: int | None = None           # 0=Female, 1=Male
+    age: int | None = None              # Years
+    age_group: str | None = None        # "20-29", etc.
+    race: str | None = None             # "East Asian", etc.
+    emotion: str | None = None          # "Happy", etc.
+    emotion_confidence: float | None = None
+    track_id: int | None = None         # Persistent ID from tracker
+```
+
+### Properties
+
+```python
+face = faces[0]
+
+# Bounding box formats
+face.bbox_xyxy  # [x1, y1, x2, y2] - same as bbox
+face.bbox_xywh  # [x1, y1, width, height]
+
+# Gender as string
+face.sex  # "Female" or "Male" (None if not predicted)
+```
+
+### Methods
+
+```python
+# Compute similarity with another face
+similarity = face1.compute_similarity(face2)
+
+# Convert to dictionary
+face_dict = face.to_dict()
+```
+
+---
+
+## Result Types
+
+### GazeResult
+
+```python
+from dataclasses import dataclass
+
+@dataclass(frozen=True)
+class GazeResult:
+    pitch: float  # Vertical angle (radians), + = up
+    yaw: float    # Horizontal angle (radians), + = right
+```
+
+**Usage:**
+
+```python
+import numpy as np
+
+result = gaze_estimator.estimate(face_crop)
+print(f"Pitch: {np.degrees(result.pitch):.1f}°")
+print(f"Yaw: {np.degrees(result.yaw):.1f}°")
+```
+
+---
+
+### SpoofingResult
+
+```python
+@dataclass(frozen=True)
+class SpoofingResult:
+    is_real: bool      # True = real, False = fake
+    confidence: float  # 0.0 to 1.0
+```
+
+**Usage:**
+
+```python
+result = spoofer.predict(image, face.bbox)
+label = "Real" if result.is_real else "Fake"
+print(f"{label}: {result.confidence:.1%}")
+```
+
+---
+
+### AttributeResult
+
+```python
+@dataclass(frozen=True)
+class AttributeResult:
+    gender: int              # 0=Female, 1=Male
+    age: int | None          # Years (AgeGender model)
+    age_group: str | None    # "20-29" (FairFace model)
+    race: str | None         # Race label (FairFace model)
+
+    @property
+    def sex(self) -> str:
+        return "Female" if self.gender == 0 else "Male"
+```
+
+**Usage:**
+
+```python
+# AgeGender model
+result = age_gender.predict(image, face.bbox)
+print(f"{result.sex}, {result.age} years old")
+
+# FairFace model
+result = fairface.predict(image, face.bbox)
+print(f"{result.sex}, {result.age_group}, {result.race}")
+```
+
+---
+
+### EmotionResult
+
+```python
+@dataclass(frozen=True)
+class EmotionResult:
+    emotion: str       # "Happy", "Sad", etc.
+    confidence: float  # 0.0 to 1.0
+```
+
+---
+
+## Embeddings
+
+Face recognition models return normalized 512-dimensional embeddings:
+
+```python
+embedding = recognizer.get_normalized_embedding(image, landmarks)
+print(f"Shape: {embedding.shape}")  # (1, 512)
+print(f"Norm: {np.linalg.norm(embedding):.4f}")  # ~1.0
+```
+
+### Similarity Computation
+
+```python
+from uniface.face_utils import compute_similarity
+
+similarity = compute_similarity(embedding1, embedding2)
+# Returns: float between -1 and 1 (cosine similarity)
+```
+
+---
+
+## Parsing Masks
+
+Face parsing returns a segmentation mask:
+
+```python
+mask = parser.parse(face_image)
+print(f"Shape: {mask.shape}")  # (H, W)
+print(f"Classes: {np.unique(mask)}")  # [0, 1, 2, ...]
+```
+
+**19 Classes:**
+
+| ID | Class | ID | Class |
+|----|-------|----|-------|
+| 0 | Background | 10 | Nose |
+| 1 | Skin | 11 | Mouth |
+| 2 | Left Eyebrow | 12 | Upper Lip |
+| 3 | Right Eyebrow | 13 | Lower Lip |
+| 4 | Left Eye | 14 | Neck |
+| 5 | Right Eye | 15 | Necklace |
+| 6 | Eyeglasses | 16 | Cloth |
+| 7 | Left Ear | 17 | Hair |
+| 8 | Right Ear | 18 | Hat |
+| 9 | Earring | | |
+
+---
+
+## Next Steps
+
+- [Coordinate Systems](coordinate-systems.md) - Bbox and landmark formats
+- [Thresholds & Calibration](thresholds-calibration.md) - Tuning confidence thresholds

docs/concepts/model-cache-offline.md

@@ -0,0 +1,262 @@
+# Model Cache & Offline Use
+
+UniFace automatically downloads and caches models. This page explains how model management works.
+
+---
+
+## Automatic Download
+
+Models are downloaded on first use:
+
+```python
+from uniface.detection import RetinaFace
+
+# First run: downloads model to cache
+detector = RetinaFace()  # ~3.5 MB download
+
+# Subsequent runs: loads from cache
+detector = RetinaFace()  # Instant
+```
+
+---
+
+## Cache Location
+
+Default cache directory:
+
+```
+~/.uniface/models/
+```
+
+**Example structure:**
+
+```
+~/.uniface/models/
+├── retinaface_mnet_v2.onnx
+├── arcface_mnet.onnx
+├── 2d_106.onnx
+├── gaze_resnet34.onnx
+├── parsing_resnet18.onnx
+└── ...
+```
+
+---
+
+## Custom Cache Directory
+
+Use the programmatic API to change the cache location at runtime:
+
+```python
+from uniface.model_store import get_cache_dir, set_cache_dir
+
+# Set a custom cache directory
+set_cache_dir('/data/models')
+
+# Verify the current path
+print(get_cache_dir())  # /data/models
+
+# All subsequent model loads use the new directory
+from uniface.detection import RetinaFace
+detector = RetinaFace()  # Downloads to /data/models/
+```
+
+Or set the `UNIFACE_CACHE_DIR` environment variable (see [Environment Variables](#environment-variables) below).
+
+---
+
+## Pre-Download Models
+
+Download models before deployment using the concurrent downloader:
+
+```python
+from uniface.model_store import download_models
+from uniface.constants import (
+    RetinaFaceWeights,
+    ArcFaceWeights,
+    AgeGenderWeights,
+)
+
+# Download multiple models concurrently (up to 4 threads by default)
+paths = download_models([
+    RetinaFaceWeights.MNET_V2,
+    ArcFaceWeights.MNET,
+    AgeGenderWeights.DEFAULT,
+])
+
+for model, path in paths.items():
+    print(f"{model.value} -> {path}")
+```
+
+Or download one at a time:
+
+```python
+from uniface.model_store import verify_model_weights
+from uniface.constants import RetinaFaceWeights
+
+path = verify_model_weights(RetinaFaceWeights.MNET_V2)
+print(f"Downloaded: {path}")
+```
+
+Or use the CLI tool:
+
+```bash
+python tools/download_model.py
+```
+
+---
+
+## Offline Use
+
+For air-gapped or offline environments:
+
+### 1. Pre-download models
+
+On a connected machine:
+
+```python
+from uniface.model_store import verify_model_weights
+from uniface.constants import RetinaFaceWeights
+
+path = verify_model_weights(RetinaFaceWeights.MNET_V2)
+print(f"Copy from: {path}")
+```
+
+### 2. Copy to target machine
+
+```bash
+# Copy the entire cache directory
+scp -r ~/.uniface/models/ user@offline-machine:~/.uniface/models/
+```
+
+### 3. Point to the cache (if non-default location)
+
+```python
+from uniface.model_store import set_cache_dir
+
+# Only needed if the models are not at ~/.uniface/models/
+set_cache_dir('/path/to/copied/models')
+```
+
+### 4. Use normally
+
+```python
+# Models load from local cache
+from uniface.detection import RetinaFace
+detector = RetinaFace()  # No network required
+```
+
+---
+
+## Model Verification
+
+Models are verified with SHA-256 checksums:
+
+```python
+from uniface.constants import MODEL_SHA256, RetinaFaceWeights
+
+# Check expected checksum
+expected = MODEL_SHA256[RetinaFaceWeights.MNET_V2]
+print(f"Expected SHA256: {expected}")
+```
+
+If a model fails verification, it's re-downloaded automatically.
+
+---
+
+## Available Models
+
+### Detection Models
+
+| Model | Size | Download |
+|-------|------|----------|
+| RetinaFace MNET_025 | 1.7 MB | ✅ |
+| RetinaFace MNET_V2 | 3.5 MB | ✅ |
+| RetinaFace RESNET34 | 56 MB | ✅ |
+| SCRFD 500M | 2.5 MB | ✅ |
+| SCRFD 10G | 17 MB | ✅ |
+| YOLOv5n-Face | 11 MB | ✅ |
+| YOLOv5s-Face | 28 MB | ✅ |
+| YOLOv5m-Face | 82 MB | ✅ |
+| YOLOv8-Lite-S | 7.4 MB | ✅ |
+| YOLOv8n-Face | 12 MB | ✅ |
+
+### Recognition Models
+
+| Model | Size | Download |
+|-------|------|----------|
+| ArcFace MNET | 8 MB | ✅ |
+| ArcFace RESNET | 166 MB | ✅ |
+| MobileFace MNET_V2 | 4 MB | ✅ |
+| SphereFace SPHERE20 | 50 MB | ✅ |
+
+### Other Models
+
+| Model | Size | Download |
+|-------|------|----------|
+| Landmark106 | 14 MB | ✅ |
+| AgeGender | 8 MB | ✅ |
+| FairFace | 44 MB | ✅ |
+| Gaze ResNet34 | 82 MB | ✅ |
+| BiSeNet ResNet18 | 51 MB | ✅ |
+| MiniFASNet V2 | 1.2 MB | ✅ |
+
+---
+
+## Clear Cache
+
+Find and remove cached models:
+
+```python
+from uniface.model_store import get_cache_dir
+print(get_cache_dir())  # shows the active cache path
+```
+
+```bash
+# Remove all cached models
+rm -rf ~/.uniface/models/
+
+# Remove specific model
+rm ~/.uniface/models/retinaface_mv2.onnx
+```
+
+Models will be re-downloaded on next use.
+
+---
+
+## Environment Variables
+
+There are three equivalent ways to configure the cache directory:
+
+**1. Programmatic API (recommended)**
+
+```python
+from uniface.model_store import get_cache_dir, set_cache_dir
+
+set_cache_dir('/path/to/custom/cache')
+print(get_cache_dir())  # /path/to/custom/cache
+```
+
+**2. Direct environment variable (Python)**
+
+```python
+import os
+os.environ['UNIFACE_CACHE_DIR'] = '/path/to/custom/cache'
+
+from uniface.detection import RetinaFace
+detector = RetinaFace()  # Uses custom cache
+```
+
+**3. Shell environment variable**
+
+```bash
+export UNIFACE_CACHE_DIR=/path/to/custom/cache
+```
+
+All three methods set the same `UNIFACE_CACHE_DIR` environment variable under the hood. `get_cache_dir()` always returns the resolved path.
+
+---
+
+## Next Steps
+
+- [Thresholds & Calibration](thresholds-calibration.md) - Tune model parameters
+- [Detection Module](../modules/detection.md) - Detection model details

docs/concepts/overview.md

@@ -0,0 +1,229 @@
+# Overview
+
+UniFace is designed as a modular, production-ready face analysis library. This page explains the architecture and design principles.
+
+---
+
+## Architecture
+
+UniFace follows a modular architecture where each face analysis task is handled by a dedicated module:
+
+```mermaid
+graph TB
+    subgraph Input
+        IMG[Image/Frame]
+    end
+
+    subgraph Detection
+        DET[RetinaFace / SCRFD / YOLOv5Face / YOLOv8Face]
+    end
+
+    subgraph Analysis
+        REC[Recognition]
+        LMK[Landmarks]
+        ATTR[Attributes]
+        GAZE[Gaze]
+        PARSE[Parsing]
+        SPOOF[Anti-Spoofing]
+        PRIV[Privacy]
+    end
+
+    subgraph Tracking
+        TRK[BYTETracker]
+    end
+
+    subgraph Indexing
+        IDX[FAISS Vector Store]
+    end
+
+    subgraph Output
+        FACE[Face Objects]
+    end
+
+    IMG --> DET
+    DET --> REC
+    DET --> LMK
+    DET --> ATTR
+    DET --> GAZE
+    DET --> PARSE
+    DET --> SPOOF
+    DET --> PRIV
+    DET --> TRK
+    REC --> IDX
+    REC --> FACE
+    LMK --> FACE
+    ATTR --> FACE
+    TRK --> FACE
+```
+
+---
+
+## Design Principles
+
+### 1. ONNX-First
+
+UniFace runs inference primarily via ONNX Runtime for core components:
+
+- **Cross-platform**: Same models work on macOS, Linux, Windows
+- **Hardware acceleration**: Automatic selection of optimal provider
+- **Production-ready**: No Python-only dependencies for inference
+
+Some optional components (e.g., emotion TorchScript, torchvision NMS) require PyTorch.
+
+### 2. Minimal Dependencies
+
+Core dependencies are kept minimal:
+
+```
+numpy         # Array operations
+opencv-python # Image processing
+onnxruntime   # Model inference
+requests      # Model download
+tqdm          # Progress bars
+```
+
+### 3. Simple API
+
+Factory functions and direct instantiation:
+
+```python
+from uniface.detection import RetinaFace
+
+detector = RetinaFace()
+
+# Or via factory function
+from uniface.detection import create_detector
+
+detector = create_detector('retinaface')
+```
+
+### 4. Type Safety
+
+Full type hints throughout:
+
+```python
+def detect(self, image: np.ndarray) -> list[Face]:
+    ...
+```
+
+---
+
+## Module Structure
+
+```
+uniface/
+├── detection/      # Face detection (RetinaFace, SCRFD, YOLOv5Face, YOLOv8Face)
+├── recognition/    # Face recognition (AdaFace, ArcFace, MobileFace, SphereFace)
+├── tracking/       # Multi-object tracking (BYTETracker)
+├── landmark/       # 106-point landmarks
+├── attribute/      # Age, gender, emotion, race
+├── parsing/        # Face semantic segmentation
+├── gaze/           # Gaze estimation
+├── spoofing/       # Anti-spoofing
+├── privacy/        # Face anonymization
+├── indexing/       # Vector indexing (FAISS)
+├── types.py        # Dataclasses (Face, GazeResult, etc.)
+├── constants.py    # Model weights and URLs
+├── model_store.py  # Model download and caching
+├── onnx_utils.py   # ONNX Runtime utilities
+└── draw.py         # Drawing utilities
+```
+
+---
+
+## Workflow
+
+A typical face analysis workflow:
+
+```python
+import cv2
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+
+# 1. Initialize models
+detector = RetinaFace()
+recognizer = ArcFace()
+age_gender = AgeGender()
+
+# 2. Load image
+image = cv2.imread("photo.jpg")
+
+# 3. Detect faces
+faces = detector.detect(image)
+
+# 4. Analyze each face
+for face in faces:
+    # Recognition embedding
+    embedding = recognizer.get_normalized_embedding(image, face.landmarks)
+
+    # Attributes
+    attrs = age_gender.predict(image, face.bbox)
+
+    print(f"Face: {attrs.sex}, {attrs.age} years")
+```
+
+---
+
+## FaceAnalyzer
+
+For convenience, `FaceAnalyzer` combines multiple modules:
+
+```python
+from uniface.analyzer import FaceAnalyzer
+from uniface.attribute import AgeGender, FairFace
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+
+detector = RetinaFace()
+recognizer = ArcFace()
+age_gender = AgeGender()
+fairface = FairFace()
+
+analyzer = FaceAnalyzer(
+    detector,
+    recognizer=recognizer,
+    age_gender=age_gender,
+    fairface=fairface,
+)
+
+faces = analyzer.analyze(image)
+for face in faces:
+    print(f"Age: {face.age}, Gender: {face.sex}")
+    print(f"Embedding: {face.embedding.shape}")
+```
+
+---
+
+## Model Lifecycle
+
+1. **First use**: Model is downloaded from GitHub releases
+2. **Cached**: Stored in `~/.uniface/models/` (configurable via `set_cache_dir()` or `UNIFACE_CACHE_DIR`)
+3. **Verified**: SHA-256 checksum validation
+4. **Loaded**: ONNX Runtime session created
+5. **Inference**: Hardware-accelerated execution
+
+```python
+# Models auto-download on first use
+detector = RetinaFace()  # Downloads if not cached
+
+# Optionally configure cache location
+from uniface.model_store import get_cache_dir, set_cache_dir
+set_cache_dir('/data/models')
+print(get_cache_dir())  # /data/models
+
+# Or manually pre-download
+from uniface.model_store import verify_model_weights
+from uniface.constants import RetinaFaceWeights
+
+path = verify_model_weights(RetinaFaceWeights.MNET_V2)
+```
+
+---
+
+## Next Steps
+
+- [Inputs & Outputs](inputs-outputs.md) - Understand data types
+- [Execution Providers](execution-providers.md) - Hardware acceleration
+- [Detection Module](../modules/detection.md) - Start with face detection
+- [Image Pipeline Recipe](../recipes/image-pipeline.md) - Complete workflow

docs/concepts/thresholds-calibration.md

@@ -0,0 +1,234 @@
+# Thresholds & Calibration
+
+This page explains how to tune detection and recognition thresholds for your use case.
+
+---
+
+## Detection Thresholds
+
+### Confidence Threshold
+
+Controls minimum confidence for face detection:
+
+```python
+from uniface.detection import RetinaFace
+
+# Default (balanced)
+detector = RetinaFace(confidence_threshold=0.5)
+
+# High precision (fewer false positives)
+detector = RetinaFace(confidence_threshold=0.8)
+
+# High recall (catch more faces)
+detector = RetinaFace(confidence_threshold=0.3)
+```
+
+**Guidelines:**
+
+| Threshold | Use Case |
+|-----------|----------|
+| 0.3 - 0.4 | Maximum recall (research, analysis) |
+| 0.5 - 0.6 | Balanced (default, general use) |
+| 0.7 - 0.9 | High precision (production, security) |
+
+---
+
+### NMS Threshold
+
+Non-Maximum Suppression removes overlapping detections:
+
+```python
+# Default
+detector = RetinaFace(nms_threshold=0.4)
+
+# Stricter (fewer overlapping boxes)
+detector = RetinaFace(nms_threshold=0.3)
+
+# Looser (for crowded scenes)
+detector = RetinaFace(nms_threshold=0.5)
+```
+
+---
+
+### Input Size
+
+Affects detection accuracy and speed:
+
+```python
+# Faster, lower accuracy
+detector = RetinaFace(input_size=(320, 320))
+
+# Balanced (default)
+detector = RetinaFace(input_size=(640, 640))
+
+# Higher accuracy, slower
+detector = RetinaFace(input_size=(1280, 1280))
+```
+
+!!! tip "Dynamic Size"
+    For RetinaFace, enable dynamic input for variable image sizes:
+    ```python
+    detector = RetinaFace(dynamic_size=True)
+    ```
+
+---
+
+## Recognition Thresholds
+
+### Similarity Threshold
+
+For identity verification (same person check):
+
+```python
+import numpy as np
+from uniface.face_utils import compute_similarity
+
+similarity = compute_similarity(embedding1, embedding2)
+
+# Threshold interpretation
+if similarity > 0.6:
+    print("Same person (high confidence)")
+elif similarity > 0.4:
+    print("Uncertain (manual review)")
+else:
+    print("Different people")
+```
+
+**Recommended thresholds:**
+
+| Threshold | Decision | False Accept Rate |
+|-----------|----------|-------------------|
+| 0.4 | Low security | Higher FAR |
+| 0.5 | Balanced | Moderate FAR |
+| 0.6 | High security | Lower FAR |
+| 0.7 | Very strict | Very low FAR |
+
+---
+
+### Calibration for Your Dataset
+
+Test on your data to find optimal thresholds:
+
+```python
+import numpy as np
+
+def calibrate_threshold(same_pairs, diff_pairs, recognizer, detector):
+    """Find optimal threshold for your dataset."""
+    same_scores = []
+    diff_scores = []
+
+    # Compute similarities for same-person pairs
+    for img1_path, img2_path in same_pairs:
+        img1 = cv2.imread(img1_path)
+        img2 = cv2.imread(img2_path)
+
+        faces1 = detector.detect(img1)
+        faces2 = detector.detect(img2)
+
+        if faces1 and faces2:
+            emb1 = recognizer.get_normalized_embedding(img1, faces1[0].landmarks)
+            emb2 = recognizer.get_normalized_embedding(img2, faces2[0].landmarks)
+            same_scores.append(np.dot(emb1, emb2.T)[0][0])
+
+    # Compute similarities for different-person pairs
+    for img1_path, img2_path in diff_pairs:
+        # ... similar process
+        diff_scores.append(similarity)
+
+    # Find optimal threshold
+    thresholds = np.arange(0.3, 0.8, 0.05)
+    best_threshold = 0.5
+    best_accuracy = 0
+
+    for thresh in thresholds:
+        tp = sum(1 for s in same_scores if s >= thresh)
+        tn = sum(1 for s in diff_scores if s < thresh)
+        accuracy = (tp + tn) / (len(same_scores) + len(diff_scores))
+
+        if accuracy > best_accuracy:
+            best_accuracy = accuracy
+            best_threshold = thresh
+
+    return best_threshold, best_accuracy
+```
+
+---
+
+## Anti-Spoofing Thresholds
+
+The MiniFASNet model returns a confidence score:
+
+```python
+from uniface.spoofing import MiniFASNet
+
+spoofer = MiniFASNet()
+result = spoofer.predict(image, face.bbox)
+
+# Default threshold (0.5)
+if result.is_real:  # confidence > 0.5
+    print("Real face")
+
+# Custom threshold for high security
+SPOOF_THRESHOLD = 0.7
+if result.confidence > SPOOF_THRESHOLD:
+    print("Real face (high confidence)")
+else:
+    print("Potentially fake")
+```
+
+---
+
+## Attribute Model Confidence
+
+### Emotion
+
+```python
+result = emotion_predictor.predict(image, landmarks)
+
+# Filter low-confidence predictions
+if result.confidence > 0.6:
+    print(f"Emotion: {result.emotion}")
+else:
+    print("Uncertain emotion")
+```
+
+---
+
+## Visualization Threshold
+
+For drawing detections, filter by confidence:
+
+```python
+from uniface.draw import draw_detections
+
+# Only draw high-confidence detections
+bboxes = [f.bbox for f in faces if f.confidence > 0.7]
+scores = [f.confidence for f in faces if f.confidence > 0.7]
+landmarks = [f.landmarks for f in faces if f.confidence > 0.7]
+
+draw_detections(
+    image=image,
+    bboxes=bboxes,
+    scores=scores,
+    landmarks=landmarks,
+    vis_threshold=0.6  # Additional visualization filter
+)
+```
+
+---
+
+## Summary
+
+| Parameter | Default | Range | Lower = | Higher = |
+|-----------|---------|-------|---------|----------|
+| `confidence_threshold` | 0.5 | 0.1-0.9 | More detections | Fewer false positives |
+| `nms_threshold` | 0.4 | 0.1-0.7 | Fewer overlaps | More overlapping boxes |
+| Similarity threshold | 0.6 | 0.3-0.8 | More matches (FAR↑) | Fewer matches (FRR↑) |
+| Spoof confidence | 0.5 | 0.3-0.9 | More "real" | Stricter liveness |
+
+---
+
+## Next Steps
+
+- [Detection Module](../modules/detection.md) - Detection model options
+- [Recognition Module](../modules/recognition.md) - Recognition model options

docs/contributing.md

@@ -0,0 +1,72 @@
+# Contributing
+
+Thank you for contributing to UniFace!
+
+---
+
+## Quick Start
+
+```bash
+# Clone
+git clone https://github.com/yakhyo/uniface.git
+cd uniface
+
+# Install dev dependencies
+pip install -e ".[dev]"
+
+# Run tests
+pytest
+```
+
+---
+
+## Code Style
+
+We use [Ruff](https://docs.astral.sh/ruff/) for formatting:
+
+```bash
+ruff format .
+ruff check . --fix
+```
+
+**Guidelines:**
+
+- Line length: 120
+- Python 3.10+ type hints
+- Google-style docstrings
+
+---
+
+## Pre-commit Hooks
+
+```bash
+pip install pre-commit
+pre-commit install
+pre-commit run --all-files
+```
+
+---
+
+## Pull Request Process
+
+1. Fork the repository
+2. Create a feature branch
+3. Write tests for new features
+4. Ensure tests pass
+5. Submit PR with clear description
+
+---
+
+## Adding New Models
+
+1. Create model class in appropriate submodule
+2. Add weight constants to `uniface/constants.py`
+3. Export in `__init__.py` files
+4. Write tests in `tests/`
+5. Add example in `tools/` or notebooks
+
+---
+
+## Questions?
+
+Open an issue on [GitHub](https://github.com/yakhyo/uniface/issues).

docs/datasets.md

@@ -0,0 +1,324 @@
+# Datasets
+
+Overview of all training datasets and evaluation benchmarks used by UniFace models.
+
+---
+
+## Quick Reference
+
+| Task        | Dataset                                          | Scale                  | Models                                      |
+| ----------- | ------------------------------------------------ | ---------------------- | ------------------------------------------- |
+| Detection   | [WIDER FACE](#wider-face)                        | 32K images             | RetinaFace, SCRFD, YOLOv5-Face, YOLOv8-Face |
+| Recognition | [MS1MV2](#ms1mv2)                                | 5.8M images, 85.7K IDs | MobileFace, SphereFace                      |
+| Recognition | [WebFace600K](#webface600k)                      | 600K images            | ArcFace                                     |
+| Recognition | [WebFace4M / WebFace12M](#webface4m--webface12m) | 4M / 12M images        | AdaFace                                     |
+| Gaze        | [Gaze360](#gaze360)                              | 238 subjects           | MobileGaze                                  |
+| Parsing     | [CelebAMask-HQ](#celebamask-hq)                  | 30K images             | BiSeNet                                     |
+| Attributes  | [CelebA](#celeba)                                | 200K images            | AgeGender                                   |
+| Attributes  | [FairFace](#fairface)                            | Balanced demographics  | FairFace                                    |
+| Attributes  | [AffectNet](#affectnet)                          | Emotion labels         | Emotion                                     |
+
+---
+
+## Training Datasets
+
+### Face Detection
+
+#### WIDER FACE
+
+Large-scale face detection benchmark with images across 61 event categories. Contains faces with a high degree of variability in scale, pose, occlusion, expression, and illumination.
+
+| Property | Value                                       |
+| -------- | ------------------------------------------- |
+| Images   | ~32,000 (train/val/test split)              |
+| Faces    | ~394,000 annotated                          |
+| Subsets  | Easy, Medium, Hard                          |
+| Used by  | RetinaFace, SCRFD, YOLOv5-Face, YOLOv8-Face |
+
+!!! info "Download & References"
+**Paper**: [WIDER FACE: A Face Detection Benchmark](https://arxiv.org/abs/1511.06523)
+
+    **Download**: [http://shuoyang1213.me/WIDERFACE/](http://shuoyang1213.me/WIDERFACE/)
+
+---
+
+### Face Recognition
+
+#### MS1MV2
+
+Refined version of the MS-Celeb-1M dataset, cleaned by InsightFace. Widely used for training face recognition models.
+
+| Property   | Value                          |
+| ---------- | ------------------------------ |
+| Identities | 85.7K                          |
+| Images     | 5.8M                           |
+| Format     | Aligned and cropped to 112x112 |
+| Used by    | MobileFace, SphereFace         |
+
+!!! info "Download"
+**Kaggle (aligned 112x112)**: [ms1m-arcface-dataset](https://www.kaggle.com/datasets/yakhyokhuja/ms1m-arcface-dataset) (from InsightFace)
+
+    **Training code**: [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition)
+
+---
+
+#### WebFace600K
+
+Medium-scale face recognition dataset from the WebFace series.
+
+| Property | Value   |
+| -------- | ------- |
+| Images   | ~600K   |
+| Used by  | ArcFace |
+
+!!! info "Source"
+**Origin**: [InsightFace](https://github.com/deepinsight/insightface)
+
+    **Paper**: [ArcFace: Additive Angular Margin Loss for Deep Face Recognition](https://arxiv.org/abs/1801.07698)
+
+---
+
+#### WebFace4M / WebFace12M
+
+Large-scale face recognition datasets from the WebFace260M collection. Used for training AdaFace models with adaptive quality-aware margin.
+
+| Property | WebFace4M     | WebFace12M     |
+| -------- | ------------- | -------------- |
+| Images   | ~4M           | ~12M           |
+| Used by  | AdaFace IR_18 | AdaFace IR_101 |
+
+!!! info "Source"
+**Paper**: [AdaFace: Quality Adaptive Margin for Face Recognition](https://arxiv.org/abs/2204.00964)
+
+    **Original code**: [mk-minchul/AdaFace](https://github.com/mk-minchul/AdaFace)
+
+---
+
+#### CASIA-WebFace
+
+Smaller-scale face recognition dataset suitable for academic research and lighter training runs.
+
+| Property   | Value                          |
+| ---------- | ------------------------------ |
+| Identities | 10.6K                          |
+| Images     | 491K                           |
+| Format     | Aligned and cropped to 112x112 |
+| Used by    | Alternative training set       |
+
+!!! info "Download"
+**Kaggle (aligned 112x112)**: [webface-112x112](https://www.kaggle.com/datasets/yakhyokhuja/webface-112x112) (from OpenSphere)
+
+---
+
+#### VGGFace2
+
+Large-scale dataset with wide variations in pose, age, illumination, ethnicity, and profession.
+
+| Property   | Value                          |
+| ---------- | ------------------------------ |
+| Identities | 8.6K                           |
+| Images     | 3.1M                           |
+| Format     | Aligned and cropped to 112x112 |
+| Used by    | Alternative training set       |
+
+!!! info "Download"
+**Kaggle (aligned 112x112)**: [vggface2-112x112](https://www.kaggle.com/datasets/yakhyokhuja/vggface2-112x112) (from OpenSphere)
+
+---
+
+### Gaze Estimation
+
+#### Gaze360
+
+Large-scale gaze estimation dataset collected in indoor and outdoor environments with diverse head poses and wide gaze ranges (up to 360 degrees).
+
+| Property    | Value                 |
+| ----------- | --------------------- |
+| Subjects    | 238                   |
+| Environment | Indoor and outdoor    |
+| Used by     | All MobileGaze models |
+
+!!! info "Download & Preprocessing"
+**Download**: [gaze360.csail.mit.edu/download.php](https://gaze360.csail.mit.edu/download.php)
+
+    **Preprocessing**: [GazeHub - Gaze360](https://phi-ai.buaa.edu.cn/Gazehub/3D-dataset/#gaze360)
+
+!!! note "UniFace Models"
+All MobileGaze models shipped with UniFace are trained exclusively on Gaze360 for 200 epochs.
+
+**Dataset structure:**
+
+```
+data/
+└── Gaze360/
+    ├── Image/
+    └── Label/
+```
+
+---
+
+#### MPIIFaceGaze
+
+Dataset for appearance-based gaze estimation from laptop webcam images of participants during everyday laptop usage. Supported by the gaze estimation training code but not used for the UniFace pretrained weights.
+
+| Property    | Value                                    |
+| ----------- | ---------------------------------------- |
+| Subjects    | 15                                       |
+| Environment | Everyday laptop usage                    |
+| Used by     | Supported (not used for UniFace weights) |
+
+!!! info "Download & Preprocessing"
+**Download**: [MPIIFaceGaze download page](https://www.mpi-inf.mpg.de/departments/computer-vision-and-machine-learning/research/gaze-based-human-computer-interaction/its-written-all-over-your-face-full-face-appearance-based-gaze-estimation)
+
+    **Preprocessing**: [GazeHub - MPIIFaceGaze](https://phi-ai.buaa.edu.cn/Gazehub/3D-dataset/#mpiifacegaze)
+
+**Dataset structure:**
+
+```
+data/
+└── MPIIFaceGaze/
+    ├── Image/
+    └── Label/
+```
+
+---
+
+### Face Parsing
+
+#### CelebAMask-HQ
+
+High-quality face parsing dataset with pixel-level annotations for 19 facial component classes.
+
+| Property   | Value                        |
+| ---------- | ---------------------------- |
+| Images     | 30,000                       |
+| Classes    | 19 facial components         |
+| Resolution | High quality                 |
+| Used by    | BiSeNet (ResNet18, ResNet34) |
+
+!!! info "Source"
+**GitHub**: [switchablenorms/CelebAMask-HQ](https://github.com/switchablenorms/CelebAMask-HQ)
+
+    **Training code**: [yakhyo/face-parsing](https://github.com/yakhyo/face-parsing)
+
+**Dataset structure:**
+
+```
+dataset/
+├── images/           # Input face images
+│   ├── image1.jpg
+│   └── ...
+└── labels/           # Segmentation masks
+    ├── image1.png
+    └── ...
+```
+
+---
+
+### Attribute Analysis
+
+#### CelebA
+
+Large-scale face attributes dataset widely used for training age and gender prediction models.
+
+| Property   | Value                |
+| ---------- | -------------------- |
+| Images     | ~200K                |
+| Attributes | 40 binary attributes |
+| Used by    | AgeGender            |
+
+!!! info "Reference"
+**Paper**: [Deep Learning Face Attributes in the Wild](https://arxiv.org/abs/1411.7766)
+
+---
+
+#### FairFace
+
+Face attribute dataset designed for balanced representation across race, gender, and age groups. Provides more equitable predictions compared to imbalanced datasets.
+
+| Property   | Value                               |
+| ---------- | ----------------------------------- |
+| Attributes | Race (7), Gender (2), Age Group (9) |
+| Used by    | FairFace                            |
+| License    | CC BY 4.0                           |
+
+!!! info "Reference"
+**Paper**: [FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age](https://arxiv.org/abs/1908.04913)
+
+    **ONNX inference**: [yakhyo/fairface-onnx](https://github.com/yakhyo/fairface-onnx)
+
+---
+
+#### AffectNet
+
+Large-scale facial expression dataset for emotion recognition training.
+
+| Property | Value                                                                   |
+| -------- | ----------------------------------------------------------------------- |
+| Classes  | 7 or 8 (Neutral, Happy, Sad, Surprise, Fear, Disgust, Angry + Contempt) |
+| Used by  | Emotion (AFFECNET7, AFFECNET8)                                          |
+
+!!! info "Reference"
+**Paper**: [AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild](https://ieeexplore.ieee.org/document/8013713)
+
+---
+
+## Evaluation Benchmarks
+
+### Face Detection
+
+#### WIDER FACE Validation Set
+
+The standard benchmark for face detection models. Results are reported across three difficulty subsets.
+
+| Subset | Criteria                                      |
+| ------ | --------------------------------------------- |
+| Easy   | Large, clear, unoccluded faces                |
+| Medium | Moderate scale and occlusion                  |
+| Hard   | Small, heavily occluded, or challenging faces |
+
+See [Model Zoo - Detection](models.md#face-detection-models) for per-model accuracy on each subset.
+
+---
+
+### Face Recognition
+
+Recognition models are evaluated across multiple benchmarks. Aligned 112x112 validation datasets are available as a single download.
+
+!!! info "Download"
+**Kaggle**: [agedb-30-calfw-cplfw-lfw-aligned-112x112](https://www.kaggle.com/datasets/yakhyokhuja/agedb-30-calfw-cplfw-lfw-aligned-112x112)
+
+| Benchmark    | Description                                                       | Used by                         |
+| ------------ | ----------------------------------------------------------------- | ------------------------------- |
+| **LFW**      | Labeled Faces in the Wild - standard face verification benchmark  | ArcFace, MobileFace, SphereFace |
+| **CALFW**    | Cross-Age LFW - face verification across age gaps                 | MobileFace, SphereFace          |
+| **CPLFW**    | Cross-Pose LFW - face verification across pose variations         | MobileFace, SphereFace          |
+| **AgeDB-30** | Age database with 30-year age gaps                                | ArcFace, MobileFace, SphereFace |
+| **CFP-FP**   | Celebrities in Frontal-Profile - frontal vs. profile verification | ArcFace                         |
+| **IJB-B**    | IARPA Janus Benchmark B - TAR@FAR=0.01%                           | AdaFace                         |
+| **IJB-C**    | IARPA Janus Benchmark C - TAR@FAR=1e-4                            | AdaFace, ArcFace                |
+
+See [Model Zoo - Recognition](models.md#face-recognition-models) for per-model accuracy on each benchmark.
+
+---
+
+### Gaze Estimation
+
+| Benchmark            | Metric        | Description                                  |
+| -------------------- | ------------- | -------------------------------------------- |
+| **Gaze360 test set** | MAE (degrees) | Mean Absolute Error in gaze angle prediction |
+
+See [Model Zoo - Gaze](models.md#gaze-estimation-models) for per-model MAE scores.
+
+---
+
+## Training Repositories
+
+For training your own models or reproducing results, see the following repositories:
+
+| Task        | Repository                                                                | Datasets Supported              |
+| ----------- | ------------------------------------------------------------------------- | ------------------------------- |
+| Detection   | [yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch) | WIDER FACE                      |
+| Recognition | [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition)     | MS1MV2, CASIA-WebFace, VGGFace2 |
+| Gaze        | [yakhyo/gaze-estimation](https://github.com/yakhyo/gaze-estimation)       | Gaze360, MPIIFaceGaze           |
+| Parsing     | [yakhyo/face-parsing](https://github.com/yakhyo/face-parsing)             | CelebAMask-HQ                   |

docs/index.md

@@ -0,0 +1,147 @@
+---
+hide:
+  - toc
+  - navigation
+  - edit
+template: home.html
+---
+
+<div class="hero" markdown>
+
+# UniFace { .hero-title }
+
+<p class="hero-subtitle">All-in-One Open-Source Face Analysis Library</p>
+
+[![PyPI Version](https://img.shields.io/pypi/v/uniface.svg?label=Version)](https://pypi.org/project/uniface/)
+[![Python Version](https://img.shields.io/badge/Python-3.10%2B-blue)](https://www.python.org/)
+[![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
+[![Github Build Status](https://github.com/yakhyo/uniface/actions/workflows/ci.yml/badge.svg)](https://github.com/yakhyo/uniface/actions)
+[![PyPI Downloads](https://static.pepy.tech/personalized-badge/uniface?period=total&units=INTERNATIONAL_SYSTEM&left_color=GRAY&right_color=BLUE&left_text=Downloads)](https://pepy.tech/projects/uniface)
+[![Kaggle Badge](https://img.shields.io/badge/Notebooks-Kaggle?label=Kaggle&color=blue)](https://www.kaggle.com/yakhyokhuja/code)
+[![Discord](https://img.shields.io/badge/Discord-Join%20Server-5865F2?logo=discord&logoColor=white)](https://discord.gg/wdzrjr7R5j)
+
+<!-- <img src="https://raw.githubusercontent.com/yakhyo/uniface/main/.github/logos/uniface_rounded_q80.webp" alt="UniFace - All-in-One Open-Source Face Analysis Library" style="max-width: 70%; margin: 1rem 0;"> -->
+
+[Get Started](quickstart.md){ .md-button .md-button--primary }
+[View on GitHub](https://github.com/yakhyo/uniface){ .md-button }
+
+</div>
+
+<div class="feature-grid" markdown>
+
+<div class="feature-card" markdown>
+### :material-face-recognition: Face Detection
+ONNX-optimized detectors (RetinaFace, SCRFD, YOLO) with 5-point landmarks.
+</div>
+
+<div class="feature-card" markdown>
+### :material-account-check: Face Recognition
+AdaFace, ArcFace, MobileFace, and SphereFace embeddings for identity verification.
+</div>
+
+<div class="feature-card" markdown>
+### :material-map-marker: Landmarks
+Accurate 106-point facial landmark localization for detailed face analysis.
+</div>
+
+<div class="feature-card" markdown>
+### :material-account-details: Attributes
+Age, gender, race (FairFace), and emotion detection from faces.
+</div>
+
+<div class="feature-card" markdown>
+### :material-face-man-shimmer: Face Parsing
+BiSeNet semantic segmentation with 19 facial component classes.
+</div>
+
+<div class="feature-card" markdown>
+### :material-eye: Gaze Estimation
+Real-time gaze direction prediction with MobileGaze models.
+</div>
+
+<div class="feature-card" markdown>
+### :material-motion-play: Tracking
+Multi-object tracking with BYTETracker for persistent face IDs across video frames.
+</div>
+
+<div class="feature-card" markdown>
+### :material-shield-check: Anti-Spoofing
+Face liveness detection with MiniFASNet to prevent fraud.
+</div>
+
+<div class="feature-card" markdown>
+### :material-blur: Privacy
+Face anonymization with 5 blur methods for privacy protection.
+</div>
+
+<div class="feature-card" markdown>
+### :material-database-search: Vector Indexing
+FAISS-backed embedding store for fast multi-identity face search.
+</div>
+
+</div>
+
+---
+
+## Installation
+
+UniFace runs inference primarily via **ONNX Runtime**; some optional components (e.g., emotion TorchScript, torchvision NMS) require **PyTorch**.
+
+**Standard**
+```bash
+pip install uniface
+```
+
+**GPU (CUDA)**
+```bash
+pip install uniface[gpu]
+```
+
+**From Source**
+```bash
+git clone https://github.com/yakhyo/uniface.git
+cd uniface
+pip install -e .
+```
+
+---
+
+## Next Steps
+
+<div class="next-steps-grid" markdown>
+
+<div class="feature-card" markdown>
+### :material-rocket-launch: Quickstart
+Get up and running in 5 minutes with common use cases.
+
+[Quickstart Guide →](quickstart.md)
+</div>
+
+<div class="feature-card" markdown>
+### :material-school: Tutorials
+Step-by-step examples for common workflows.
+
+[View Tutorials →](recipes/image-pipeline.md)
+</div>
+
+<div class="feature-card" markdown>
+### :material-api: API Reference
+Explore individual modules and their APIs.
+
+[Browse API →](modules/detection.md)
+</div>
+
+<div class="feature-card" markdown>
+### :material-book-open-variant: Guides
+Learn about the architecture and design principles.
+
+[Read Guides →](concepts/overview.md)
+</div>
+
+</div>
+
+---
+
+## License
+
+UniFace is released under the [MIT License](https://opensource.org/licenses/MIT).

docs/installation.md

@@ -0,0 +1,196 @@
+# Installation
+
+This guide covers all installation options for UniFace.
+
+---
+
+## Requirements
+
+- **Python**: 3.10 or higher
+- **Operating Systems**: macOS, Linux, Windows
+
+---
+
+## Quick Install
+
+The simplest way to install UniFace:
+
+```bash
+pip install uniface
+```
+
+This installs the CPU version with all core dependencies.
+
+---
+
+## Platform-Specific Installation
+
+### macOS (Apple Silicon - M1/M2/M3/M4)
+
+For Apple Silicon Macs, the standard installation automatically includes ARM64 optimizations:
+
+```bash
+pip install uniface
+```
+
+!!! tip "Native Performance"
+    The base `onnxruntime` package has native Apple Silicon support with ARM64 optimizations built-in since version 1.13+. No additional configuration needed.
+
+Verify ARM64 installation:
+
+```bash
+python -c "import platform; print(platform.machine())"
+# Should show: arm64
+```
+
+---
+
+### Linux/Windows with NVIDIA GPU
+
+For CUDA acceleration on NVIDIA GPUs:
+
+```bash
+pip install uniface[gpu]
+```
+
+**Requirements:**
+
+- `uniface[gpu]` automatically installs `onnxruntime-gpu`. Requirements depend on the ORT version and execution provider.
+
+!!! info "CUDA Compatibility"
+    See the [ONNX Runtime GPU compatibility matrix](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html) for matching CUDA and cuDNN versions.
+
+Verify GPU installation:
+
+```python
+import onnxruntime as ort
+print("Available providers:", ort.get_available_providers())
+# Should include: 'CUDAExecutionProvider'
+```
+
+---
+
+### FAISS Vector Indexing
+
+For fast multi-identity face search using a FAISS index:
+
+```bash
+pip install faiss-cpu   # CPU
+pip install faiss-gpu   # NVIDIA GPU (CUDA)
+```
+
+See the [Indexing module](modules/indexing.md) for usage.
+
+---
+
+### CPU-Only (All Platforms)
+
+```bash
+pip install uniface
+```
+
+Works on all platforms with automatic CPU fallback.
+
+---
+
+## Install from Source
+
+For development or the latest features:
+
+```bash
+git clone https://github.com/yakhyo/uniface.git
+cd uniface
+pip install -e .
+```
+
+With development dependencies:
+
+```bash
+pip install -e ".[dev]"
+```
+
+---
+
+## Dependencies
+
+UniFace has minimal dependencies:
+
+| Package | Purpose |
+|---------|---------|
+| `numpy` | Array operations |
+| `opencv-python` | Image processing |
+| `onnxruntime` | Model inference |
+| `scikit-image` | Geometric transforms |
+| `requests` | Model download |
+| `tqdm` | Progress bars |
+
+**Optional:**
+
+| Package | Install extra | Purpose |
+|---------|---------------|---------|
+| `faiss-cpu` / `faiss-gpu` | `pip install faiss-cpu` | FAISS vector indexing |
+| `onnxruntime-gpu` | `uniface[gpu]` | CUDA acceleration |
+| `torch` | `pip install torch` | Emotion model uses TorchScript |
+| `torchvision` | `pip install torchvision` | Faster NMS for YOLO detectors |
+
+---
+
+## Verify Installation
+
+Test your installation:
+
+```python
+import uniface
+print(f"UniFace version: {uniface.__version__}")
+
+# Check available ONNX providers
+import onnxruntime as ort
+print(f"Available providers: {ort.get_available_providers()}")
+
+# Quick test
+from uniface.detection import RetinaFace
+detector = RetinaFace()
+print("Installation successful!")
+```
+
+---
+
+## Troubleshooting
+
+### Import Errors
+
+If you encounter import errors, ensure you're using Python 3.10+:
+
+```bash
+python --version
+# Should show: Python 3.10.x or higher
+```
+
+### Model Download Issues
+
+Models are automatically downloaded on first use. If downloads fail:
+
+```python
+from uniface.model_store import verify_model_weights
+from uniface.constants import RetinaFaceWeights
+
+# Manually download a model
+model_path = verify_model_weights(RetinaFaceWeights.MNET_V2)
+print(f"Model downloaded to: {model_path}")
+```
+
+### Performance Issues on Mac
+
+Verify you're using the ARM64 build (not x86_64 via Rosetta):
+
+```bash
+python -c "import platform; print(platform.machine())"
+# Should show: arm64 (not x86_64)
+```
+
+---
+
+## Next Steps
+
+- [Quickstart Guide](quickstart.md) - Get started in 5 minutes
+- [Execution Providers](concepts/execution-providers.md) - Hardware acceleration setup

docs/license-attribution.md

@@ -0,0 +1,24 @@
+# Licenses & Attribution
+
+## UniFace License
+
+UniFace is released under the [MIT License](https://opensource.org/licenses/MIT).
+
+---
+
+## Model Credits
+
+| Model | Source | License |
+|-------|--------|---------|
+| RetinaFace | [yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch) | MIT |
+| SCRFD | [InsightFace](https://github.com/deepinsight/insightface) | MIT |
+| YOLOv5-Face | [yakhyo/yolov5-face-onnx-inference](https://github.com/yakhyo/yolov5-face-onnx-inference) | GPL-3.0 |
+| YOLOv8-Face | [yakhyo/yolov8-face-onnx-inference](https://github.com/yakhyo/yolov8-face-onnx-inference) | GPL-3.0 |
+| AdaFace | [yakhyo/adaface-onnx](https://github.com/yakhyo/adaface-onnx) | MIT |
+| ArcFace | [InsightFace](https://github.com/deepinsight/insightface) | MIT |
+| MobileFace | [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition) | MIT |
+| SphereFace | [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition) | MIT |
+| BiSeNet | [yakhyo/face-parsing](https://github.com/yakhyo/face-parsing) | MIT |
+| MobileGaze | [yakhyo/gaze-estimation](https://github.com/yakhyo/gaze-estimation) | MIT |
+| MiniFASNet | [yakhyo/face-anti-spoofing](https://github.com/yakhyo/face-anti-spoofing) | Apache-2.0 |
+| FairFace | [yakhyo/fairface-onnx](https://github.com/yakhyo/fairface-onnx) | CC BY 4.0 |

docs/models.md

@@ -0,0 +1,389 @@
+# Model Zoo
+
+Complete guide to all available models and their performance characteristics.
+
+---
+
+## Face Detection Models
+
+### RetinaFace Family
+
+RetinaFace models are trained on the [WIDER FACE](datasets.md#wider-face) dataset.
+
+| Model Name     | Params | Size  | Easy   | Medium | Hard   |
+| -------------- | ------ | ----- | ------ | ------ | ------ |
+| `MNET_025`   | 0.4M   | 1.7MB | 88.48% | 87.02% | 80.61% |
+| `MNET_050`   | 1.0M   | 2.6MB | 89.42% | 87.97% | 82.40% |
+| `MNET_V1`    | 3.5M   | 3.8MB | 90.59% | 89.14% | 84.13% |
+| `MNET_V2` :material-check-circle: | 3.2M   | 3.5MB | 91.70% | 91.03% | 86.60% |
+| `RESNET18`   | 11.7M  | 27MB  | 92.50% | 91.02% | 86.63% |
+| `RESNET34`   | 24.8M  | 56MB  | 94.16% | 93.12% | 88.90% |
+
+!!! info "Accuracy & Benchmarks"
+    **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 `python tools/detect.py --source <image>`
+
+---
+
+### SCRFD Family
+
+SCRFD (Sample and Computation Redistribution for Efficient Face Detection) models trained on [WIDER FACE](datasets.md#wider-face) dataset.
+
+| Model Name       | Params | Size  | Easy   | Medium | Hard   |
+| ---------------- | ------ | ----- | ------ | ------ | ------ |
+| `SCRFD_500M_KPS`   | 0.6M   | 2.5MB | 90.57% | 88.12% | 68.51% |
+| `SCRFD_10G_KPS` :material-check-circle: | 4.2M   | 17MB  | 95.16% | 93.87% | 83.05% |
+
+!!! info "Accuracy & Benchmarks"
+    **Accuracy**: WIDER FACE validation set - from [SCRFD paper](https://arxiv.org/abs/2105.04714)
+
+    **Speed**: Benchmark on your own hardware using `python tools/detect.py --source <image>`
+
+---
+
+### YOLOv5-Face Family
+
+YOLOv5-Face models provide detection with 5-point facial landmarks, trained on [WIDER FACE](datasets.md#wider-face) dataset.
+
+| Model Name     | Size | Easy   | Medium | Hard   |
+| -------------- | ---- | ------ | ------ | ------ |
+| `YOLOV5N`    | 11MB | 93.61% | 91.52% | 80.53% |
+| `YOLOV5S` :material-check-circle: | 28MB | 94.33% | 92.61% | 83.15% |
+| `YOLOV5M`    | 82MB | 95.30% | 93.76% | 85.28% |
+
+!!! info "Accuracy & Benchmarks"
+    **Accuracy**: WIDER FACE validation set - from [YOLOv5-Face paper](https://arxiv.org/abs/2105.12931)
+
+    **Speed**: Benchmark on your own hardware using `python tools/detect.py --source <image>`
+
+!!! note "Fixed Input Size"
+    All YOLOv5-Face models use a fixed input size of 640×640.
+
+---
+
+### YOLOv8-Face Family
+
+YOLOv8-Face models use anchor-free design with DFL (Distribution Focal Loss) for bbox regression. Provides detection with 5-point facial landmarks.
+
+| Model Name       | Size   | Easy   | Medium | Hard   |
+| ---------------- | ------ | ------ | ------ | ------ |
+| `YOLOV8_LITE_S`| 7.4MB  | 93.4%  | 91.2%  | 78.6%  |
+| `YOLOV8N` :material-check-circle: | 12MB   | 94.6%  | 92.3%  | 79.6%  |
+
+!!! info "Accuracy & Benchmarks"
+    **Accuracy**: WIDER FACE validation set (Easy/Medium/Hard subsets)
+
+    **Speed**: Benchmark on your own hardware using `python tools/detect.py --source <image> --method yolov8face`
+
+!!! note "Fixed Input Size"
+    All YOLOv8-Face models use a fixed input size of 640×640.
+
+---
+
+## Face Recognition Models
+
+### AdaFace
+
+Face recognition using adaptive margin based on image quality.
+
+| Model Name  | Backbone | Dataset     | Size   | IJB-B TAR | IJB-C TAR |
+| ----------- | -------- | ----------- | ------ | --------- | --------- |
+| `IR_18` :material-check-circle: | IR-18    | WebFace4M   | 92 MB  | 93.03%    | 94.99%    |
+| `IR_101`  | IR-101   | WebFace12M  | 249 MB | -         | 97.66%    |
+
+!!! info "Training Data & Accuracy"
+    **Dataset**: [WebFace4M / WebFace12M](datasets.md#webface4m--webface12m) (4M / 12M images)
+
+    **Accuracy**: IJB-B and IJB-C benchmarks, TAR@FAR=0.01%
+
+!!! tip "Key Innovation"
+    AdaFace introduces adaptive margin that adjusts based on image quality, providing better performance on low-quality images compared to fixed-margin approaches.
+
+
+---
+
+### ArcFace
+
+Face recognition using additive angular margin loss.
+
+| Model Name  | Backbone  | Params | Size  | LFW    | CFP-FP | AgeDB-30 | IJB-C |
+| ----------- | --------- | ------ | ----- | ------ | ------ | -------- | ----- |
+| `MNET` :material-check-circle: | MobileNet | 2.0M   | 8MB   | 99.70% | 98.00% | 96.58%   | 95.02% |
+| `RESNET`  | ResNet50  | 43.6M  | 166MB | 99.83% | 99.33% | 98.23%   | 97.25% |
+
+!!! info "Training Data"
+    **Dataset**: Trained on [WebFace600K](datasets.md#webface600k) (600K images)
+
+    **Accuracy**: IJB-C accuracy reported as TAR@FAR=1e-4
+
+---
+
+### MobileFace
+
+Lightweight face recognition models with MobileNet backbones.
+
+| Model Name        | Backbone         | Params | Size | LFW    | CALFW  | CPLFW  | AgeDB-30 |
+| ----------------- | ---------------- | ------ | ---- | ------ | ------ | ------ | -------- |
+| `MNET_025`      | MobileNetV1 0.25 | 0.36M  | 1MB  | 98.76% | 92.02% | 82.37% | 90.02%   |
+| `MNET_V2` :material-check-circle:    | MobileNetV2      | 2.29M  | 4MB  | 99.55% | 94.87% | 86.89% | 95.16%   |
+| `MNET_V3_SMALL` | MobileNetV3-S    | 1.25M  | 3MB  | 99.30% | 93.77% | 85.29% | 92.79%   |
+| `MNET_V3_LARGE` | MobileNetV3-L    | 3.52M  | 10MB | 99.53% | 94.56% | 86.79% | 95.13%   |
+
+!!! info "Training Data"
+    **Dataset**: Trained on [MS1MV2](datasets.md#ms1mv2) (5.8M images, 85K identities)
+
+    **Accuracy**: Evaluated on LFW, CALFW, CPLFW, and AgeDB-30 benchmarks
+
+---
+
+### SphereFace
+
+Face recognition using angular softmax loss.
+
+| Model Name   | Backbone | Params | Size | LFW    | CALFW  | CPLFW  | AgeDB-30 |
+| ------------ | -------- | ------ | ---- | ------ | ------ | ------ | -------- |
+| `SPHERE20` | Sphere20 | 24.5M  | 50MB | 99.67% | 95.61% | 88.75% | 96.58%   |
+| `SPHERE36` | Sphere36 | 34.6M  | 92MB | 99.72% | 95.64% | 89.92% | 96.83%   |
+
+!!! info "Training Data"
+    **Dataset**: Trained on [MS1MV2](datasets.md#ms1mv2) (5.8M images, 85K identities)
+
+    **Accuracy**: Evaluated on LFW, CALFW, CPLFW, and AgeDB-30 benchmarks
+
+!!! note "Architecture"
+    SphereFace uses angular softmax loss, an earlier approach before ArcFace. These models provide good accuracy with moderate resource requirements.
+
+---
+
+## Facial Landmark Models
+
+### 106-Point Landmark Detection
+
+Facial landmark localization model.
+
+| Model Name | Points | Params | Size |
+| ---------- | ------ | ------ | ---- |
+| `2D106`  | 106    | 3.7M   | 14MB |
+
+**Landmark Groups:**
+
+| Group | Points | Count |
+|-------|--------|-------|
+| Face contour | 0-32 | 33 points |
+| Eyebrows | 33-50 | 18 points |
+| Nose | 51-62 | 12 points |
+| Eyes | 63-86 | 24 points |
+| Mouth | 87-105 | 19 points |
+
+---
+
+## Attribute Analysis Models
+
+### Age & Gender Detection
+
+| Model Name  | Attributes  | Params | Size |
+| ----------- | ----------- | ------ | ---- |
+| `AgeGender` | Age, Gender | 2.1M   | 8MB  |
+
+!!! info "Training Data"
+    **Dataset**: Trained on [CelebA](datasets.md#celeba)
+
+!!! warning "Accuracy Note"
+    Accuracy varies by demographic and image quality. Test on your specific use case.
+
+---
+
+### FairFace Attributes
+
+| Model Name  | Attributes            | Params | Size  |
+| ----------- | --------------------- | ------ | ----- |
+| `FairFace` | Race, Gender, Age Group | -      | 44MB  |
+
+!!! info "Training Data"
+    **Dataset**: Trained on [FairFace](datasets.md#fairface) dataset with balanced demographics
+
+!!! tip "Equitable Predictions"
+    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+
+
+---
+
+### Emotion Detection
+
+| Model Name    | Classes | Params | Size |
+| ------------- | ------- | ------ | ---- |
+| `AFFECNET7` | 7       | 0.5M   | 2MB  |
+| `AFFECNET8` | 8       | 0.5M   | 2MB  |
+
+**Classes (7)**: Neutral, Happy, Sad, Surprise, Fear, Disgust, Angry
+
+**Classes (8)**: Above + Contempt
+
+!!! info "Training Data"
+    **Dataset**: Trained on [AffectNet](datasets.md#affectnet)
+
+!!! note "Accuracy Note"
+    Emotion detection accuracy depends heavily on facial expression clarity and cultural context.
+
+---
+
+## Gaze Estimation Models
+
+### MobileGaze Family
+
+Gaze direction prediction models trained on [Gaze360](datasets.md#gaze360) dataset. Returns pitch (vertical) and yaw (horizontal) angles in radians.
+
+| Model Name     | Params | Size    | MAE*  |
+| -------------- | ------ | ------- | ----- |
+| `RESNET18`   | 11.7M  | 43 MB   | 12.84 |
+| `RESNET34` :material-check-circle: | 24.8M  | 81.6 MB | 11.33 |
+| `RESNET50`   | 25.6M  | 91.3 MB | 11.34 |
+| `MOBILENET_V2` | 3.5M   | 9.59 MB | 13.07 |
+| `MOBILEONE_S0` | 2.1M   | 4.8 MB  | 12.58 |
+
+*MAE (Mean Absolute Error) in degrees on Gaze360 test set - lower is better
+
+!!! info "Training Data"
+    **Dataset**: Trained on [Gaze360](datasets.md#gaze360) (indoor/outdoor scenes with diverse head poses)
+
+    **Training**: 200 epochs with classification-based approach (binned angles)
+
+!!! note "Input Requirements"
+    Requires face crop as input. Use face detection first to obtain bounding boxes.
+
+---
+
+## Face Parsing Models
+
+### BiSeNet Family
+
+BiSeNet (Bilateral Segmentation Network) models for semantic face parsing. Segments face images into 19 facial component classes.
+
+| Model Name     | Params | Size    | Classes |
+| -------------- | ------ | ------- | ------- |
+| `RESNET18` :material-check-circle: | 13.3M  | 50.7 MB | 19      |
+| `RESNET34`   | 24.1M  | 89.2 MB | 19      |
+
+!!! info "Training Data"
+    **Dataset**: Trained on [CelebAMask-HQ](datasets.md#celebamask-hq)
+
+    **Architecture**: BiSeNet with ResNet backbone
+
+    **Input Size**: 512×512 (automatically resized)
+
+**19 Facial Component Classes:**
+
+| # | Class | # | Class | # | Class |
+|---|-------|---|-------|---|-------|
+| 0 | Background | 7 | Left Ear | 14 | Neck |
+| 1 | Skin | 8 | Right Ear | 15 | Neck Lace |
+| 2 | Left Eyebrow | 9 | Ear Ring | 16 | Cloth |
+| 3 | Right Eyebrow | 10 | Nose | 17 | Hair |
+| 4 | Left Eye | 11 | Mouth | 18 | Hat |
+| 5 | Right Eye | 12 | Upper Lip | | |
+| 6 | Eye Glasses | 13 | Lower Lip | | |
+
+**Applications:**
+
+- Face makeup and beauty applications
+- Virtual try-on systems
+- Face editing and manipulation
+- Facial feature extraction
+- Portrait segmentation
+
+!!! note "Input Requirements"
+    Input should be a cropped face image. For full pipeline, use face detection first to obtain face crops.
+
+---
+
+### XSeg
+
+XSeg from DeepFaceLab outputs masks for face regions. Requires 5-point landmarks for face alignment.
+
+| Model Name | Size   | Output |
+|------------|--------|--------|
+| `DEFAULT`  | 67 MB  | Mask [0, 1] |
+
+!!! info "Model Details"
+    **Origin**: DeepFaceLab
+
+    **Input**: NHWC format, normalized to [0, 1]
+
+    **Alignment**: Requires 5-point landmarks (not bbox crops)
+
+**Applications:**
+
+- Face region extraction
+- Face swapping pipelines
+- Occlusion handling
+
+!!! note "Input Requirements"
+    Requires 5-point facial landmarks. Use a face detector like RetinaFace to obtain landmarks first.
+
+---
+
+## Anti-Spoofing Models
+
+### MiniFASNet Family
+
+Face anti-spoofing models for liveness detection. Detect if a face is real (live) or fake (photo, video replay, mask).
+
+| Model Name | Size   | Scale |
+| ---------- | ------ | ----- |
+| `V1SE`   | 1.2 MB | 4.0   |
+| `V2` :material-check-circle:  | 1.2 MB | 2.7   |
+
+!!! info "Output Format"
+    **Output**: Returns `SpoofingResult(is_real, confidence)` where is_real: True=Real, False=Fake
+
+!!! note "Input Requirements"
+    Requires face bounding box from a detector.
+
+---
+
+## Model Management
+
+Models are automatically downloaded and cached on first use.
+
+- **Cache location**: `~/.uniface/models/` (configurable via `set_cache_dir()` or `UNIFACE_CACHE_DIR` env var)
+- **Inspect cache path**: `get_cache_dir()` returns the resolved active path
+- **Verification**: Models are verified with SHA-256 checksums
+- **Concurrent download**: `download_models([...])` fetches multiple models in parallel
+- **Manual download**: Use `python tools/download_model.py` to pre-download models
+
+See [Model Cache & Offline Use](concepts/model-cache-offline.md) for full details.
+
+---
+
+## References
+
+### 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
+- **YOLOv8-Face Original**: [derronqi/yolov8-face](https://github.com/derronqi/yolov8-face) - Original PyTorch implementation
+- **YOLOv8-Face ONNX**: [yakhyo/yolov8-face-onnx-inference](https://github.com/yakhyo/yolov8-face-onnx-inference) - ONNX inference implementation
+- **AdaFace Original**: [mk-minchul/AdaFace](https://github.com/mk-minchul/AdaFace) - Original PyTorch implementation
+- **AdaFace ONNX**: [yakhyo/adaface-onnx](https://github.com/yakhyo/adaface-onnx) - ONNX export and inference
+- **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 Segmentation**: [yakhyo/face-segmentation](https://github.com/yakhyo/face-segmentation) - XSeg ONNX Inference
+- **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)
+- **AdaFace**: [AdaFace: Quality Adaptive Margin for Face Recognition](https://arxiv.org/abs/2204.00964)
+- **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)

docs/modules/attributes.md

@@ -0,0 +1,283 @@
+# Attributes
+
+Facial attribute analysis for age, gender, race, and emotion detection.
+
+---
+
+## Available Models
+
+| Model | Attributes | Size | Notes |
+|-------|------------|------|-------|
+| **AgeGender** | Age, Gender | 8 MB | Exact age prediction |
+| **FairFace** | Gender, Age Group, Race | 44 MB | Balanced demographics |
+| **Emotion** | 7-8 emotions | 2 MB | Requires PyTorch |
+
+---
+
+## AgeGender
+
+Predicts exact age and binary gender.
+
+### Basic Usage
+
+```python
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
+
+detector = RetinaFace()
+age_gender = AgeGender()
+
+faces = detector.detect(image)
+
+for face in faces:
+    result = age_gender.predict(image, face.bbox)
+    print(f"Gender: {result.sex}")  # "Female" or "Male"
+    print(f"Age: {result.age} years")
+```
+
+### Output
+
+```python
+# AttributeResult fields
+result.gender     # 0=Female, 1=Male
+result.sex        # "Female" or "Male" (property)
+result.age        # int, age in years
+result.age_group  # None (not provided by this model)
+result.race       # None (not provided by this model)
+```
+
+---
+
+## FairFace
+
+Predicts gender, age group, and race with balanced demographics.
+
+### Basic Usage
+
+```python
+from uniface.attribute import FairFace
+from uniface.detection import RetinaFace
+
+detector = RetinaFace()
+fairface = FairFace()
+
+faces = detector.detect(image)
+
+for face in faces:
+    result = fairface.predict(image, face.bbox)
+    print(f"Gender: {result.sex}")
+    print(f"Age Group: {result.age_group}")
+    print(f"Race: {result.race}")
+```
+
+### Output
+
+```python
+# AttributeResult fields
+result.gender     # 0=Female, 1=Male
+result.sex        # "Female" or "Male"
+result.age        # None (not provided by this model)
+result.age_group  # "20-29", "30-39", etc.
+result.race       # Race/ethnicity label
+```
+
+### Race Categories
+
+| Label |
+|-------|
+| White |
+| Black |
+| Latino Hispanic |
+| East Asian |
+| Southeast Asian |
+| Indian |
+| Middle Eastern |
+
+### Age Groups
+
+| Group |
+|-------|
+| 0-2 |
+| 3-9 |
+| 10-19 |
+| 20-29 |
+| 30-39 |
+| 40-49 |
+| 50-59 |
+| 60-69 |
+| 70+ |
+
+---
+
+## Emotion
+
+Predicts facial emotions. Requires PyTorch.
+
+!!! warning "Optional Dependency"
+    Emotion detection requires PyTorch. Install with:
+    ```bash
+    pip install torch
+    ```
+
+### Basic Usage
+
+```python
+from uniface.detection import RetinaFace
+from uniface.attribute import Emotion
+from uniface.constants import DDAMFNWeights
+
+detector = RetinaFace()
+emotion = Emotion(model_name=DDAMFNWeights.AFFECNET7)
+
+faces = detector.detect(image)
+
+for face in faces:
+    result = emotion.predict(image, face.landmarks)
+    print(f"Emotion: {result.emotion}")
+    print(f"Confidence: {result.confidence:.2%}")
+```
+
+### Emotion Classes
+
+=== "7-Class (AFFECNET7)"
+
+    | Label |
+    |-------|
+    | Neutral |
+    | Happy |
+    | Sad |
+    | Surprise |
+    | Fear |
+    | Disgust |
+    | Angry |
+
+=== "8-Class (AFFECNET8)"
+
+    | Label |
+    |-------|
+    | Neutral |
+    | Happy |
+    | Sad |
+    | Surprise |
+    | Fear |
+    | Disgust |
+    | Angry |
+    | Contempt |
+
+### Model Variants
+
+```python
+from uniface.attribute import Emotion
+from uniface.constants import DDAMFNWeights
+
+# 7-class emotion
+emotion = Emotion(model_name=DDAMFNWeights.AFFECNET7)
+
+# 8-class emotion
+emotion = Emotion(model_name=DDAMFNWeights.AFFECNET8)
+```
+
+---
+
+## Combining Models
+
+### Full Attribute Analysis
+
+```python
+from uniface.attribute import AgeGender, FairFace
+from uniface.detection import RetinaFace
+
+detector = RetinaFace()
+age_gender = AgeGender()
+fairface = FairFace()
+
+faces = detector.detect(image)
+
+for face in faces:
+    # Get exact age from AgeGender
+    ag_result = age_gender.predict(image, face.bbox)
+
+    # Get race from FairFace
+    ff_result = fairface.predict(image, face.bbox)
+
+    print(f"Gender: {ag_result.sex}")
+    print(f"Exact Age: {ag_result.age}")
+    print(f"Age Group: {ff_result.age_group}")
+    print(f"Race: {ff_result.race}")
+```
+
+### Using FaceAnalyzer
+
+```python
+from uniface.analyzer import FaceAnalyzer
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
+
+analyzer = FaceAnalyzer(
+    RetinaFace(),
+    age_gender=AgeGender(),
+)
+
+faces = analyzer.analyze(image)
+
+for face in faces:
+    print(f"Age: {face.age}, Gender: {face.sex}")
+```
+
+---
+
+## Visualization
+
+```python
+import cv2
+
+def draw_attributes(image, face, result):
+    """Draw attributes on image."""
+    x1, y1, x2, y2 = map(int, face.bbox)
+
+    # Draw bounding box
+    cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+    # Build label
+    label = f"{result.sex}"
+    if result.age:
+        label += f", {result.age}y"
+    if result.age_group:
+        label += f", {result.age_group}"
+    if result.race:
+        label += f", {result.race}"
+
+    # Draw label
+    cv2.putText(
+        image, label, (x1, y1 - 10),
+        cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2
+    )
+
+    return image
+
+# Usage
+for face in faces:
+    result = age_gender.predict(image, face.bbox)
+    image = draw_attributes(image, face, result)
+
+cv2.imwrite("attributes.jpg", image)
+```
+
+---
+
+## Accuracy Notes
+
+!!! note "Model Limitations"
+    - **AgeGender**: Trained on CelebA; accuracy varies by demographic
+    - **FairFace**: Trained for balanced demographics; better cross-racial accuracy
+    - **Emotion**: Accuracy depends on facial expression clarity
+
+    Always test on your specific use case and consider cultural context.
+
+---
+
+## Next Steps
+
+- [Parsing](parsing.md) - Face semantic segmentation
+- [Gaze](gaze.md) - Gaze estimation
+- [Image Pipeline Recipe](../recipes/image-pipeline.md) - Complete workflow

docs/modules/detection.md

@@ -0,0 +1,293 @@
+# Detection
+
+Face detection is the first step in any face analysis pipeline. UniFace provides four detection models.
+
+---
+
+## Available Models
+
+| Model | Backbone | Size | Easy | Medium | Hard | Landmarks |
+|-------|----------|------|------|--------|------|:---------:|
+| **RetinaFace** | MobileNet V2 | 3.5 MB | 91.7% | 91.0% | 86.6% | :material-check: |
+| **SCRFD** | SCRFD-10G | 17 MB | 95.2% | 93.9% | 83.1% | :material-check: |
+| **YOLOv5-Face** | YOLOv5s | 28 MB | 94.3% | 92.6% | 83.2% | :material-check: |
+| **YOLOv8-Face** | YOLOv8n | 12 MB | 94.6% | 92.3% | 79.6% | :material-check: |
+
+!!! note "Dataset"
+    All models trained on WIDERFACE dataset.
+---
+
+## RetinaFace
+
+Single-shot face detector with multi-scale feature pyramid.
+
+### Basic Usage
+
+```python
+from uniface.detection import RetinaFace
+
+detector = RetinaFace()
+faces = detector.detect(image)
+
+for face in faces:
+    print(f"Confidence: {face.confidence:.2f}")
+    print(f"BBox: {face.bbox}")
+    print(f"Landmarks: {face.landmarks.shape}")  # (5, 2)
+```
+
+### Model Variants
+
+```python
+from uniface.detection import RetinaFace
+from uniface.constants import RetinaFaceWeights
+
+# Lightweight (mobile/edge)
+detector = RetinaFace(model_name=RetinaFaceWeights.MNET_025)
+
+# Balanced (default)
+detector = RetinaFace(model_name=RetinaFaceWeights.MNET_V2)
+
+# High accuracy
+detector = RetinaFace(model_name=RetinaFaceWeights.RESNET34)
+```
+
+| Variant | Params | Size | Easy | Medium | Hard |
+|---------|--------|------|------|--------|------|
+| MNET_025 | 0.4M | 1.7 MB | 88.5% | 87.0% | 80.6% |
+| MNET_050 | 1.0M | 2.6 MB | 89.4% | 88.0% | 82.4% |
+| MNET_V1 | 3.5M | 3.8 MB | 90.6% | 89.1% | 84.1% |
+| **MNET_V2** :material-check-circle: | 3.2M | 3.5 MB | 91.7% | 91.0% | 86.6% |
+| RESNET18 | 11.7M | 27 MB | 92.5% | 91.0% | 86.6% |
+| RESNET34 | 24.8M | 56 MB | 94.2% | 93.1% | 88.9% |
+
+### Configuration
+
+```python
+detector = RetinaFace(
+    model_name=RetinaFaceWeights.MNET_V2,
+    confidence_threshold=0.5,  # Min confidence
+    nms_threshold=0.4,         # NMS IoU threshold
+    input_size=(640, 640),     # Input resolution
+    dynamic_size=False,        # Enable dynamic input size
+    providers=None,            # Auto-detect, or ['CPUExecutionProvider']
+)
+```
+
+---
+
+## SCRFD
+
+State-of-the-art detection with excellent accuracy-speed tradeoff.
+
+### Basic Usage
+
+```python
+from uniface.detection import SCRFD
+
+detector = SCRFD()
+faces = detector.detect(image)
+```
+
+### Model Variants
+
+```python
+from uniface.detection import SCRFD
+from uniface.constants import SCRFDWeights
+
+# Real-time (lightweight)
+detector = SCRFD(model_name=SCRFDWeights.SCRFD_500M_KPS)
+
+# High accuracy (default)
+detector = SCRFD(model_name=SCRFDWeights.SCRFD_10G_KPS)
+```
+
+| Variant | Params | Size | Easy | Medium | Hard |
+|---------|--------|------|------|--------|------|
+| SCRFD_500M_KPS | 0.6M | 2.5 MB | 90.6% | 88.1% | 68.5% |
+| **SCRFD_10G_KPS** :material-check-circle: | 4.2M | 17 MB | 95.2% | 93.9% | 83.1% |
+
+### Configuration
+
+```python
+detector = SCRFD(
+    model_name=SCRFDWeights.SCRFD_10G_KPS,
+    confidence_threshold=0.5,
+    nms_threshold=0.4,
+    input_size=(640, 640),
+    providers=None,  # Auto-detect, or ['CPUExecutionProvider']
+)
+```
+
+---
+
+## YOLOv5-Face
+
+YOLO-based detection optimized for faces.
+
+### Basic Usage
+
+```python
+from uniface.detection import YOLOv5Face
+
+detector = YOLOv5Face()
+faces = detector.detect(image)
+```
+
+### Model Variants
+
+```python
+from uniface.detection import YOLOv5Face
+from uniface.constants import YOLOv5FaceWeights
+
+# Lightweight
+detector = YOLOv5Face(model_name=YOLOv5FaceWeights.YOLOV5N)
+
+# Balanced (default)
+detector = YOLOv5Face(model_name=YOLOv5FaceWeights.YOLOV5S)
+
+# High accuracy
+detector = YOLOv5Face(model_name=YOLOv5FaceWeights.YOLOV5M)
+```
+
+| Variant | Size | Easy | Medium | Hard |
+|---------|------|------|--------|------|
+| YOLOV5N | 11 MB | 93.6% | 91.5% | 80.5% |
+| **YOLOV5S** :material-check-circle: | 28 MB | 94.3% | 92.6% | 83.2% |
+| YOLOV5M | 82 MB | 95.3% | 93.8% | 85.3% |
+
+!!! note "Fixed Input Size"
+    YOLOv5-Face uses a fixed input size of 640×640.
+
+### Configuration
+
+```python
+detector = YOLOv5Face(
+    model_name=YOLOv5FaceWeights.YOLOV5S,
+    confidence_threshold=0.6,
+    nms_threshold=0.5,
+    nms_mode='numpy',  # or 'torchvision' for faster NMS
+    providers=None,    # Auto-detect, or ['CPUExecutionProvider']
+)
+```
+
+---
+
+## YOLOv8-Face
+
+Anchor-free detection with DFL (Distribution Focal Loss) for accurate bbox regression.
+
+### Basic Usage
+
+```python
+from uniface.detection import YOLOv8Face
+
+detector = YOLOv8Face()
+faces = detector.detect(image)
+```
+
+### Model Variants
+
+```python
+from uniface.detection import YOLOv8Face
+from uniface.constants import YOLOv8FaceWeights
+
+# Lightweight
+detector = YOLOv8Face(model_name=YOLOv8FaceWeights.YOLOV8_LITE_S)
+
+# Recommended (default)
+detector = YOLOv8Face(model_name=YOLOv8FaceWeights.YOLOV8N)
+```
+
+| Variant | Size | Easy | Medium | Hard |
+|---------|------|------|--------|------|
+| YOLOV8_LITE_S | 7.4 MB | 93.4% | 91.2% | 78.6% |
+| **YOLOV8N** :material-check-circle: | 12 MB | 94.6% | 92.3% | 79.6% |
+
+!!! note "Fixed Input Size"
+    YOLOv8-Face uses a fixed input size of 640×640.
+
+### Configuration
+
+```python
+detector = YOLOv8Face(
+    model_name=YOLOv8FaceWeights.YOLOV8N,
+    confidence_threshold=0.5,
+    nms_threshold=0.45,
+    nms_mode='numpy',  # or 'torchvision' for faster NMS
+    providers=None,    # Auto-detect, or ['CPUExecutionProvider']
+)
+```
+
+---
+
+## Factory Function
+
+Create detectors dynamically:
+
+```python
+from uniface.detection import create_detector
+
+detector = create_detector('retinaface')
+# or
+detector = create_detector('scrfd')
+# or
+detector = create_detector('yolov5face')
+# or
+detector = create_detector('yolov8face')
+```
+
+---
+
+## Output Format
+
+All detectors return `list[Face]`:
+
+```python
+for face in faces:
+    # Bounding box [x1, y1, x2, y2]
+    bbox = face.bbox
+
+    # Detection confidence (0-1)
+    confidence = face.confidence
+
+    # 5-point landmarks (5, 2)
+    landmarks = face.landmarks
+    # [left_eye, right_eye, nose, left_mouth, right_mouth]
+```
+
+---
+
+## Visualization
+
+```python
+from uniface.draw import draw_detections
+
+draw_detections(
+    image=image,
+    bboxes=[f.bbox for f in faces],
+    scores=[f.confidence for f in faces],
+    landmarks=[f.landmarks for f in faces],
+    vis_threshold=0.6
+)
+
+cv2.imwrite("result.jpg", image)
+```
+
+---
+
+## Performance Comparison
+
+Benchmark on your hardware:
+
+```bash
+python tools/detect.py --source image.jpg
+```
+
+---
+
+## See Also
+
+- [Recognition Module](recognition.md) - Extract embeddings from detected faces
+- [Landmarks Module](landmarks.md) - Get 106-point landmarks
+- [Image Pipeline Recipe](../recipes/image-pipeline.md) - Complete detection workflow
+- [Concepts: Thresholds](../concepts/thresholds-calibration.md) - Tuning detection parameters

docs/modules/gaze.md

@@ -0,0 +1,272 @@
+# Gaze Estimation
+
+Gaze estimation predicts where a person is looking (pitch and yaw angles).
+
+---
+
+## Available Models
+
+| Model | Backbone | Size | MAE* |
+|-------|----------|------|------|
+| ResNet18 | ResNet18 | 43 MB | 12.84° |
+| **ResNet34** :material-check-circle: | ResNet34 | 82 MB | 11.33° |
+| ResNet50 | ResNet50 | 91 MB | 11.34° |
+| MobileNetV2 | MobileNetV2 | 9.6 MB | 13.07° |
+| MobileOne-S0 | MobileOne | 4.8 MB | 12.58° |
+
+*MAE = Mean Absolute Error on Gaze360 test set (lower is better)
+
+---
+
+## Basic Usage
+
+```python
+import cv2
+import numpy as np
+from uniface.detection import RetinaFace
+from uniface.gaze import MobileGaze
+
+detector = RetinaFace()
+gaze_estimator = MobileGaze()
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+for face in faces:
+    # Crop face
+    x1, y1, x2, y2 = map(int, face.bbox)
+    face_crop = image[y1:y2, x1:x2]
+
+    if face_crop.size > 0:
+        # Estimate gaze
+        result = gaze_estimator.estimate(face_crop)
+
+        # Convert to degrees
+        pitch_deg = np.degrees(result.pitch)
+        yaw_deg = np.degrees(result.yaw)
+
+        print(f"Pitch: {pitch_deg:.1f}°, Yaw: {yaw_deg:.1f}°")
+```
+
+---
+
+## Model Variants
+
+```python
+from uniface.gaze import MobileGaze
+from uniface.constants import GazeWeights
+
+# Default (ResNet34, recommended)
+gaze = MobileGaze()
+
+# Lightweight for mobile/edge
+gaze = MobileGaze(model_name=GazeWeights.MOBILEONE_S0)
+
+# Higher accuracy
+gaze = MobileGaze(model_name=GazeWeights.RESNET50)
+```
+
+---
+
+## Output Format
+
+```python
+result = gaze_estimator.estimate(face_crop)
+
+# GazeResult dataclass
+result.pitch  # Vertical angle in radians
+result.yaw    # Horizontal angle in radians
+```
+
+### Angle Convention
+
+```
+          pitch = +90° (looking up)
+               │
+               │
+yaw = -90° ────┼──── yaw = +90°
+(looking left) │     (looking right)
+               │
+          pitch = -90° (looking down)
+```
+
+- **Pitch**: Vertical gaze angle
+  - Positive = looking up
+  - Negative = looking down
+
+- **Yaw**: Horizontal gaze angle
+  - Positive = looking right
+  - Negative = looking left
+
+---
+
+## Visualization
+
+```python
+from uniface.draw import draw_gaze
+
+# Detect faces
+faces = detector.detect(image)
+
+for face in faces:
+    x1, y1, x2, y2 = map(int, face.bbox)
+    face_crop = image[y1:y2, x1:x2]
+
+    if face_crop.size > 0:
+        result = gaze_estimator.estimate(face_crop)
+
+        # Draw gaze arrow on image
+        draw_gaze(image, face.bbox, result.pitch, result.yaw)
+
+cv2.imwrite("gaze_output.jpg", image)
+```
+
+### Custom Visualization
+
+```python
+import cv2
+import numpy as np
+
+def draw_gaze_custom(image, bbox, pitch, yaw, length=100, color=(0, 255, 0)):
+    """Draw custom gaze arrow."""
+    x1, y1, x2, y2 = map(int, bbox)
+
+    # Face center
+    cx = (x1 + x2) // 2
+    cy = (y1 + y2) // 2
+
+    # Calculate endpoint
+    dx = -length * np.sin(yaw) * np.cos(pitch)
+    dy = -length * np.sin(pitch)
+
+    # Draw arrow
+    end_x = int(cx + dx)
+    end_y = int(cy + dy)
+
+    cv2.arrowedLine(image, (cx, cy), (end_x, end_y), color, 2, tipLength=0.3)
+
+    return image
+```
+
+---
+
+## Real-Time Gaze Tracking
+
+```python
+import cv2
+import numpy as np
+from uniface.detection import RetinaFace
+from uniface.gaze import MobileGaze
+from uniface.draw import draw_gaze
+
+detector = RetinaFace()
+gaze_estimator = MobileGaze()
+
+cap = cv2.VideoCapture(0)
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+
+    for face in faces:
+        x1, y1, x2, y2 = map(int, face.bbox)
+        face_crop = frame[y1:y2, x1:x2]
+
+        if face_crop.size > 0:
+            result = gaze_estimator.estimate(face_crop)
+
+            # Draw bounding box
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+            # Draw gaze
+            draw_gaze(frame, face.bbox, result.pitch, result.yaw)
+
+            # Display angles
+            pitch_deg = np.degrees(result.pitch)
+            yaw_deg = np.degrees(result.yaw)
+            label = f"P:{pitch_deg:.0f} Y:{yaw_deg:.0f}"
+            cv2.putText(frame, label, (x1, y1 - 10),
+                       cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+
+    cv2.imshow("Gaze Estimation", frame)
+
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+---
+
+## Use Cases
+
+### Attention Detection
+
+```python
+def is_looking_at_camera(result, threshold=15):
+    """Check if person is looking at camera."""
+    pitch_deg = abs(np.degrees(result.pitch))
+    yaw_deg = abs(np.degrees(result.yaw))
+
+    return pitch_deg < threshold and yaw_deg < threshold
+
+# Usage
+result = gaze_estimator.estimate(face_crop)
+if is_looking_at_camera(result):
+    print("Looking at camera")
+else:
+    print("Looking away")
+```
+
+### Gaze Direction Classification
+
+```python
+def classify_gaze_direction(result, threshold=20):
+    """Classify gaze into directions."""
+    pitch_deg = np.degrees(result.pitch)
+    yaw_deg = np.degrees(result.yaw)
+
+    directions = []
+
+    if pitch_deg > threshold:
+        directions.append("up")
+    elif pitch_deg < -threshold:
+        directions.append("down")
+
+    if yaw_deg > threshold:
+        directions.append("right")
+    elif yaw_deg < -threshold:
+        directions.append("left")
+
+    if not directions:
+        return "center"
+
+    return " ".join(directions)
+
+# Usage
+result = gaze_estimator.estimate(face_crop)
+direction = classify_gaze_direction(result)
+print(f"Looking: {direction}")
+```
+
+---
+
+## Factory Function
+
+```python
+from uniface.gaze import create_gaze_estimator
+
+gaze = create_gaze_estimator()  # Returns MobileGaze
+```
+
+---
+
+## Next Steps
+
+- [Anti-Spoofing](spoofing.md) - Face liveness detection
+- [Privacy](privacy.md) - Face anonymization
+- [Video Recipe](../recipes/video-webcam.md) - Real-time processing

docs/modules/indexing.md

@@ -0,0 +1,172 @@
+# Indexing
+
+FAISS-backed vector store for fast similarity search over embeddings.
+
+!!! info "Optional dependency"
+    ```bash
+    pip install faiss-cpu
+    ```
+
+---
+
+## FAISS
+
+```python
+from uniface.indexing import FAISS
+```
+
+A thin wrapper around a FAISS `IndexFlatIP` (inner-product) index. Vectors
+**must** be L2-normalised before adding so that inner product equals cosine
+similarity. The store does not normalise internally.
+
+Each vector is paired with a metadata `dict` that can carry any
+JSON-serialisable payload (person ID, name, source path, etc.).
+
+### Constructor
+
+```python
+store = FAISS(embedding_size=512, db_path="./vector_index")
+```
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `embedding_size` | `int` | `512` | Dimension of embedding vectors |
+| `db_path` | `str` | `"./vector_index"` | Directory for persisting index and metadata |
+
+---
+
+### Methods
+
+#### `add(embedding, metadata)`
+
+Add a single embedding with associated metadata.
+
+```python
+store.add(embedding, {"person_id": "alice", "source": "photo.jpg"})
+```
+
+| Parameter | Type | Description |
+|-----------|------|-------------|
+| `embedding` | `np.ndarray` | L2-normalised embedding vector |
+| `metadata` | `dict[str, Any]` | Arbitrary JSON-serialisable key-value pairs |
+
+---
+
+#### `search(embedding, threshold=0.4)`
+
+Find the closest match for a query embedding.
+
+```python
+result, similarity = store.search(query_embedding, threshold=0.4)
+if result:
+    print(result["person_id"], similarity)
+```
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `embedding` | `np.ndarray` | — | L2-normalised query vector |
+| `threshold` | `float` | `0.4` | Minimum cosine similarity to accept a match |
+
+**Returns:** `(metadata, similarity)` if a match is found, or `(None, similarity)` when below threshold or the index is empty.
+
+---
+
+#### `remove(key, value)`
+
+Remove all entries where `metadata[key] == value` and rebuild the index.
+
+```python
+removed = store.remove("person_id", "bob")
+print(f"Removed {removed} entries")
+```
+
+| Parameter | Type | Description |
+|-----------|------|-------------|
+| `key` | `str` | Metadata key to match |
+| `value` | `Any` | Value to match |
+
+**Returns:** Number of entries removed.
+
+---
+
+#### `save()`
+
+Persist the FAISS index and metadata to disk.
+
+```python
+store.save()
+```
+
+Writes two files to `db_path`:
+
+- `faiss_index.bin` — binary FAISS index
+- `metadata.json` — JSON array of metadata dicts
+
+---
+
+#### `load()`
+
+Load a previously saved index and metadata.
+
+```python
+store = FAISS(db_path="./vector_index")
+loaded = store.load()  # True if files exist
+```
+
+**Returns:** `True` if loaded successfully, `False` if files are missing.
+
+**Raises:** `RuntimeError` if files exist but cannot be read.
+
+---
+
+### Properties
+
+| Property | Type | Description |
+|----------|------|-------------|
+| `size` | `int` | Number of vectors in the index |
+| `len(store)` | `int` | Same as `size` |
+
+---
+
+## Example: End-to-End
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+from uniface.indexing import FAISS
+
+detector = RetinaFace()
+recognizer = ArcFace()
+
+# Build
+store = FAISS(db_path="./my_index")
+
+image = cv2.imread("alice.jpg")
+faces = detector.detect(image)
+embedding = recognizer.get_normalized_embedding(image, faces[0].landmarks)
+store.add(embedding, {"person_id": "alice"})
+store.save()
+
+# Search
+store2 = FAISS(db_path="./my_index")
+store2.load()
+
+query = cv2.imread("unknown.jpg")
+faces = detector.detect(query)
+emb = recognizer.get_normalized_embedding(query, faces[0].landmarks)
+
+result, sim = store2.search(emb)
+if result:
+    print(f"Matched: {result['person_id']} (similarity: {sim:.3f})")
+else:
+    print(f"No match (similarity: {sim:.3f})")
+```
+
+---
+
+## See Also
+
+- [Face Search Recipe](../recipes/face-search.md) - Building and querying indexes
+- [Recognition Module](recognition.md) - Embedding extraction
+- [Thresholds Guide](../concepts/thresholds-calibration.md) - Tuning similarity thresholds

docs/modules/landmarks.md

@@ -0,0 +1,252 @@
+# Landmarks
+
+Facial landmark detection provides precise localization of facial features.
+
+---
+
+## Available Models
+
+| Model | Points | Size |
+|-------|--------|------|
+| **Landmark106** | 106 | 14 MB |
+
+!!! info "5-Point Landmarks"
+    Basic 5-point landmarks are included with all detection models (RetinaFace, SCRFD, YOLOv5-Face, YOLOv8-Face).
+
+---
+
+## 106-Point Landmarks
+
+### Basic Usage
+
+```python
+from uniface.detection import RetinaFace
+from uniface.landmark import Landmark106
+
+detector = RetinaFace()
+landmarker = Landmark106()
+
+# Detect face
+faces = detector.detect(image)
+
+# Get detailed landmarks
+if faces:
+    landmarks = landmarker.get_landmarks(image, faces[0].bbox)
+    print(f"Landmarks shape: {landmarks.shape}")  # (106, 2)
+```
+
+### Landmark Groups
+
+| Range | Group | Points |
+|-------|-------|--------|
+| 0-32 | Face Contour | 33 |
+| 33-50 | Eyebrows | 18 |
+| 51-62 | Nose | 12 |
+| 63-86 | Eyes | 24 |
+| 87-105 | Mouth | 19 |
+
+### Extract Specific Features
+
+```python
+landmarks = landmarker.get_landmarks(image, face.bbox)
+
+# Face contour
+contour = landmarks[0:33]
+
+# Left eyebrow
+left_eyebrow = landmarks[33:42]
+
+# Right eyebrow
+right_eyebrow = landmarks[42:51]
+
+# Nose
+nose = landmarks[51:63]
+
+# Left eye
+left_eye = landmarks[63:72]
+
+# Right eye
+right_eye = landmarks[76:84]
+
+# Mouth
+mouth = landmarks[87:106]
+```
+
+---
+
+## 5-Point Landmarks (Detection)
+
+All detection models provide 5-point landmarks:
+
+```python
+from uniface.detection import RetinaFace
+
+detector = RetinaFace()
+faces = detector.detect(image)
+
+if faces:
+    landmarks_5 = faces[0].landmarks
+    print(f"Shape: {landmarks_5.shape}")  # (5, 2)
+
+    left_eye = landmarks_5[0]
+    right_eye = landmarks_5[1]
+    nose = landmarks_5[2]
+    left_mouth = landmarks_5[3]
+    right_mouth = landmarks_5[4]
+```
+
+---
+
+## Visualization
+
+### Draw 106 Landmarks
+
+```python
+import cv2
+
+def draw_landmarks(image, landmarks, color=(0, 255, 0), radius=2):
+    """Draw landmarks on image."""
+    for x, y in landmarks.astype(int):
+        cv2.circle(image, (x, y), radius, color, -1)
+    return image
+
+# Usage
+landmarks = landmarker.get_landmarks(image, face.bbox)
+image_with_landmarks = draw_landmarks(image.copy(), landmarks)
+cv2.imwrite("landmarks.jpg", image_with_landmarks)
+```
+
+### Draw with Connections
+
+```python
+def draw_landmarks_with_connections(image, landmarks):
+    """Draw landmarks with facial feature connections."""
+    landmarks = landmarks.astype(int)
+
+    # Face contour (0-32)
+    for i in range(32):
+        cv2.line(image, tuple(landmarks[i]), tuple(landmarks[i+1]), (255, 255, 0), 1)
+
+    # Left eyebrow (33-41)
+    for i in range(33, 41):
+        cv2.line(image, tuple(landmarks[i]), tuple(landmarks[i+1]), (0, 255, 0), 1)
+
+    # Right eyebrow (42-50)
+    for i in range(42, 50):
+        cv2.line(image, tuple(landmarks[i]), tuple(landmarks[i+1]), (0, 255, 0), 1)
+
+    # Nose (51-62)
+    for i in range(51, 62):
+        cv2.line(image, tuple(landmarks[i]), tuple(landmarks[i+1]), (0, 0, 255), 1)
+
+    # Draw points
+    for x, y in landmarks:
+        cv2.circle(image, (x, y), 2, (0, 255, 255), -1)
+
+    return image
+```
+
+---
+
+## Use Cases
+
+### Face Alignment
+
+```python
+from uniface.face_utils import face_alignment
+
+# Align face using 5-point landmarks
+aligned = face_alignment(image, faces[0].landmarks)
+# Returns: 112x112 aligned face
+```
+
+### Eye Aspect Ratio (Blink Detection)
+
+```python
+import numpy as np
+
+def eye_aspect_ratio(eye_landmarks):
+    """Calculate eye aspect ratio for blink detection."""
+    # Vertical distances
+    v1 = np.linalg.norm(eye_landmarks[1] - eye_landmarks[5])
+    v2 = np.linalg.norm(eye_landmarks[2] - eye_landmarks[4])
+
+    # Horizontal distance
+    h = np.linalg.norm(eye_landmarks[0] - eye_landmarks[3])
+
+    ear = (v1 + v2) / (2.0 * h)
+    return ear
+
+# Usage with 106-point landmarks
+left_eye = landmarks[63:72]  # Approximate eye points
+ear = eye_aspect_ratio(left_eye)
+
+if ear < 0.2:
+    print("Eye closed (blink detected)")
+```
+
+### Head Pose Estimation
+
+```python
+import cv2
+import numpy as np
+
+def estimate_head_pose(landmarks, image_shape):
+    """Estimate head pose from facial landmarks."""
+    # 3D model points (generic face model)
+    model_points = np.array([
+        (0.0, 0.0, 0.0),       # Nose tip
+        (0.0, -330.0, -65.0),  # Chin
+        (-225.0, 170.0, -135.0),  # Left eye corner
+        (225.0, 170.0, -135.0),   # Right eye corner
+        (-150.0, -150.0, -125.0), # Left mouth corner
+        (150.0, -150.0, -125.0)   # Right mouth corner
+    ], dtype=np.float64)
+
+    # 2D image points (from 106 landmarks)
+    image_points = np.array([
+        landmarks[51],   # Nose tip
+        landmarks[16],   # Chin
+        landmarks[63],   # Left eye corner
+        landmarks[76],   # Right eye corner
+        landmarks[87],   # Left mouth corner
+        landmarks[93]    # Right mouth corner
+    ], dtype=np.float64)
+
+    # Camera matrix
+    h, w = image_shape[:2]
+    focal_length = w
+    center = (w / 2, h / 2)
+    camera_matrix = np.array([
+        [focal_length, 0, center[0]],
+        [0, focal_length, center[1]],
+        [0, 0, 1]
+    ], dtype=np.float64)
+
+    # Solve PnP
+    dist_coeffs = np.zeros((4, 1))
+    success, rotation_vector, translation_vector = cv2.solvePnP(
+        model_points, image_points, camera_matrix, dist_coeffs
+    )
+
+    return rotation_vector, translation_vector
+```
+
+---
+
+## Factory Function
+
+```python
+from uniface.landmark import create_landmarker
+
+landmarker = create_landmarker()  # Returns Landmark106
+```
+
+---
+
+## See Also
+
+- [Detection Module](detection.md) - Face detection with 5-point landmarks
+- [Attributes Module](attributes.md) - Age, gender, emotion
+- [Gaze Module](gaze.md) - Gaze estimation
+- [Concepts: Coordinate Systems](../concepts/coordinate-systems.md) - Landmark formats

docs/modules/parsing.md

@@ -0,0 +1,333 @@
+# Parsing
+
+Face parsing segments faces into semantic components or face regions.
+
+---
+
+## Available Models
+
+| Model | Backbone | Size | Output |
+|-------|----------|------|--------|
+| **BiSeNet ResNet18** :material-check-circle: | ResNet18 | 51 MB | 19 classes |
+| BiSeNet ResNet34 | ResNet34 | 89 MB | 19 classes |
+| XSeg | - | 67 MB | Mask |
+
+---
+
+## Basic Usage
+
+```python
+import cv2
+from uniface.parsing import BiSeNet
+from uniface.draw import vis_parsing_maps
+
+# Initialize parser
+parser = BiSeNet()
+
+# Load face image (cropped)
+face_image = cv2.imread("face.jpg")
+
+# Parse face
+mask = parser.parse(face_image)
+print(f"Mask shape: {mask.shape}")  # (H, W)
+
+# Visualize
+face_rgb = cv2.cvtColor(face_image, cv2.COLOR_BGR2RGB)
+vis_result = vis_parsing_maps(face_rgb, mask, save_image=False)
+
+# Save result
+vis_bgr = cv2.cvtColor(vis_result, cv2.COLOR_RGB2BGR)
+cv2.imwrite("parsed.jpg", vis_bgr)
+```
+
+---
+
+## 19 Facial Component Classes
+
+| ID | Class | ID | Class |
+|----|-------|----|-------|
+| 0 | Background | 10 | Nose |
+| 1 | Skin | 11 | Mouth |
+| 2 | Left Eyebrow | 12 | Upper Lip |
+| 3 | Right Eyebrow | 13 | Lower Lip |
+| 4 | Left Eye | 14 | Neck |
+| 5 | Right Eye | 15 | Necklace |
+| 6 | Eyeglasses | 16 | Cloth |
+| 7 | Left Ear | 17 | Hair |
+| 8 | Right Ear | 18 | Hat |
+| 9 | Earring | | |
+
+---
+
+## Model Variants
+
+```python
+from uniface.parsing import BiSeNet
+from uniface.constants import ParsingWeights
+
+# Default (ResNet18)
+parser = BiSeNet()
+
+# Higher accuracy (ResNet34)
+parser = BiSeNet(model_name=ParsingWeights.RESNET34)
+```
+
+| Variant | Params | Size |
+|---------|--------|------|
+| **RESNET18** :material-check-circle: | 13.3M | 51 MB |
+| RESNET34 | 24.1M | 89 MB |
+
+---
+
+## Full Pipeline
+
+### With Face Detection
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.parsing import BiSeNet
+from uniface.draw import vis_parsing_maps
+
+detector = RetinaFace()
+parser = BiSeNet()
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+for i, face in enumerate(faces):
+    # Crop face
+    x1, y1, x2, y2 = map(int, face.bbox)
+    face_crop = image[y1:y2, x1:x2]
+
+    # Parse
+    mask = parser.parse(face_crop)
+
+    # Visualize
+    face_rgb = cv2.cvtColor(face_crop, cv2.COLOR_BGR2RGB)
+    vis_result = vis_parsing_maps(face_rgb, mask, save_image=False)
+
+    # Save
+    vis_bgr = cv2.cvtColor(vis_result, cv2.COLOR_RGB2BGR)
+    cv2.imwrite(f"face_{i}_parsed.jpg", vis_bgr)
+```
+
+---
+
+## Extract Specific Components
+
+### Get Single Component Mask
+
+```python
+import numpy as np
+
+# Parse face
+mask = parser.parse(face_image)
+
+# Extract specific component
+SKIN = 1
+HAIR = 17
+LEFT_EYE = 4
+RIGHT_EYE = 5
+
+# Binary mask for skin
+skin_mask = (mask == SKIN).astype(np.uint8) * 255
+
+# Binary mask for hair
+hair_mask = (mask == HAIR).astype(np.uint8) * 255
+
+# Binary mask for eyes
+eyes_mask = ((mask == LEFT_EYE) | (mask == RIGHT_EYE)).astype(np.uint8) * 255
+```
+
+### Count Pixels per Component
+
+```python
+import numpy as np
+
+mask = parser.parse(face_image)
+
+component_names = {
+    0: 'Background', 1: 'Skin', 2: 'L-Eyebrow', 3: 'R-Eyebrow',
+    4: 'L-Eye', 5: 'R-Eye', 6: 'Eyeglasses', 7: 'L-Ear', 8: 'R-Ear',
+    9: 'Earring', 10: 'Nose', 11: 'Mouth',
+    12: 'U-Lip', 13: 'L-Lip', 14: 'Neck', 15: 'Necklace',
+    16: 'Cloth', 17: 'Hair', 18: 'Hat'
+}
+
+for class_id in np.unique(mask):
+    pixel_count = np.sum(mask == class_id)
+    name = component_names.get(class_id, f'Class {class_id}')
+    print(f"{name}: {pixel_count} pixels")
+```
+
+---
+
+## Applications
+
+### Face Makeup
+
+Apply virtual makeup using component masks:
+
+```python
+import cv2
+import numpy as np
+
+def apply_lip_color(image, mask, color=(180, 50, 50)):
+    """Apply lip color using parsing mask."""
+    result = image.copy()
+
+    # Get lip mask (upper lip=12, lower lip=13)
+    lip_mask = ((mask == 12) | (mask == 13)).astype(np.uint8)
+
+    # Create color overlay
+    overlay = np.zeros_like(image)
+    overlay[:] = color
+
+    # Alpha blend lip region
+    alpha = 0.4
+    mask_3ch = lip_mask[:, :, np.newaxis]
+    result = np.where(mask_3ch, (image * (1 - alpha) + overlay * alpha).astype(np.uint8), result)
+
+    return result
+```
+
+### Background Replacement
+
+```python
+def replace_background(image, mask, background):
+    """Replace background using parsing mask."""
+    # Create foreground mask (everything except background)
+    foreground_mask = (mask != 0).astype(np.uint8)
+
+    # Resize background to match image
+    background = cv2.resize(background, (image.shape[1], image.shape[0]))
+
+    # Combine
+    result = image.copy()
+    result[foreground_mask == 0] = background[foreground_mask == 0]
+
+    return result
+```
+
+### Hair Segmentation
+
+```python
+def get_hair_mask(mask):
+    """Extract clean hair mask."""
+    hair_mask = (mask == 17).astype(np.uint8) * 255
+
+    # Clean up with morphological operations
+    kernel = np.ones((5, 5), np.uint8)
+    hair_mask = cv2.morphologyEx(hair_mask, cv2.MORPH_CLOSE, kernel)
+    hair_mask = cv2.morphologyEx(hair_mask, cv2.MORPH_OPEN, kernel)
+
+    return hair_mask
+```
+
+---
+
+## Visualization Options
+
+```python
+from uniface.draw import vis_parsing_maps
+
+# Default visualization
+vis_result = vis_parsing_maps(face_rgb, mask)
+
+# With different parameters
+vis_result = vis_parsing_maps(
+    face_rgb,
+    mask,
+    save_image=False,  # Don't save to file
+)
+```
+
+---
+
+## XSeg
+
+XSeg outputs a mask for face regions. Unlike BiSeNet which works on bbox crops, XSeg requires 5-point landmarks for face alignment.
+
+### Basic Usage
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.parsing import XSeg
+
+detector = RetinaFace()
+parser = XSeg()
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+for face in faces:
+    if face.landmarks is not None:
+        mask = parser.parse(image, landmarks=face.landmarks)
+        print(f"Mask shape: {mask.shape}")  # (H, W), values in [0, 1]
+```
+
+### Parameters
+
+```python
+from uniface.parsing import XSeg
+
+# Default settings
+parser = XSeg()
+
+# Custom settings
+parser = XSeg(
+    align_size=256,   # Face alignment size
+    blur_sigma=5,     # Gaussian blur for smoothing (0 = raw)
+)
+```
+
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `align_size` | 256 | Face alignment output size |
+| `blur_sigma` | 0 | Mask smoothing (0 = no blur) |
+
+### Methods
+
+```python
+# Full pipeline: align -> segment -> warp back to original space
+mask = parser.parse(image, landmarks=landmarks)
+
+# For pre-aligned face crops
+mask = parser.parse_aligned(face_crop)
+
+# Get mask + crop + inverse matrix for custom warping
+mask, face_crop, inverse_matrix = parser.parse_with_inverse(image, landmarks)
+```
+
+### BiSeNet vs XSeg
+
+| Feature | BiSeNet | XSeg |
+|---------|---------|------|
+| Output | 19 class labels | Mask [0, 1] |
+| Input | Bbox crop | Requires landmarks |
+| Use case | Facial components | Face region extraction |
+
+---
+
+## Factory Function
+
+```python
+from uniface.parsing import create_face_parser
+from uniface.constants import ParsingWeights, XSegWeights
+
+# BiSeNet (default)
+parser = create_face_parser()
+
+# XSeg
+parser = create_face_parser(XSegWeights.DEFAULT)
+```
+
+---
+
+## Next Steps
+
+- [Gaze](gaze.md) - Gaze estimation
+- [Privacy](privacy.md) - Face anonymization
+- [Detection](detection.md) - Face detection

docs/modules/privacy.md

@@ -0,0 +1,260 @@
+# Privacy
+
+Face anonymization protects privacy by blurring or obscuring faces in images and videos.
+
+---
+
+## Available Methods
+
+| Method | Description |
+|--------|-------------|
+| **pixelate** | Blocky pixelation |
+| **gaussian** | Smooth blur |
+| **blackout** | Solid color fill |
+| **elliptical** | Oval-shaped blur |
+| **median** | Edge-preserving blur |
+
+---
+
+## Quick Start
+
+```python
+from uniface.detection import RetinaFace
+from uniface.privacy import BlurFace
+import cv2
+
+detector = RetinaFace()
+blurrer = BlurFace(method='gaussian', blur_strength=5.0)
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+anonymized = blurrer.anonymize(image, faces)
+
+cv2.imwrite("anonymized.jpg", anonymized)
+```
+
+---
+
+## Blur Methods
+
+### Pixelate
+
+Blocky pixelation effect (common in news media):
+
+```python
+blurrer = BlurFace(method='pixelate', pixel_blocks=15)
+```
+
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `pixel_blocks` | 15 | Number of blocks (lower = more pixelated) |
+
+### Gaussian
+
+Smooth, natural-looking blur:
+
+```python
+blurrer = BlurFace(method='gaussian', blur_strength=3.0)
+```
+
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `blur_strength` | 3.0 | Blur intensity (higher = more blur) |
+
+### Blackout
+
+Solid color fill for maximum privacy:
+
+```python
+blurrer = BlurFace(method='blackout', color=(0, 0, 0))
+```
+
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `color` | (0, 0, 0) | Fill color (BGR format) |
+
+### Elliptical
+
+Oval-shaped blur matching natural face shape:
+
+```python
+blurrer = BlurFace(method='elliptical', blur_strength=3.0, margin=20)
+```
+
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `blur_strength` | 3.0 | Blur intensity |
+| `margin` | 20 | Margin around face |
+
+### Median
+
+Edge-preserving blur with artistic effect:
+
+```python
+blurrer = BlurFace(method='median', blur_strength=3.0)
+```
+
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `blur_strength` | 3.0 | Blur intensity |
+
+---
+
+## In-Place Processing
+
+Modify image directly (faster, saves memory):
+
+```python
+blurrer = BlurFace(method='pixelate')
+
+# In-place modification
+result = blurrer.anonymize(image, faces, inplace=True)
+# 'image' and 'result' point to the same array
+```
+
+---
+
+## Real-Time Anonymization
+
+### Webcam
+
+```python
+import cv2
+from uniface.detection 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()
+```
+
+### Video File
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.privacy import BlurFace
+
+detector = RetinaFace()
+blurrer = BlurFace(method='gaussian')
+
+cap = cv2.VideoCapture("input_video.mp4")
+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))
+
+fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+out = cv2.VideoWriter('output_video.mp4', fourcc, fps, (width, height))
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+    frame = blurrer.anonymize(frame, faces, inplace=True)
+    out.write(frame)
+
+cap.release()
+out.release()
+```
+
+---
+
+## Selective Anonymization
+
+### Exclude Specific Faces
+
+```python
+def anonymize_except(image, all_faces, exclude_embeddings, recognizer, threshold=0.6):
+    """Anonymize all faces except those matching exclude_embeddings."""
+    faces_to_blur = []
+
+    for face in all_faces:
+        # Get embedding
+        embedding = recognizer.get_normalized_embedding(image, face.landmarks)
+
+        # Check if should be excluded
+        should_exclude = False
+        for ref_emb in exclude_embeddings:
+            similarity = np.dot(embedding, ref_emb.T)[0][0]
+            if similarity > threshold:
+                should_exclude = True
+                break
+
+        if not should_exclude:
+            faces_to_blur.append(face)
+
+    # Blur remaining faces
+    return blurrer.anonymize(image, faces_to_blur)
+```
+
+### Confidence-Based
+
+```python
+def anonymize_low_confidence(image, faces, blurrer, confidence_threshold=0.8):
+    """Anonymize faces below confidence threshold."""
+    faces_to_blur = [f for f in faces if f.confidence < confidence_threshold]
+    return blurrer.anonymize(image, faces_to_blur)
+```
+
+---
+
+## Comparison
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.privacy import BlurFace
+
+detector = RetinaFace()
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+methods = ['pixelate', 'gaussian', 'blackout', 'elliptical', 'median']
+
+for method in methods:
+    blurrer = BlurFace(method=method)
+    result = blurrer.anonymize(image.copy(), faces)
+    cv2.imwrite(f"anonymized_{method}.jpg", result)
+```
+
+---
+
+## Command-Line Tool
+
+```bash
+# Anonymize image with pixelation
+python tools/anonymize.py --source photo.jpg
+
+# Real-time webcam
+python tools/anonymize.py --source 0 --method gaussian
+
+# Custom blur strength
+python tools/anonymize.py --source photo.jpg --method gaussian --blur-strength 5.0
+```
+
+---
+
+## Next Steps
+
+- [Anonymize Stream Recipe](../recipes/anonymize-stream.md) - Video pipeline
+- [Detection](detection.md) - Face detection options
+- [Batch Processing Recipe](../recipes/batch-processing.md) - Process multiple files

docs/modules/recognition.md

@@ -0,0 +1,301 @@
+# Recognition
+
+Face recognition extracts embeddings for identity verification and face search.
+
+---
+
+## Available Models
+
+| Model | Backbone | Size | Embedding Dim |
+|-------|----------|------|---------------|
+| **AdaFace** | IR-18/IR-101 | 92-249 MB | 512 |
+| **ArcFace** | MobileNet/ResNet | 8-166 MB | 512 |
+| **MobileFace** | MobileNet V2/V3 | 1-10 MB | 512 |
+| **SphereFace** | Sphere20/36 | 50-92 MB | 512 |
+
+---
+
+## AdaFace
+
+Face recognition using adaptive margin based on image quality.
+
+### Basic Usage
+
+```python
+from uniface.detection import RetinaFace
+from uniface.recognition import AdaFace
+
+detector = RetinaFace()
+recognizer = AdaFace()
+
+# Detect face
+faces = detector.detect(image)
+
+# Extract embedding
+if faces:
+    embedding = recognizer.get_normalized_embedding(image, faces[0].landmarks)
+    print(f"Embedding shape: {embedding.shape}")  # (1, 512)
+```
+
+### Model Variants
+
+```python
+from uniface.recognition import AdaFace
+from uniface.constants import AdaFaceWeights
+
+# Lightweight (default)
+recognizer = AdaFace(model_name=AdaFaceWeights.IR_18)
+
+# High accuracy
+recognizer = AdaFace(model_name=AdaFaceWeights.IR_101)
+
+# Force CPU execution
+recognizer = AdaFace(providers=['CPUExecutionProvider'])
+```
+
+| Variant | Dataset | Size | IJB-B | IJB-C |
+|---------|---------|------|-------|-------|
+| **IR_18** :material-check-circle: | WebFace4M | 92 MB | 93.03% | 94.99% |
+| IR_101 | WebFace12M | 249 MB | - | 97.66% |
+
+!!! info "Benchmark Metrics"
+    IJB-B and IJB-C accuracy reported as TAR@FAR=0.01%
+
+---
+
+## ArcFace
+
+Face recognition using additive angular margin loss.
+
+### Basic Usage
+
+```python
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+
+detector = RetinaFace()
+recognizer = ArcFace()
+
+# Detect face
+faces = detector.detect(image)
+
+# Extract embedding
+if faces:
+    embedding = recognizer.get_normalized_embedding(image, faces[0].landmarks)
+    print(f"Embedding shape: {embedding.shape}")  # (1, 512)
+```
+
+### Model Variants
+
+```python
+from uniface.recognition import ArcFace
+from uniface.constants import ArcFaceWeights
+
+# Lightweight (default)
+recognizer = ArcFace(model_name=ArcFaceWeights.MNET)
+
+# High accuracy
+recognizer = ArcFace(model_name=ArcFaceWeights.RESNET)
+
+# Force CPU execution
+recognizer = ArcFace(providers=['CPUExecutionProvider'])
+```
+
+| Variant | Backbone | Size | LFW | CFP-FP | AgeDB-30 | IJB-C |
+|---------|----------|------|-----|--------|----------|-------|
+| **MNET** :material-check-circle: | MobileNet | 8 MB | 99.70% | 98.00% | 96.58% | 95.02% |
+| RESNET | ResNet50 | 166 MB | 99.83% | 99.33% | 98.23% | 97.25% |
+
+!!! info "Training Data & Metrics"
+    **Dataset**: Trained on WebFace600K (600K images)
+
+    **Accuracy**: IJB-C reported as TAR@FAR=1e-4
+
+---
+
+## MobileFace
+
+Lightweight face recognition models with MobileNet backbones.
+
+### Basic Usage
+
+```python
+from uniface.recognition import MobileFace
+
+recognizer = MobileFace()
+embedding = recognizer.get_normalized_embedding(image, landmarks)
+```
+
+### Model Variants
+
+```python
+from uniface.recognition import MobileFace
+from uniface.constants import MobileFaceWeights
+
+# Ultra-lightweight
+recognizer = MobileFace(model_name=MobileFaceWeights.MNET_025)
+
+# Balanced (default)
+recognizer = MobileFace(model_name=MobileFaceWeights.MNET_V2)
+
+# Higher accuracy
+recognizer = MobileFace(model_name=MobileFaceWeights.MNET_V3_LARGE)
+```
+
+| Variant | Params | Size | LFW | CALFW | CPLFW | AgeDB-30 |
+|---------|--------|------|-----|-------|-------|----------|
+| MNET_025 | 0.36M | 1 MB | 98.76% | 92.02% | 82.37% | 90.02% |
+| **MNET_V2** :material-check-circle: | 2.29M | 4 MB | 99.55% | 94.87% | 86.89% | 95.16% |
+| MNET_V3_SMALL | 1.25M | 3 MB | 99.30% | 93.77% | 85.29% | 92.79% |
+| MNET_V3_LARGE | 3.52M | 10 MB | 99.53% | 94.56% | 86.79% | 95.13% |
+
+---
+
+## SphereFace
+
+Face recognition using angular softmax loss (A-Softmax).
+
+### Basic Usage
+
+```python
+from uniface.recognition import SphereFace
+from uniface.constants import SphereFaceWeights
+
+recognizer = SphereFace(model_name=SphereFaceWeights.SPHERE20)
+embedding = recognizer.get_normalized_embedding(image, landmarks)
+```
+
+| Variant | Params | Size | LFW | CALFW | CPLFW | AgeDB-30 |
+|---------|--------|------|-----|-------|-------|----------|
+| SPHERE20 | 24.5M | 50 MB | 99.67% | 95.61% | 88.75% | 96.58% |
+| SPHERE36 | 34.6M | 92 MB | 99.72% | 95.64% | 89.92% | 96.83% |
+
+---
+
+## Face Comparison
+
+### Compute Similarity
+
+```python
+from uniface.face_utils import compute_similarity
+import numpy as np
+
+# Extract embeddings
+emb1 = recognizer.get_normalized_embedding(image1, landmarks1)
+emb2 = recognizer.get_normalized_embedding(image2, landmarks2)
+
+# Method 1: Using utility function
+similarity = compute_similarity(emb1, emb2)
+
+# Method 2: Direct computation
+similarity = np.dot(emb1, emb2.T)[0][0]
+
+print(f"Similarity: {similarity:.4f}")
+```
+
+### Threshold Guidelines
+
+| Threshold | Decision | Use Case |
+|-----------|----------|----------|
+| > 0.7 | Very high confidence | Security-critical |
+| > 0.6 | Same person | General verification |
+| 0.4 - 0.6 | Uncertain | Manual review needed |
+| < 0.4 | Different people | Rejection |
+
+---
+
+## Face Alignment
+
+Recognition models require aligned faces. UniFace handles this internally:
+
+```python
+# Alignment is done automatically
+embedding = recognizer.get_normalized_embedding(image, landmarks)
+
+# Or manually align
+from uniface.face_utils import face_alignment
+
+aligned_face = face_alignment(image, landmarks)
+# Returns: 112x112 aligned face image
+```
+
+---
+
+## Building a Face Database
+
+```python
+import numpy as np
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+
+detector = RetinaFace()
+recognizer = ArcFace()
+
+# Build database
+database = {}
+for person_id, image_path in person_images.items():
+    image = cv2.imread(image_path)
+    faces = detector.detect(image)
+
+    if faces:
+        embedding = recognizer.get_normalized_embedding(image, faces[0].landmarks)
+        database[person_id] = embedding
+
+# Save for later use
+np.savez('face_database.npz', **database)
+
+# Load database
+data = np.load('face_database.npz')
+database = {key: data[key] for key in data.files}
+```
+
+---
+
+## Face Search
+
+Find a person in a database:
+
+```python
+def search_face(query_embedding, database, threshold=0.6):
+    """Find best match in database."""
+    best_match = None
+    best_similarity = -1
+
+    for person_id, db_embedding in database.items():
+        similarity = np.dot(query_embedding, db_embedding.T)[0][0]
+
+        if similarity > best_similarity and similarity > threshold:
+            best_similarity = similarity
+            best_match = person_id
+
+    return best_match, best_similarity
+
+# Usage
+query_embedding = recognizer.get_normalized_embedding(query_image, landmarks)
+match, similarity = search_face(query_embedding, database)
+
+if match:
+    print(f"Found: {match} (similarity: {similarity:.4f})")
+else:
+    print("No match found")
+```
+
+---
+
+## Factory Function
+
+```python
+from uniface.recognition import create_recognizer
+
+# Available methods: 'arcface', 'adaface', 'mobileface', 'sphereface'
+recognizer = create_recognizer('arcface')
+recognizer = create_recognizer('adaface')
+```
+
+---
+
+## See Also
+
+- [Detection Module](detection.md) - Detect faces first
+- [Face Search Recipe](../recipes/face-search.md) - Complete search system
+- [Thresholds](../concepts/thresholds-calibration.md) - Calibration guide

docs/modules/spoofing.md

@@ -0,0 +1,267 @@
+# Anti-Spoofing
+
+Face anti-spoofing detects whether a face is real (live) or fake (photo, video replay, mask).
+
+---
+
+## Available Models
+
+| Model | Size |
+|-------|------|
+| MiniFASNet V1SE | 1.2 MB |
+| **MiniFASNet V2** :material-check-circle: | 1.2 MB |
+
+---
+
+## Basic Usage
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.spoofing import MiniFASNet
+
+detector = RetinaFace()
+spoofer = MiniFASNet()
+
+image = cv2.imread("photo.jpg")
+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:.1%}")
+```
+
+---
+
+## Output Format
+
+```python
+result = spoofer.predict(image, face.bbox)
+
+# SpoofingResult dataclass
+result.is_real     # True = real, False = fake
+result.confidence  # 0.0 to 1.0
+```
+
+---
+
+## Model Variants
+
+```python
+from uniface.spoofing import MiniFASNet
+from uniface.constants import MiniFASNetWeights
+
+# Default (V2, recommended)
+spoofer = MiniFASNet()
+
+# V1SE variant
+spoofer = MiniFASNet(model_name=MiniFASNetWeights.V1SE)
+```
+
+| Variant | Size | Scale Factor |
+|---------|------|--------------|
+| V1SE | 1.2 MB | 4.0 |
+| **V2** :material-check-circle: | 1.2 MB | 2.7 |
+
+---
+
+## Confidence Thresholds
+
+`result.is_real` is based on the model's top predicted class (argmax). If you want stricter behavior,
+apply your own confidence threshold:
+
+```python
+result = spoofer.predict(image, face.bbox)
+
+# High security (fewer false accepts)
+HIGH_THRESHOLD = 0.7
+if result.is_real and result.confidence > HIGH_THRESHOLD:
+    print("Real (high confidence)")
+else:
+    print("Suspicious")
+
+# Balanced (argmax decision)
+if result.is_real:
+    print("Real")
+else:
+    print("Fake")
+```
+
+---
+
+## Visualization
+
+```python
+import cv2
+
+def draw_spoofing_result(image, face, result):
+    """Draw spoofing result on image."""
+    x1, y1, x2, y2 = map(int, face.bbox)
+
+    # Color based on result
+    color = (0, 255, 0) if result.is_real else (0, 0, 255)
+    label = "Real" if result.is_real else "Fake"
+
+    # Draw bounding box
+    cv2.rectangle(image, (x1, y1), (x2, y2), color, 2)
+
+    # Draw label
+    text = f"{label}: {result.confidence:.1%}"
+    cv2.putText(image, text, (x1, y1 - 10),
+                cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
+
+    return image
+
+# Usage
+for face in faces:
+    result = spoofer.predict(image, face.bbox)
+    image = draw_spoofing_result(image, face, result)
+
+cv2.imwrite("spoofing_result.jpg", image)
+```
+
+---
+
+## Real-Time Liveness Detection
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.spoofing import MiniFASNet
+
+detector = RetinaFace()
+spoofer = MiniFASNet()
+
+cap = cv2.VideoCapture(0)
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+
+    for face in faces:
+        result = spoofer.predict(frame, face.bbox)
+
+        # Draw result
+        x1, y1, x2, y2 = map(int, face.bbox)
+        color = (0, 255, 0) if result.is_real else (0, 0, 255)
+        label = f"{'Real' if result.is_real else 'Fake'}: {result.confidence:.0%}"
+
+        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("Liveness Detection", frame)
+
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+---
+
+## Use Cases
+
+### Access Control
+
+```python
+def verify_liveness(image, face, spoofer, threshold=0.6):
+    """Verify face is real for access control."""
+    result = spoofer.predict(image, face.bbox)
+
+    if result.is_real and result.confidence > threshold:
+        return True, result.confidence
+    return False, result.confidence
+
+# Usage
+is_live, confidence = verify_liveness(image, face, spoofer)
+if is_live:
+    print(f"Access granted (confidence: {confidence:.1%})")
+else:
+    print(f"Access denied - possible spoof attempt")
+```
+
+### Multi-Frame Verification
+
+For higher security, verify across multiple frames:
+
+```python
+def verify_liveness_multiframe(frames, detector, spoofer, min_real=3):
+    """Verify liveness across multiple frames."""
+    real_count = 0
+
+    for frame in frames:
+        faces = detector.detect(frame)
+        if not faces:
+            continue
+
+        result = spoofer.predict(frame, faces[0].bbox)
+        if result.is_real:
+            real_count += 1
+
+    return real_count >= min_real
+
+# Collect frames and verify
+frames = []
+for _ in range(5):
+    ret, frame = cap.read()
+    if ret:
+        frames.append(frame)
+
+is_verified = verify_liveness_multiframe(frames, detector, spoofer)
+```
+
+---
+
+## Attack Types Detected
+
+MiniFASNet can detect various spoof attacks:
+
+| Attack Type | Detection |
+|-------------|-----------|
+| Printed photos | ✅ |
+| Screen replay | ✅ |
+| Video replay | ✅ |
+| Paper masks | ✅ |
+| 3D masks | Limited |
+
+!!! warning "Limitations"
+    - High-quality 3D masks may not be detected
+    - Performance varies with lighting and image quality
+    - Always combine with other verification methods for high-security applications
+
+---
+
+## Command-Line Tool
+
+```bash
+# Image
+python tools/spoofing.py --source photo.jpg
+
+# Webcam
+python tools/spoofing.py --source 0
+```
+
+---
+
+## Factory Function
+
+```python
+from uniface.spoofing import create_spoofer
+
+spoofer = create_spoofer()  # Returns MiniFASNet
+```
+
+---
+
+## Next Steps
+
+- [Privacy](privacy.md) - Face anonymization
+- [Detection](detection.md) - Face detection
+- [Recognition](recognition.md) - Face recognition

docs/modules/tracking.md

@@ -0,0 +1,263 @@
+# Tracking
+
+Multi-object tracking using [BYTETracker](https://github.com/yakhyo/bytetrack-tracker) with Kalman filtering and IoU-based association. The tracker assigns persistent IDs to detected objects across video frames using a two-stage association strategy — first matching high-confidence detections, then low-confidence ones.
+
+---
+
+## How It Works
+
+BYTETracker takes detection bounding boxes as input and returns tracked bounding boxes with persistent IDs. It does not depend on any specific detector — any source of `[x1, y1, x2, y2, score]` arrays will work.
+
+Each frame, the tracker:
+
+1. Splits detections into high-confidence and low-confidence groups
+2. Matches high-confidence detections to existing tracks using IoU
+3. Matches remaining tracks to low-confidence detections (second chance)
+4. Starts new tracks for unmatched high-confidence detections
+5. Removes tracks that have been lost for too long
+
+The Kalman filter predicts where each track will be in the next frame, which helps maintain associations even when detections are noisy.
+
+---
+
+## Basic Usage
+
+```python
+import cv2
+import numpy as np
+from uniface.common import xyxy_to_cxcywh
+from uniface.detection import SCRFD
+from uniface.tracking import BYTETracker
+from uniface.draw import draw_tracks
+
+detector = SCRFD()
+tracker = BYTETracker(track_thresh=0.5, track_buffer=30)
+
+cap = cv2.VideoCapture("video.mp4")
+
+while cap.isOpened():
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    # 1. Detect faces
+    faces = detector.detect(frame)
+
+    # 2. Build detections array: [x1, y1, x2, y2, score]
+    dets = np.array([[*f.bbox, f.confidence] for f in faces])
+    dets = dets if len(dets) > 0 else np.empty((0, 5))
+
+    # 3. Update tracker
+    tracks = tracker.update(dets)
+
+    # 4. Map track IDs back to face objects
+    if len(tracks) > 0 and len(faces) > 0:
+        face_bboxes = np.array([f.bbox for f in faces], dtype=np.float32)
+        track_ids = tracks[:, 4].astype(int)
+
+        face_centers = xyxy_to_cxcywh(face_bboxes)[:, :2]
+        track_centers = xyxy_to_cxcywh(tracks[:, :4])[:, :2]
+
+        for ti in range(len(tracks)):
+            dists = (track_centers[ti, 0] - face_centers[:, 0]) ** 2 + (track_centers[ti, 1] - face_centers[:, 1]) ** 2
+            faces[int(np.argmin(dists))].track_id = track_ids[ti]
+
+    # 5. Draw
+    tracked_faces = [f for f in faces if f.track_id is not None]
+    draw_tracks(image=frame, faces=tracked_faces)
+    cv2.imshow("Tracking", frame)
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+Each track ID gets a deterministic color via golden-ratio hue stepping, so the same person keeps the same color across the entire video.
+
+---
+
+## Webcam Tracking
+
+```python
+import cv2
+import numpy as np
+from uniface.common import xyxy_to_cxcywh
+from uniface.detection import SCRFD
+from uniface.tracking import BYTETracker
+from uniface.draw import draw_tracks
+
+detector = SCRFD()
+tracker = BYTETracker(track_thresh=0.5, track_buffer=30)
+cap = cv2.VideoCapture(0)
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+    dets = np.array([[*f.bbox, f.confidence] for f in faces])
+    dets = dets if len(dets) > 0 else np.empty((0, 5))
+
+    tracks = tracker.update(dets)
+
+    if len(tracks) > 0 and len(faces) > 0:
+        face_bboxes = np.array([f.bbox for f in faces], dtype=np.float32)
+        track_ids = tracks[:, 4].astype(int)
+
+        face_centers = xyxy_to_cxcywh(face_bboxes)[:, :2]
+        track_centers = xyxy_to_cxcywh(tracks[:, :4])[:, :2]
+
+        for ti in range(len(tracks)):
+            dists = (track_centers[ti, 0] - face_centers[:, 0]) ** 2 + (track_centers[ti, 1] - face_centers[:, 1]) ** 2
+            faces[int(np.argmin(dists))].track_id = track_ids[ti]
+
+    draw_tracks(image=frame, faces=[f for f in faces if f.track_id is not None])
+    cv2.imshow("Face Tracking - Press 'q' to quit", frame)
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+---
+
+## Parameters
+
+```python
+from uniface.tracking import BYTETracker
+
+tracker = BYTETracker(
+    track_thresh=0.5,
+    track_buffer=30,
+    match_thresh=0.8,
+    low_thresh=0.1,
+)
+```
+
+| Parameter | Default | Description |
+|-----------|---------|-------------|
+| `track_thresh` | 0.5 | Detections above this score go through first-pass association |
+| `track_buffer` | 30 | How many frames to keep a lost track before removing it |
+| `match_thresh` | 0.8 | IoU threshold for matching tracks to detections |
+| `low_thresh` | 0.1 | Detections below this score are discarded entirely |
+
+---
+
+## Input / Output
+
+**Input** — `(N, 5)` numpy array with `[x1, y1, x2, y2, confidence]` per detection:
+
+```python
+detections = np.array([
+    [100, 50, 200, 160, 0.95],
+    [300, 80, 380, 200, 0.87],
+])
+```
+
+**Output** — `(M, 5)` numpy array with `[x1, y1, x2, y2, track_id]` per active track:
+
+```python
+tracks = tracker.update(detections)
+# array([[101.2, 51.3, 199.8, 159.8, 1.],
+#        [300.5, 80.2, 379.7, 200.1, 2.]])
+```
+
+The output bounding boxes come from the Kalman filter prediction, so they may differ slightly from the input. Track IDs are integers that persist across frames for the same object.
+
+---
+
+## Resetting the Tracker
+
+When switching to a different video or scene, reset the tracker to clear all internal state:
+
+```python
+tracker.reset()
+```
+
+This clears all active, lost, and removed tracks, resets the frame counter, and resets the ID counter back to zero.
+
+---
+
+## Visualization
+
+`draw_tracks` draws bounding boxes color-coded by track ID:
+
+```python
+from uniface.draw import draw_tracks
+
+draw_tracks(
+    image=frame,
+    faces=tracked_faces,
+    draw_landmarks=True,
+    draw_id=True,
+    corner_bbox=True,
+)
+```
+
+---
+
+## Small Face Performance
+
+!!! warning "Tracking performance with small faces"
+    The tracker relies on IoU (Intersection over Union) to match detections across
+    frames. When faces occupy a small portion of the image — for example in
+    surveillance footage or wide-angle cameras — even slight movement between frames
+    can cause a large drop in IoU. This makes it harder for the tracker to maintain
+    consistent IDs, and you may see IDs switching or resetting more often than expected.
+
+    This is not specific to BYTETracker; it applies to any IoU-based tracker. A few
+    things that can help:
+
+    - **Lower `match_thresh`** (e.g. `0.5` or `0.6`) so the tracker accepts lower
+      overlap as a valid match.
+    - **Increase `track_buffer`** (e.g. `60` or higher) to hold onto lost tracks
+      longer before discarding them.
+    - **Use a higher-resolution input** if possible, so face bounding boxes are
+      larger in pixel terms.
+
+    ```python
+    tracker = BYTETracker(
+        track_thresh=0.4,
+        track_buffer=60,
+        match_thresh=0.6,
+    )
+    ```
+
+---
+
+## CLI Tool
+
+```bash
+# Track faces in a video
+python tools/track.py --source video.mp4
+
+# Webcam
+python tools/track.py --source 0
+
+# Save output
+python tools/track.py --source video.mp4 --output tracked.mp4
+
+# Use RetinaFace instead of SCRFD
+python tools/track.py --source video.mp4 --detector retinaface
+
+# Keep lost tracks longer
+python tools/track.py --source video.mp4 --track-buffer 60
+```
+
+---
+
+## References
+
+- [yakhyo/bytetrack-tracker](https://github.com/yakhyo/bytetrack-tracker) — standalone BYTETracker implementation used in UniFace
+- [ByteTrack paper](https://arxiv.org/abs/2110.06864) — Zhang et al., "ByteTrack: Multi-Object Tracking by Associating Every Detection Box"
+
+---
+
+## See Also
+
+- [Detection](detection.md) — face detection models
+- [Video & Webcam](../recipes/video-webcam.md) — video processing patterns
+- [Inputs & Outputs](../concepts/inputs-outputs.md) — data types and formats

docs/notebooks.md

@@ -0,0 +1,59 @@
+# Interactive Notebooks
+
+Run UniFace examples directly in your browser with Google Colab, or download and run locally with Jupyter.
+
+---
+
+## Available Notebooks
+
+| Notebook | Colab | Description |
+|----------|:-----:|-------------|
+| [Face Detection](https://github.com/yakhyo/uniface/blob/main/examples/01_face_detection.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/01_face_detection.ipynb) | Detect faces and 5-point landmarks |
+| [Face Alignment](https://github.com/yakhyo/uniface/blob/main/examples/02_face_alignment.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/02_face_alignment.ipynb) | Align faces for recognition |
+| [Face Verification](https://github.com/yakhyo/uniface/blob/main/examples/03_face_verification.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/03_face_verification.ipynb) | Compare faces for identity |
+| [Face Search](https://github.com/yakhyo/uniface/blob/main/examples/04_face_search.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/04_face_search.ipynb) | Find a person in group photos |
+| [Face Analyzer](https://github.com/yakhyo/uniface/blob/main/examples/05_face_analyzer.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/05_face_analyzer.ipynb) | All-in-one face analysis |
+| [Face Parsing](https://github.com/yakhyo/uniface/blob/main/examples/06_face_parsing.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/06_face_parsing.ipynb) | Semantic face segmentation |
+| [Face Anonymization](https://github.com/yakhyo/uniface/blob/main/examples/07_face_anonymization.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/07_face_anonymization.ipynb) | Privacy-preserving blur |
+| [Gaze Estimation](https://github.com/yakhyo/uniface/blob/main/examples/08_gaze_estimation.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/08_gaze_estimation.ipynb) | Gaze direction estimation |
+| [Face Segmentation](https://github.com/yakhyo/uniface/blob/main/examples/09_face_segmentation.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/09_face_segmentation.ipynb) | Face segmentation with XSeg |
+| [Face Vector Store](https://github.com/yakhyo/uniface/blob/main/examples/10_face_vector_store.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/10_face_vector_store.ipynb) | FAISS-backed face database |
+
+---
+
+## Running Locally
+
+Download and run notebooks on your machine:
+
+```bash
+# Clone the repository
+git clone https://github.com/yakhyo/uniface.git
+cd uniface
+
+# Install dependencies
+pip install uniface jupyter
+
+# Launch Jupyter
+jupyter notebook examples/
+```
+
+---
+
+## Running on Google Colab
+
+Click any **"Open in Colab"** badge above. The notebooks automatically:
+
+1. Install UniFace via pip
+2. Clone the repository to access test images
+3. Set up the correct working directory
+
+!!! tip "GPU Acceleration"
+    In Colab, go to **Runtime → Change runtime type → GPU** for faster inference.
+
+---
+
+## Next Steps
+
+- [Quickstart](quickstart.md) - Code snippets for common use cases
+- [Tutorials](recipes/image-pipeline.md) - Step-by-step workflow guides
+- [API Reference](modules/detection.md) - Detailed module documentation

docs/overrides/home.html

@@ -0,0 +1,5 @@
+{% extends "main.html" %}
+
+{% block source %}
+<!-- Hide edit/view source on home page -->
+{% endblock %}

docs/overrides/main.html

@@ -0,0 +1,7 @@
+{% extends "base.html" %}
+
+{% block announce %}
+  <a href="https://github.com/yakhyo/uniface" target="_blank" rel="noopener">
+    Support our work &mdash; give UniFace a <span class="twemoji">{% include ".icons/octicons/star-fill-16.svg" %}</span> on <strong>GitHub</strong> and help us reach more developers!
+  </a>
+{% endblock %}

docs/quickstart.md

@@ -0,0 +1,489 @@
+# Quickstart
+
+Get up and running with UniFace in 5 minutes. This guide covers the most common use cases.
+
+---
+
+## Face Detection
+
+Detect faces in an image:
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+
+# Load image
+image = cv2.imread("photo.jpg")
+
+# Initialize detector (models auto-download on first use)
+detector = RetinaFace()
+
+# Detect faces
+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")
+```
+
+**Output:**
+
+```
+Face 1:
+  Confidence: 0.99
+  BBox: [120.5, 85.3, 245.8, 210.6]
+  Landmarks: 5 points
+```
+
+---
+
+## Visualize Detections
+
+Draw bounding boxes and landmarks:
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.draw import draw_detections
+
+# Detect faces
+detector = RetinaFace()
+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]
+
+# Draw on image
+draw_detections(
+    image=image,
+    bboxes=bboxes,
+    scores=scores,
+    landmarks=landmarks,
+    vis_threshold=0.6,
+)
+
+# Save result
+cv2.imwrite("output.jpg", image)
+```
+
+---
+
+## Face Recognition
+
+Compare two faces:
+
+```python
+import cv2
+import numpy as np
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+
+# Initialize models
+detector = RetinaFace()
+recognizer = ArcFace()
+
+# Load two images
+image1 = cv2.imread("person1.jpg")
+image2 = cv2.imread("person2.jpg")
+
+# Detect faces
+faces1 = detector.detect(image1)
+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)
+
+    # Compute similarity (cosine similarity)
+    similarity = np.dot(emb1, emb2.T)[0][0]
+
+    # Interpret result
+    if similarity > 0.6:
+        print(f"Same person (similarity: {similarity:.3f})")
+    else:
+        print(f"Different people (similarity: {similarity:.3f})")
+```
+
+!!! tip "Similarity Thresholds"
+    - `> 0.6`: Same person (high confidence)
+    - `0.4 - 0.6`: Uncertain (manual review)
+    - `< 0.4`: Different people
+
+---
+
+## Age & Gender Detection
+
+```python
+import cv2
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
+
+# Initialize models
+detector = RetinaFace()
+age_gender = AgeGender()
+
+# Load image
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+# Predict attributes
+for i, face in enumerate(faces):
+    result = age_gender.predict(image, face.bbox)
+    print(f"Face {i+1}: {result.sex}, {result.age} years old")
+```
+
+**Output:**
+
+```
+Face 1: Male, 32 years old
+Face 2: Female, 28 years old
+```
+
+---
+
+## FairFace Attributes
+
+Detect race, gender, and age group:
+
+```python
+import cv2
+from uniface.attribute import FairFace
+from uniface.detection import RetinaFace
+
+detector = RetinaFace()
+fairface = FairFace()
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+for i, face in enumerate(faces):
+    result = fairface.predict(image, face.bbox)
+    print(f"Face {i+1}: {result.sex}, {result.age_group}, {result.race}")
+```
+
+**Output:**
+
+```
+Face 1: Male, 30-39, East Asian
+Face 2: Female, 20-29, White
+```
+
+---
+
+## Facial Landmarks (106 Points)
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.landmark import Landmark106
+
+detector = RetinaFace()
+landmarker = Landmark106()
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+if faces:
+    landmarks = landmarker.get_landmarks(image, faces[0].bbox)
+    print(f"Detected {len(landmarks)} landmarks")
+
+    # Draw landmarks
+    for x, y in landmarks.astype(int):
+        cv2.circle(image, (x, y), 2, (0, 255, 0), -1)
+
+    cv2.imwrite("landmarks.jpg", image)
+```
+
+---
+
+## Gaze Estimation
+
+```python
+import cv2
+import numpy as np
+from uniface.detection import RetinaFace
+from uniface.gaze import MobileGaze
+from uniface.draw import draw_gaze
+
+detector = RetinaFace()
+gaze_estimator = MobileGaze()
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+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)
+```
+
+---
+
+## Face Parsing
+
+Segment face into semantic components:
+
+```python
+import cv2
+import numpy as np
+from uniface.parsing import BiSeNet
+from uniface.draw import vis_parsing_maps
+
+parser = BiSeNet()
+
+# 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)
+
+print(f"Detected {len(np.unique(mask))} facial components")
+```
+
+---
+
+## Face Anonymization
+
+Blur faces for privacy protection:
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.privacy import BlurFace
+
+detector = RetinaFace()
+blurrer = BlurFace(method='pixelate')
+
+image = cv2.imread("group_photo.jpg")
+faces = detector.detect(image)
+anonymized = blurrer.anonymize(image, faces)
+cv2.imwrite("anonymized.jpg", anonymized)
+```
+
+**Custom blur settings:**
+
+```python
+blurrer = BlurFace(method='gaussian', blur_strength=5.0)
+anonymized = blurrer.anonymize(image, faces)
+```
+
+**Available methods:**
+
+| Method | Description |
+|--------|-------------|
+| `pixelate` | Blocky effect (news media standard) |
+| `gaussian` | Smooth, natural blur |
+| `blackout` | Solid color boxes (maximum privacy) |
+| `elliptical` | Soft oval blur (natural face shape) |
+| `median` | Edge-preserving blur |
+
+---
+
+## Face Anti-Spoofing
+
+Detect real vs. fake faces:
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.spoofing import MiniFASNet
+
+detector = RetinaFace()
+spoofer = MiniFASNet()
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+for i, face in enumerate(faces):
+    result = spoofer.predict(image, face.bbox)
+    label = 'Real' if result.is_real else 'Fake'
+    print(f"Face {i+1}: {label} ({result.confidence:.1%})")
+```
+
+---
+
+## Webcam Demo
+
+Real-time face detection:
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.draw import draw_detections
+
+detector = RetinaFace()
+cap = cv2.VideoCapture(0)
+
+print("Press 'q' to quit")
+
+while True:
+    ret, frame = cap.read()
+    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)
+
+    cv2.imshow("UniFace - Press 'q' to quit", frame)
+
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+---
+
+## Face Tracking
+
+Track faces across video frames with persistent IDs:
+
+```python
+import cv2
+import numpy as np
+from uniface.common import xyxy_to_cxcywh
+from uniface.detection import SCRFD
+from uniface.tracking import BYTETracker
+from uniface.draw import draw_tracks
+
+detector = SCRFD()
+tracker = BYTETracker(track_thresh=0.5, track_buffer=30)
+
+cap = cv2.VideoCapture("video.mp4")
+
+while cap.isOpened():
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+    dets = np.array([[*f.bbox, f.confidence] for f in faces])
+    dets = dets if len(dets) > 0 else np.empty((0, 5))
+
+    tracks = tracker.update(dets)
+
+    # Assign track IDs to faces
+    if len(tracks) > 0 and len(faces) > 0:
+        face_bboxes = np.array([f.bbox for f in faces], dtype=np.float32)
+        track_ids = tracks[:, 4].astype(int)
+
+        face_centers = xyxy_to_cxcywh(face_bboxes)[:, :2]
+        track_centers = xyxy_to_cxcywh(tracks[:, :4])[:, :2]
+
+        for ti in range(len(tracks)):
+            dists = (track_centers[ti, 0] - face_centers[:, 0]) ** 2 + (track_centers[ti, 1] - face_centers[:, 1]) ** 2
+            faces[int(np.argmin(dists))].track_id = track_ids[ti]
+
+    tracked_faces = [f for f in faces if f.track_id is not None]
+    draw_tracks(image=frame, faces=tracked_faces)
+    cv2.imshow("Tracking", frame)
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+For more details, see the [Tracking module](modules/tracking.md).
+
+---
+
+## Model Selection
+
+For detailed model comparisons and benchmarks, see the [Model Zoo](models.md).
+
+**Available models by task:**
+
+| Task | Available Models |
+|------|------------------|
+| Detection | `RetinaFace`, `SCRFD`, `YOLOv5Face`, `YOLOv8Face` |
+| Recognition | `ArcFace`, `AdaFace`, `MobileFace`, `SphereFace` |
+| Tracking | `BYTETracker` |
+| Gaze | `MobileGaze` (ResNet18/34/50, MobileNetV2, MobileOneS0) |
+| Parsing | `BiSeNet` (ResNet18/34) |
+| Attributes | `AgeGender`, `FairFace`, `Emotion` |
+| Anti-Spoofing | `MiniFASNet` (V1SE, V2) |
+
+---
+
+## Common Issues
+
+### Models Not Downloading
+
+```python
+from uniface.model_store import verify_model_weights
+from uniface.constants import RetinaFaceWeights
+
+# Manually download a model
+model_path = verify_model_weights(RetinaFaceWeights.MNET_V2)
+print(f"Model downloaded to: {model_path}")
+```
+
+### Check Hardware Acceleration
+
+```python
+import onnxruntime as ort
+print("Available providers:", ort.get_available_providers())
+
+# macOS M-series should show: ['CoreMLExecutionProvider', ...]
+# NVIDIA GPU should show: ['CUDAExecutionProvider', ...]
+```
+
+### Slow Performance on Mac
+
+Verify you're using the ARM64 build of Python:
+
+```bash
+python -c "import platform; print(platform.machine())"
+# Should show: arm64 (not x86_64)
+```
+
+### Import Errors
+
+```python
+from uniface.detection import RetinaFace, SCRFD
+from uniface.recognition import ArcFace, AdaFace
+from uniface.attribute import AgeGender, FairFace
+from uniface.landmark import Landmark106
+from uniface.gaze import MobileGaze
+from uniface.parsing import BiSeNet, XSeg
+from uniface.privacy import BlurFace
+from uniface.spoofing import MiniFASNet
+from uniface.tracking import BYTETracker
+from uniface.analyzer import FaceAnalyzer
+from uniface.indexing import FAISS  # pip install faiss-cpu
+from uniface.draw import draw_detections, draw_tracks
+```
+
+---
+
+## Next Steps
+
+- [Model Zoo](models.md) - All models, benchmarks, and selection guide
+- [API Reference](modules/detection.md) - Explore individual modules and their APIs
+- [Tutorials](recipes/image-pipeline.md) - Step-by-step examples for common workflows
+- [Guides](concepts/overview.md) - Learn about the architecture and design principles

docs/recipes/anonymize-stream.md

@@ -0,0 +1,104 @@
+# Anonymize Stream
+
+Blur faces in real-time video streams for privacy protection.
+
+!!! note "Work in Progress"
+    This page contains example code patterns. Test thoroughly before using in production.
+
+---
+
+## Webcam Anonymization
+
+```python
+import cv2
+from uniface.detection 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()
+```
+
+---
+
+## Video File Anonymization
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.privacy import BlurFace
+
+detector = RetinaFace()
+blurrer = BlurFace(method='gaussian')
+
+cap = cv2.VideoCapture("input.mp4")
+fps = cap.get(cv2.CAP_PROP_FPS)
+w, h = int(cap.get(3)), int(cap.get(4))
+
+out = cv2.VideoWriter('output.mp4', cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+
+while cap.read()[0]:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+    blurrer.anonymize(frame, faces, inplace=True)
+    out.write(frame)
+
+cap.release()
+out.release()
+```
+
+---
+
+## Single Image
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.privacy import BlurFace
+
+detector = RetinaFace()
+blurrer = BlurFace(method='pixelate')
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+result = blurrer.anonymize(image, faces)
+cv2.imwrite("anonymized.jpg", result)
+```
+
+---
+
+## Available Blur Methods
+
+| Method | Usage |
+|--------|-------|
+| Pixelate | `BlurFace(method='pixelate', pixel_blocks=15)` |
+| Gaussian | `BlurFace(method='gaussian', blur_strength=3.0)` |
+| Blackout | `BlurFace(method='blackout', color=(0,0,0))` |
+| Elliptical | `BlurFace(method='elliptical', margin=20)` |
+| Median | `BlurFace(method='median', blur_strength=3.0)` |
+
+---
+
+## See Also
+
+- [Privacy Module](../modules/privacy.md) - Privacy protection details
+- [Video & Webcam](video-webcam.md) - Real-time processing
+- [Detection Module](../modules/detection.md) - Face detection

docs/recipes/batch-processing.md

@@ -0,0 +1,84 @@
+# Batch Processing
+
+Process multiple images efficiently.
+
+!!! note "Work in Progress"
+    This page contains example code patterns. Test thoroughly before using in production.
+
+---
+
+## Basic Batch Processing
+
+```python
+import cv2
+from pathlib import Path
+from uniface.detection import RetinaFace
+
+detector = RetinaFace()
+
+def process_directory(input_dir, output_dir):
+    """Process all images in a directory."""
+    input_path = Path(input_dir)
+    output_path = Path(output_dir)
+    output_path.mkdir(parents=True, exist_ok=True)
+
+    for image_path in input_path.glob("*.jpg"):
+        print(f"Processing {image_path.name}...")
+
+        image = cv2.imread(str(image_path))
+        faces = detector.detect(image)
+
+        print(f"  Found {len(faces)} face(s)")
+
+        # Process and save results
+        # ... your code here ...
+
+# Usage
+process_directory("input_images/", "output_images/")
+```
+
+---
+
+## With Progress Bar
+
+```python
+from tqdm import tqdm
+
+for image_path in tqdm(image_files, desc="Processing"):
+    # ... process image ...
+    pass
+```
+
+---
+
+## Extract Embeddings
+
+```python
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+import numpy as np
+
+detector = RetinaFace()
+recognizer = ArcFace()
+
+embeddings = {}
+for image_path in Path("faces/").glob("*.jpg"):
+    image = cv2.imread(str(image_path))
+    faces = detector.detect(image)
+
+    if faces:
+        embedding = recognizer.get_normalized_embedding(image, faces[0].landmarks)
+        embeddings[image_path.stem] = embedding
+
+# Save embeddings
+np.savez("embeddings.npz", **embeddings)
+```
+
+---
+
+## See Also
+
+- [Video & Webcam](video-webcam.md) - Real-time processing
+- [Face Search](face-search.md) - Search through embeddings
+- [Image Pipeline](image-pipeline.md) - Full analysis pipeline
+- [Detection Module](../modules/detection.md) - Detection options

docs/recipes/custom-models.md

@@ -0,0 +1,92 @@
+# Custom Models
+
+Add your own ONNX models to UniFace.
+
+!!! note "Work in Progress"
+    This page contains example code patterns for advanced users. Test thoroughly before using in production.
+
+---
+
+## Overview
+
+UniFace is designed to be extensible. You can add custom ONNX models by:
+
+1. Creating a class that inherits from the appropriate base class
+2. Implementing required methods
+3. Using the ONNX Runtime utilities provided by UniFace
+
+---
+
+## Add Custom Detection Model
+
+```python
+from uniface.detection.base import BaseDetector
+from uniface.onnx_utils import create_onnx_session
+from uniface.types import Face
+import numpy as np
+
+class MyDetector(BaseDetector):
+    def __init__(self, model_path: str, confidence_threshold: float = 0.5):
+        super().__init__(confidence_threshold=confidence_threshold)
+        self.session = create_onnx_session(model_path)
+        self.threshold = confidence_threshold
+
+    def preprocess(self, image: np.ndarray) -> np.ndarray:
+        # Your preprocessing logic
+        # e.g., resize, normalize, transpose
+        raise NotImplementedError
+
+    def postprocess(self, outputs, shape) -> list[Face]:
+        # Your postprocessing logic
+        # e.g., decode boxes, apply NMS, create Face objects
+        raise NotImplementedError
+
+    def detect(self, image: np.ndarray) -> list[Face]:
+        # 1. Preprocess image
+        input_tensor = self.preprocess(image)
+
+        # 2. Run inference
+        outputs = self.session.run(None, {'input': input_tensor})
+
+        # 3. Postprocess outputs to Face objects
+        return self.postprocess(outputs, image.shape)
+```
+
+---
+
+## Add Custom Recognition Model
+
+```python
+from uniface.recognition.base import BaseRecognizer, PreprocessConfig
+
+class MyRecognizer(BaseRecognizer):
+    def __init__(self, model_path: str, providers=None):
+        preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
+        super().__init__(model_path, preprocessing, providers=providers)
+
+    # Optional: override preprocess() if your model expects custom normalization.
+```
+
+---
+
+## Usage
+
+```python
+from my_module import MyDetector, MyRecognizer
+
+# Use custom models
+detector = MyDetector("path/to/detection_model.onnx")
+recognizer = MyRecognizer("path/to/recognition_model.onnx")
+
+# Use like built-in models
+faces = detector.detect(image)
+embedding = recognizer.get_normalized_embedding(image, faces[0].landmarks)
+```
+
+---
+
+## See Also
+
+- [Detection Module](../modules/detection.md) - Built-in detection models
+- [Recognition Module](../modules/recognition.md) - Built-in recognition models
+- [Concepts: Overview](../concepts/overview.md) - Architecture overview

docs/recipes/face-search.md

@@ -0,0 +1,166 @@
+# Face Search
+
+Find and identify people in images and video streams.
+
+UniFace supports two search approaches:
+
+| Approach             | Use case                                         | Tool                    |
+| -------------------- | ------------------------------------------------ | ----------------------- |
+| **Reference search** | "Is this specific person in the video?"          | `tools/search.py`       |
+| **Vector search**    | "Who is this?" against a database of known faces | `tools/faiss_search.py` |
+
+---
+
+## Reference Search (single image)
+
+Compare every detected face against a single reference photo:
+
+```python
+import cv2
+import numpy as np
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+from uniface.face_utils import compute_similarity
+
+detector = RetinaFace()
+recognizer = ArcFace()
+
+ref_image = cv2.imread("reference.jpg")
+ref_faces = detector.detect(ref_image)
+ref_embedding = recognizer.get_normalized_embedding(ref_image, ref_faces[0].landmarks)
+
+query_image = cv2.imread("group_photo.jpg")
+faces = detector.detect(query_image)
+
+for face in faces:
+    embedding = recognizer.get_normalized_embedding(query_image, face.landmarks)
+    sim = compute_similarity(ref_embedding, embedding)
+
+    label = f"Match ({sim:.2f})" if sim > 0.4 else f"Unknown ({sim:.2f})"
+    print(label)
+```
+
+**CLI tool:**
+
+```bash
+python tools/search.py --reference ref.jpg --source video.mp4
+python tools/search.py --reference ref.jpg --source 0  # webcam
+```
+
+---
+
+## Vector Search (FAISS index)
+
+For identifying faces against a database of many known people, use the
+[`FAISS`](../modules/indexing.md) vector store.
+
+!!! info "Install extra"
+`bash
+    pip install faiss-cpu
+    `
+
+### Build an index
+
+Organise face images in person sub-folders:
+
+```
+dataset/
+├── alice/
+│   ├── 001.jpg
+│   └── 002.jpg
+├── bob/
+│   └── 001.jpg
+└── charlie/
+    ├── 001.jpg
+    └── 002.jpg
+```
+
+```python
+import cv2
+from pathlib import Path
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+from uniface.indexing import FAISS
+
+detector = RetinaFace()
+recognizer = ArcFace()
+store = FAISS(db_path="./my_index")
+
+for person_dir in sorted(Path("dataset").iterdir()):
+    if not person_dir.is_dir():
+        continue
+    for img_path in person_dir.glob("*.jpg"):
+        image = cv2.imread(str(img_path))
+        faces = detector.detect(image)
+        if faces:
+            emb = recognizer.get_normalized_embedding(image, faces[0].landmarks)
+            store.add(emb, {"person_id": person_dir.name, "source": str(img_path)})
+
+store.save()
+print(f"Index saved: {store}")
+```
+
+**CLI tool:**
+
+```bash
+python tools/faiss_search.py build --faces-dir dataset/ --db-path ./my_index
+```
+
+### Search against the index
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+from uniface.indexing import FAISS
+
+detector = RetinaFace()
+recognizer = ArcFace()
+
+store = FAISS(db_path="./my_index")
+store.load()
+
+image = cv2.imread("query.jpg")
+faces = detector.detect(image)
+
+for face in faces:
+    embedding = recognizer.get_normalized_embedding(image, face.landmarks)
+    result, similarity = store.search(embedding, threshold=0.4)
+
+    if result:
+        print(f"Matched: {result['person_id']} ({similarity:.2f})")
+    else:
+        print(f"Unknown ({similarity:.2f})")
+```
+
+**CLI tool:**
+
+```bash
+python tools/faiss_search.py run --db-path ./my_index --source video.mp4
+python tools/faiss_search.py run --db-path ./my_index --source 0  # webcam
+```
+
+### Manage the index
+
+```python
+from uniface.indexing import FAISS
+
+store = FAISS(db_path="./my_index")
+store.load()
+
+print(f"Total vectors: {len(store)}")
+
+removed = store.remove("person_id", "bob")
+print(f"Removed {removed} entries")
+
+store.save()
+```
+
+---
+
+## See Also
+
+- [Indexing Module](../modules/indexing.md) - Full `FAISS` API reference
+- [Recognition Module](../modules/recognition.md) - Face recognition details
+- [Video & Webcam](video-webcam.md) - Real-time processing
+- [Concepts: Thresholds](../concepts/thresholds-calibration.md) - Tuning similarity thresholds

docs/recipes/image-pipeline.md

@@ -0,0 +1,293 @@
+# Image Pipeline
+
+A complete pipeline for processing images with detection, recognition, and attribute analysis.
+
+---
+
+## Basic Pipeline
+
+```python
+import cv2
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+from uniface.draw import draw_detections
+
+# Initialize models
+detector = RetinaFace()
+recognizer = ArcFace()
+age_gender = AgeGender()
+
+def process_image(image_path):
+    """Process a single image through the full pipeline."""
+    # Load image
+    image = cv2.imread(image_path)
+
+    # Step 1: Detect faces
+    faces = detector.detect(image)
+    print(f"Found {len(faces)} face(s)")
+
+    results = []
+
+    for i, face in enumerate(faces):
+        # Step 2: Extract embedding
+        embedding = recognizer.get_normalized_embedding(image, face.landmarks)
+
+        # Step 3: Predict attributes
+        attrs = age_gender.predict(image, face.bbox)
+
+        results.append({
+            'face_id': i,
+            'bbox': face.bbox,
+            'confidence': face.confidence,
+            'embedding': embedding,
+            'gender': attrs.sex,
+            'age': attrs.age
+        })
+
+        print(f"  Face {i+1}: {attrs.sex}, {attrs.age} years old")
+
+    # Visualize
+    draw_detections(
+        image=image,
+        bboxes=[f.bbox for f in faces],
+        scores=[f.confidence for f in faces],
+        landmarks=[f.landmarks for f in faces]
+    )
+
+    return image, results
+
+# Usage
+result_image, results = process_image("photo.jpg")
+cv2.imwrite("result.jpg", result_image)
+```
+
+---
+
+## Using FaceAnalyzer
+
+For convenience, use the built-in `FaceAnalyzer`:
+
+```python
+from uniface.analyzer import FaceAnalyzer
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+import cv2
+
+# Initialize with desired modules
+detector = RetinaFace()
+recognizer = ArcFace()
+age_gender = AgeGender()
+
+analyzer = FaceAnalyzer(
+    detector,
+    recognizer=recognizer,
+    age_gender=age_gender,
+)
+
+# Process image
+image = cv2.imread("photo.jpg")
+faces = analyzer.analyze(image)
+
+# Access enriched Face objects
+for face in faces:
+    print(f"Confidence: {face.confidence:.2f}")
+    print(f"Embedding: {face.embedding.shape}")
+    print(f"Age: {face.age}, Gender: {face.sex}")
+```
+
+---
+
+## Full Analysis Pipeline
+
+Complete pipeline with all modules:
+
+```python
+import cv2
+import numpy as np
+from uniface.attribute import AgeGender, FairFace
+from uniface.detection import RetinaFace
+from uniface.gaze import MobileGaze
+from uniface.landmark import Landmark106
+from uniface.recognition import ArcFace
+from uniface.parsing import BiSeNet
+from uniface.spoofing import MiniFASNet
+from uniface.draw import draw_detections, draw_gaze
+
+class FaceAnalysisPipeline:
+    def __init__(self):
+        # Initialize all models
+        self.detector = RetinaFace()
+        self.recognizer = ArcFace()
+        self.age_gender = AgeGender()
+        self.fairface = FairFace()
+        self.landmarker = Landmark106()
+        self.gaze = MobileGaze()
+        self.parser = BiSeNet()
+        self.spoofer = MiniFASNet()
+
+    def analyze(self, image):
+        """Run full analysis pipeline."""
+        faces = self.detector.detect(image)
+        results = []
+
+        for face in faces:
+            result = {
+                'bbox': face.bbox,
+                'confidence': face.confidence,
+                'landmarks_5': face.landmarks
+            }
+
+            # Recognition embedding
+            result['embedding'] = self.recognizer.get_normalized_embedding(
+                image, face.landmarks
+            )
+
+            # Attributes
+            ag_result = self.age_gender.predict(image, face.bbox)
+            result['age'] = ag_result.age
+            result['gender'] = ag_result.sex
+
+            # FairFace attributes
+            ff_result = self.fairface.predict(image, face.bbox)
+            result['age_group'] = ff_result.age_group
+            result['race'] = ff_result.race
+
+            # 106-point landmarks
+            result['landmarks_106'] = self.landmarker.get_landmarks(
+                image, face.bbox
+            )
+
+            # Gaze estimation
+            x1, y1, x2, y2 = map(int, face.bbox)
+            face_crop = image[y1:y2, x1:x2]
+            if face_crop.size > 0:
+                gaze_result = self.gaze.estimate(face_crop)
+                result['gaze_pitch'] = gaze_result.pitch
+                result['gaze_yaw'] = gaze_result.yaw
+
+            # Face parsing
+            if face_crop.size > 0:
+                result['parsing_mask'] = self.parser.parse(face_crop)
+
+            # Anti-spoofing
+            spoof_result = self.spoofer.predict(image, face.bbox)
+            result['is_real'] = spoof_result.is_real
+            result['spoof_confidence'] = spoof_result.confidence
+
+            results.append(result)
+
+        return results
+
+# Usage
+pipeline = FaceAnalysisPipeline()
+results = pipeline.analyze(cv2.imread("photo.jpg"))
+
+for i, r in enumerate(results):
+    print(f"\nFace {i+1}:")
+    print(f"  Gender: {r['gender']}, Age: {r['age']}")
+    print(f"  Race: {r['race']}, Age Group: {r['age_group']}")
+    print(f"  Gaze: pitch={np.degrees(r['gaze_pitch']):.1f}°")
+    print(f"  Real: {r['is_real']} ({r['spoof_confidence']:.1%})")
+```
+
+---
+
+## Visualization Pipeline
+
+```python
+import cv2
+import numpy as np
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
+from uniface.gaze import MobileGaze
+from uniface.draw import draw_detections, draw_gaze
+
+def visualize_analysis(image_path, output_path):
+    """Create annotated visualization of face analysis."""
+    detector = RetinaFace()
+    age_gender = AgeGender()
+    gaze = MobileGaze()
+
+    image = cv2.imread(image_path)
+    faces = detector.detect(image)
+
+    for face in faces:
+        x1, y1, x2, y2 = map(int, face.bbox)
+
+        # Draw bounding box
+        cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+        # Age and gender
+        attrs = age_gender.predict(image, face.bbox)
+        label = f"{attrs.sex}, {attrs.age}y"
+        cv2.putText(image, label, (x1, y1 - 10),
+                    cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
+
+        # Gaze
+        face_crop = image[y1:y2, x1:x2]
+        if face_crop.size > 0:
+            gaze_result = gaze.estimate(face_crop)
+            draw_gaze(image, face.bbox, gaze_result.pitch, gaze_result.yaw)
+
+        # Confidence
+        conf_label = f"{face.confidence:.0%}"
+        cv2.putText(image, conf_label, (x1, y2 + 20),
+                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1)
+
+    cv2.imwrite(output_path, image)
+    print(f"Saved to {output_path}")
+
+# Usage
+visualize_analysis("input.jpg", "output.jpg")
+```
+
+---
+
+## JSON Output
+
+Export results to JSON:
+
+```python
+import json
+import numpy as np
+
+def results_to_json(results):
+    """Convert analysis results to JSON-serializable format."""
+    output = []
+
+    for r in results:
+        item = {
+            'bbox': r['bbox'].tolist(),
+            'confidence': float(r['confidence']),
+            'age': int(r['age']) if r.get('age') else None,
+            'gender': r.get('gender'),
+            'race': r.get('race'),
+            'is_real': r.get('is_real'),
+            'gaze': {
+                'pitch_deg': float(np.degrees(r['gaze_pitch'])) if 'gaze_pitch' in r else None,
+                'yaw_deg': float(np.degrees(r['gaze_yaw'])) if 'gaze_yaw' in r else None
+            }
+        }
+        output.append(item)
+
+    return output
+
+# Usage
+results = pipeline.analyze(image)
+json_data = results_to_json(results)
+
+with open('results.json', 'w') as f:
+    json.dump(json_data, f, indent=2)
+```
+
+---
+
+## Next Steps
+
+- [Batch Processing](batch-processing.md) - Process multiple images
+- [Video & Webcam](video-webcam.md) - Real-time processing
+- [Face Search](face-search.md) - Build a search system
+- [Detection Module](../modules/detection.md) - Detection options
+- [Recognition Module](../modules/recognition.md) - Recognition details

docs/recipes/video-webcam.md

@@ -0,0 +1,177 @@
+# Video & Webcam
+
+Real-time face analysis for video streams.
+
+!!! note "Work in Progress"
+    This page contains example code patterns. Test thoroughly before using in production.
+
+---
+
+## Webcam Detection
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+from uniface.draw import draw_detections
+
+detector = RetinaFace()
+cap = cv2.VideoCapture(0)
+
+print("Press 'q' to quit")
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+
+    draw_detections(
+        image=frame,
+        bboxes=[f.bbox for f in faces],
+        scores=[f.confidence for f in faces],
+        landmarks=[f.landmarks for f in faces]
+    )
+
+    cv2.imshow("Face Detection", frame)
+
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+---
+
+## Video File Processing
+
+```python
+import cv2
+from uniface.detection import RetinaFace
+
+def process_video(input_path, output_path):
+    """Process a video file."""
+    detector = RetinaFace()
+    cap = cv2.VideoCapture(input_path)
+
+    # 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))
+
+    # Setup output
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    while cap.read()[0]:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        faces = detector.detect(frame)
+        # ... process and draw ...
+
+        out.write(frame)
+
+    cap.release()
+    out.release()
+
+# Usage
+process_video("input.mp4", "output.mp4")
+```
+
+---
+
+## Webcam Tracking
+
+To track faces across frames with persistent IDs, pair a detector with `BYTETracker`:
+
+```python
+import cv2
+import numpy as np
+from uniface.common import xyxy_to_cxcywh
+from uniface.detection import SCRFD
+from uniface.tracking import BYTETracker
+from uniface.draw import draw_tracks
+
+detector = SCRFD()
+tracker = BYTETracker(track_thresh=0.5, track_buffer=30)
+cap = cv2.VideoCapture(0)
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+    dets = np.array([[*f.bbox, f.confidence] for f in faces])
+    dets = dets if len(dets) > 0 else np.empty((0, 5))
+
+    tracks = tracker.update(dets)
+
+    if len(tracks) > 0 and len(faces) > 0:
+        face_bboxes = np.array([f.bbox for f in faces], dtype=np.float32)
+        track_ids = tracks[:, 4].astype(int)
+
+        face_centers = xyxy_to_cxcywh(face_bboxes)[:, :2]
+        track_centers = xyxy_to_cxcywh(tracks[:, :4])[:, :2]
+
+        for ti in range(len(tracks)):
+            dists = (track_centers[ti, 0] - face_centers[:, 0]) ** 2 + (track_centers[ti, 1] - face_centers[:, 1]) ** 2
+            faces[int(np.argmin(dists))].track_id = track_ids[ti]
+
+    draw_tracks(image=frame, faces=[f for f in faces if f.track_id is not None])
+    cv2.imshow("Face Tracking", frame)
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+For more details on tracker parameters and tuning, see [Tracking](../modules/tracking.md).
+
+---
+
+## Performance Tips
+
+### Skip Frames
+
+```python
+PROCESS_EVERY_N = 3  # Process every 3rd frame
+frame_count = 0
+last_faces = []
+
+while True:
+    ret, frame = cap.read()
+    if frame_count % PROCESS_EVERY_N == 0:
+        last_faces = detector.detect(frame)
+    frame_count += 1
+    # Draw last_faces...
+```
+
+### FPS Counter
+
+```python
+import time
+
+prev_time = time.time()
+while True:
+    curr_time = time.time()
+    fps = 1 / (curr_time - prev_time)
+    prev_time = curr_time
+
+    cv2.putText(frame, f"FPS: {fps:.1f}", (10, 30),
+                cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+```
+
+---
+
+## See Also
+
+- [Tracking Module](../modules/tracking.md) - Face tracking with BYTETracker
+- [Anonymize Stream](anonymize-stream.md) - Privacy protection in video
+- [Batch Processing](batch-processing.md) - Process multiple files
+- [Detection Module](../modules/detection.md) - Detection options
+- [Gaze Module](../modules/gaze.md) - Gaze estimation

docs/stylesheets/extra.css

@@ -0,0 +1,225 @@
+/* UniFace Documentation - Custom Styles */
+
+/* ===== Hero Section ===== */
+
+.md-content .hero {
+  text-align: center;
+  padding: 3rem 1rem 2rem;
+  margin: 0 auto;
+  max-width: 900px;
+}
+
+.hero-title {
+  font-size: 3.5rem !important;
+  font-weight: 800 !important;
+  margin-bottom: 0.5rem !important;
+  background: linear-gradient(135deg, var(--md-primary-fg-color) 0%, #7c4dff 100%);
+  -webkit-background-clip: text;
+  -webkit-text-fill-color: transparent;
+  background-clip: text;
+}
+
+.hero-tagline {
+  font-size: 1.5rem;
+  color: var(--md-default-fg-color);
+  margin-bottom: 0.5rem !important;
+  font-weight: 500;
+}
+
+.hero-subtitle {
+  font-size: 1rem;
+  color: var(--md-default-fg-color--light);
+  margin-bottom: 1.5rem !important;
+  font-weight: 400;
+  letter-spacing: 0.5px;
+}
+
+.hero .md-button {
+  margin: 0.5rem 0.25rem;
+  padding: 0.7rem 1.5rem;
+  font-weight: 600;
+  border-radius: 8px;
+  transition: all 0.2s ease;
+}
+
+.hero .md-button--primary {
+  background: linear-gradient(135deg, var(--md-primary-fg-color) 0%, #5c6bc0 100%);
+  border: none;
+  box-shadow: 0 4px 14px rgba(63, 81, 181, 0.4);
+}
+
+.hero .md-button--primary:hover {
+  transform: translateY(-2px);
+  box-shadow: 0 6px 20px rgba(63, 81, 181, 0.5);
+}
+
+.hero .md-button:not(.md-button--primary) {
+  border: 2px solid var(--md-primary-fg-color);
+  background: transparent;
+  color: var(--md-primary-fg-color);
+}
+
+.hero .md-button:not(.md-button--primary):hover {
+  background: var(--md-primary-fg-color);
+  border-color: var(--md-primary-fg-color);
+  color: white;
+  transform: translateY(-2px);
+}
+
+/* Badge styling in hero */
+.hero p a img {
+  margin: 0 3px;
+  height: 24px !important;
+}
+
+/* ===== Feature Grid ===== */
+.feature-grid {
+  display: grid;
+  grid-template-columns: repeat(4, 1fr);
+  gap: 1.25rem;
+  margin: 2rem 0;
+}
+
+.feature-card {
+  padding: 1.5rem;
+  border-radius: 12px;
+  background: var(--md-code-bg-color);
+  border: 1px solid var(--md-default-fg-color--lightest);
+  transition: all 0.3s ease;
+  position: relative;
+  overflow: hidden;
+}
+
+.feature-card::before {
+  content: '';
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  height: 3px;
+  background: linear-gradient(90deg, var(--md-primary-fg-color), #7c4dff);
+  opacity: 0;
+  transition: opacity 0.3s ease;
+}
+
+.feature-card:hover {
+  transform: translateY(-4px);
+  box-shadow: 0 12px 24px rgba(0, 0, 0, 0.1);
+  border-color: var(--md-primary-fg-color--light);
+}
+
+.feature-card:hover::before {
+  opacity: 1;
+}
+
+.feature-card h3 {
+  margin-top: 0 !important;
+  margin-bottom: 0.75rem !important;
+  font-size: 1rem !important;
+  font-weight: 600;
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+}
+
+.feature-card p {
+  margin: 0;
+  font-size: 0.875rem;
+  color: var(--md-default-fg-color--light);
+  line-height: 1.5;
+}
+
+.feature-card a {
+  display: inline-block;
+  margin-top: 0.75rem;
+  font-weight: 500;
+  font-size: 0.875rem;
+}
+
+/* ===== Next Steps Grid (2 columns) ===== */
+.next-steps-grid {
+  display: grid;
+  grid-template-columns: repeat(2, 1fr);
+  gap: 1.25rem;
+  margin: 2rem 0;
+}
+
+.next-steps-grid .feature-card {
+  padding: 2rem;
+}
+
+.next-steps-grid .feature-card h3 {
+  font-size: 1.1rem !important;
+}
+
+/* ===== Dark Mode Adjustments ===== */
+[data-md-color-scheme="slate"] .hero-title {
+  background: linear-gradient(135deg, #7c4dff 0%, #b388ff 100%);
+  -webkit-background-clip: text;
+  -webkit-text-fill-color: transparent;
+  background-clip: text;
+}
+
+[data-md-color-scheme="slate"] .feature-card:hover {
+  box-shadow: 0 12px 24px rgba(0, 0, 0, 0.3);
+}
+
+[data-md-color-scheme="slate"] .hero .md-button--primary {
+  background: linear-gradient(135deg, #7c4dff 0%, #b388ff 100%);
+  box-shadow: 0 4px 14px rgba(124, 77, 255, 0.4);
+}
+
+[data-md-color-scheme="slate"] .hero .md-button--primary:hover {
+  box-shadow: 0 6px 20px rgba(124, 77, 255, 0.5);
+}
+
+[data-md-color-scheme="slate"] .hero .md-button:not(.md-button--primary) {
+  border: 2px solid rgba(255, 255, 255, 0.3);
+  background: rgba(255, 255, 255, 0.05);
+  color: rgba(255, 255, 255, 0.9);
+}
+
+[data-md-color-scheme="slate"] .hero .md-button:not(.md-button--primary):hover {
+  background: rgba(255, 255, 255, 0.1);
+  border-color: rgba(255, 255, 255, 0.5);
+  color: white;
+  transform: translateY(-2px);
+}
+
+/* ===== Responsive Design ===== */
+@media (max-width: 1200px) {
+  .feature-grid {
+    grid-template-columns: repeat(2, 1fr);
+  }
+}
+
+@media (max-width: 768px) {
+  .hero-title {
+    font-size: 2.5rem !important;
+  }
+
+  .hero-subtitle {
+    font-size: 1.1rem;
+  }
+
+  .feature-grid,
+  .next-steps-grid {
+    grid-template-columns: 1fr;
+  }
+
+  .hero .md-button {
+    display: block;
+    margin: 0.5rem auto;
+    max-width: 200px;
+  }
+}
+
+@media (max-width: 480px) {
+  .hero-title {
+    font-size: 2rem !important;
+  }
+
+  .feature-card {
+    padding: 1.25rem;
+  }
+}

mkdocs.yml

@@ -0,0 +1,168 @@
+site_name: UniFace
+site_description: All-in-One Face Analysis Library with ONNX Runtime
+site_author: Yakhyokhuja Valikhujaev
+site_url: https://yakhyo.github.io/uniface
+
+repo_name: yakhyo/uniface
+repo_url: https://github.com/yakhyo/uniface
+edit_uri: edit/main/docs/
+
+copyright: Copyright © 2025 Yakhyokhuja Valikhujaev
+
+theme:
+  name: material
+  custom_dir: docs/overrides
+  palette:
+    - media: "(prefers-color-scheme)"
+      toggle:
+        icon: material/link
+        name: Switch to light mode
+    - media: "(prefers-color-scheme: light)"
+      scheme: default
+      primary: indigo
+      accent: indigo
+      toggle:
+        icon: material/toggle-switch
+        name: Switch to dark mode
+    - media: "(prefers-color-scheme: dark)"
+      scheme: slate
+      primary: black
+      accent: indigo
+      toggle:
+        icon: material/toggle-switch-off-outline
+        name: Switch to system preference
+  font:
+    text: Roboto
+    code: Roboto Mono
+  features:
+    - navigation.tabs
+    - navigation.top
+    - navigation.footer
+    - navigation.indexes
+    - navigation.instant
+    - navigation.tracking
+    - search.suggest
+    - search.highlight
+    - content.code.copy
+    - content.code.annotate
+    - content.action.edit
+    - content.action.view
+    - content.tabs.link
+    - announce.dismiss
+    - toc.follow
+
+  icon:
+    logo: material/book-open-page-variant
+    repo: fontawesome/brands/git-alt
+    admonition:
+      note: octicons/tag-16
+      abstract: octicons/checklist-16
+      info: octicons/info-16
+      tip: octicons/squirrel-16
+      success: octicons/check-16
+      question: octicons/question-16
+      warning: octicons/alert-16
+      failure: octicons/x-circle-16
+      danger: octicons/zap-16
+      bug: octicons/bug-16
+      example: octicons/beaker-16
+      quote: octicons/quote-16
+
+extra:
+  social:
+    - icon: fontawesome/brands/github
+      link: https://github.com/yakhyo
+    - icon: fontawesome/brands/python
+      link: https://pypi.org/project/uniface/
+    - icon: fontawesome/brands/x-twitter
+      link: https://x.com/y_valikhujaev
+  analytics:
+    provider: google
+    property: G-FGEHR2K5ZE
+
+extra_css:
+  - stylesheets/extra.css
+
+markdown_extensions:
+  - admonition
+  - footnotes
+  - attr_list
+  - md_in_html
+  - def_list
+  - tables
+  - toc:
+      permalink: false
+      toc_depth: 3
+  - pymdownx.superfences:
+      custom_fences:
+        - name: mermaid
+          class: mermaid
+          format: !!python/name:pymdownx.superfences.fence_code_format
+  - pymdownx.details
+  - pymdownx.highlight:
+      anchor_linenums: true
+      line_spans: __span
+      pygments_lang_class: true
+  - pymdownx.inlinehilite
+  - pymdownx.snippets
+  - pymdownx.tabbed:
+      alternate_style: true
+  - pymdownx.emoji:
+      emoji_index: !!python/name:material.extensions.emoji.twemoji
+      emoji_generator: !!python/name:material.extensions.emoji.to_svg
+  - pymdownx.tasklist:
+      custom_checkbox: true
+  - pymdownx.keys
+  - pymdownx.mark
+  - pymdownx.critic
+  - pymdownx.caret
+  - pymdownx.tilde
+
+plugins:
+  - search
+  - git-committers:
+      repository: yakhyo/uniface
+      branch: main
+      token: !ENV MKDOCS_GIT_COMMITTERS_APIKEY
+  - git-revision-date-localized:
+      enable_creation_date: true
+      type: timeago
+
+nav:
+  - Home: index.md
+  - Getting Started:
+      - Installation: installation.md
+      - Quickstart: quickstart.md
+      - Notebooks: notebooks.md
+      - Model Zoo: models.md
+      - Datasets: datasets.md
+  - Tutorials:
+      - Image Pipeline: recipes/image-pipeline.md
+      - Video & Webcam: recipes/video-webcam.md
+      - Face Search: recipes/face-search.md
+      - Batch Processing: recipes/batch-processing.md
+      - Anonymize Stream: recipes/anonymize-stream.md
+      - Custom Models: recipes/custom-models.md
+  - API Reference:
+      - Detection: modules/detection.md
+      - Recognition: modules/recognition.md
+      - Tracking: modules/tracking.md
+      - Landmarks: modules/landmarks.md
+      - Attributes: modules/attributes.md
+      - Parsing: modules/parsing.md
+      - Gaze: modules/gaze.md
+      - Anti-Spoofing: modules/spoofing.md
+      - Privacy: modules/privacy.md
+      - Indexing: modules/indexing.md
+  - Guides:
+      - Overview: concepts/overview.md
+      - Inputs & Outputs: concepts/inputs-outputs.md
+      - Coordinate Systems: concepts/coordinate-systems.md
+      - Execution Providers: concepts/execution-providers.md
+      - Model Cache: concepts/model-cache-offline.md
+      - Thresholds: concepts/thresholds-calibration.md
+  - Resources:
+      - Contributing: contributing.md
+      - License: license-attribution.md
+      - Releases: https://github.com/yakhyo/uniface/releases
+      - Discussions: https://github.com/yakhyo/uniface/discussions

pyproject.toml

@@ -0,0 +1,140 @@
+[project]
+name = "uniface"
+version = "3.1.0"
+description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Tracking, Landmark Analysis, Face Parsing, Gaze Estimation, Age, and Gender Detection"
+readme = "README.md"
+license = "MIT"
+authors = [{ name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" }]
+maintainers = [
+    { name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" },
+]
+
+requires-python = ">=3.10,<3.14"
+keywords = [
+    "face-detection",
+    "face-recognition",
+    "face-tracking",
+    "facial-landmarks",
+    "face-parsing",
+    "face-segmentation",
+    "gaze-estimation",
+    "age-detection",
+    "gender-detection",
+    "computer-vision",
+    "deep-learning",
+    "onnx",
+    "onnxruntime",
+    "face-analysis",
+    "bisenet",
+]
+
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "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",
+    "onnxruntime>=1.16.0",
+    "scikit-image>=0.19.0",
+    "scipy>=1.7.0",
+    "requests>=2.28.0",
+    "tqdm>=4.64.0",
+]
+
+[project.optional-dependencies]
+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://yakhyo.github.io/uniface"
+"Quick Start" = "https://yakhyo.github.io/uniface/quickstart/"
+"Model Zoo" = "https://yakhyo.github.io/uniface/models/"
+
+[build-system]
+requires = ["setuptools>=64", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+packages = { find = { where = ["."], include = ["uniface*"] } }
+
+[tool.setuptools.package-data]
+uniface = ["py.typed"]
+
+[tool.ruff]
+line-length = 120
+target-version = "py310"
+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.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"

requirements.txt

@@ -1,8 +1,7 @@
-pytest
-numpy
-opencv-python
-opencv-python-headless
-onnx
-onnxruntime
-requests
-torch
+numpy>=1.21.0
+opencv-python>=4.5.0
+onnxruntime>=1.16.0
+scikit-image>=0.19.0
+scipy>=1.7.0
+requests>=2.28.0
+tqdm>=4.64.0

scripts/release.sh

@@ -1,23 +0,0 @@
-#!/bin/bash
-
-# Exit on errors
-set -e
-
-cd "$(dirname "$0")"/..
-
-echo "Deleting existing release-related files..."
-rm -rf dist/ build/ *.egg-info
-
-pip install --upgrade pip
-pip install twine
-
-echo "Creating a package for the current release (PyPI compatible)..."
-python3 setup.py sdist bdist_wheel
-
-echo "Release package created successfully in the 'dist/' folder."
-
-
-echo "Uploading the package to PyPI..."
-twine upload dist/*
-
-echo "Release uploaded successfully!"

setup.py

@@ -1,43 +0,0 @@
-import os
-from setuptools import setup, find_packages
-
-# Read the README file for the long description
-long_description = ""
-if os.path.exists("README.md"):
-    with open("README.md", "r", encoding="utf-8") as f:
-        long_description = f.read()
-
-setup(
-    name="uniface",
-    version="0.1.1",
-    packages=find_packages(),
-    install_requires=[
-        "numpy",
-        "opencv-python",
-        "onnx",
-        "onnxruntime",
-        "requests",
-        "torch"
-    ],
-    extras_require={
-        "dev": ["pytest"],
-    },
-    description="UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Age, and Gender Detection",
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    author="Yakhyokhuja Valikhujaev",
-    author_email="yakhyo9696@gmail.com",
-    url="https://github.com/yakhyo/uniface",
-    license="MIT",
-    classifiers=[
-        "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.10",
-        "License :: OSI Approved :: MIT License",
-        "Operating System :: OS Independent",
-        "Topic :: Software Development :: Libraries :: Python Modules",
-    ],
-    keywords="face detection, face recognition, facial landmark, facial attribute, onnx, opencv, retinaface",
-    python_requires=">=3.8",
-)

test.py

@@ -1,57 +0,0 @@
-import os
-import cv2
-import numpy as np
-
-from uniface import RetinaFace, draw_detections
-
-
-def run_inference(image_path, save_image=False, vis_threshold=0.6):
-    """
-    Perform inference on an image, draw detections, and optionally save the output image.
-
-    Args:
-        image_path (str): Path to the input image.
-        save_image (bool): Whether to save the output image with detections.
-        vis_threshold (float): Confidence threshold for displaying detections.
-    """
-    # Load the image
-    original_image = cv2.imread(image_path)
-    if original_image is None:
-        print(f"Error: Could not read image from {image_path}")
-        return
-
-    # Perform face detection
-    boxes, landmarks = retinaface_inference.detect(original_image)
-
-    # Draw detections on the image
-    draw_detections(original_image, (boxes, landmarks), vis_threshold)
-
-    # Save the output image if requested
-    if save_image:
-        im_name = os.path.splitext(os.path.basename(image_path))[0]
-        save_name = f"{im_name}_out.jpg"
-        cv2.imwrite(save_name, original_image)
-        print(f"Image saved at '{save_name}'")
-
-
-if __name__ == '__main__':
-    import time
-
-    # Initialize and run the ONNX inference
-    retinaface_inference = RetinaFace(
-        model="retinaface_mnet_v2",
-        conf_thresh=0.5,
-        pre_nms_topk=5000,
-        nms_thresh=0.4,
-        post_nms_topk=750,
-    )
-
-    img_path = "assets/test.jpg"
-    avg = 0
-    for _ in range(50):
-        st = time.time()
-        run_inference(img_path, save_image=True, vis_threshold=0.6)
-        d = time.time() - st
-        print(d)
-        avg += d
-    print("avg", avg / 50)

tests/test_age_gender.py

@@ -0,0 +1,139 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+from __future__ import annotations
+
+import numpy as np
+import pytest
+
+from uniface.attribute import AgeGender, AttributeResult
+
+
+@pytest.fixture
+def age_gender_model():
+    return AgeGender()
+
+
+@pytest.fixture
+def mock_image():
+    return np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+def mock_bbox():
+    return [100, 100, 300, 300]
+
+
+def test_model_initialization(age_gender_model):
+    assert age_gender_model is not None, 'AgeGender model initialization failed.'
+
+
+def test_prediction_output_format(age_gender_model, mock_image, mock_bbox):
+    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):
+    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):
+    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):
+    test_bboxes = [
+        [50, 50, 150, 150],
+        [100, 100, 300, 300],
+        [50, 50, 400, 400],
+    ]
+
+    for bbox in test_bboxes:
+        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):
+    test_sizes = [(480, 640, 3), (720, 1280, 3), (1080, 1920, 3)]
+
+    for size in test_sizes:
+        mock_image = np.random.randint(0, 255, size, dtype=np.uint8)
+        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):
+    result1 = age_gender_model.predict(mock_image, mock_bbox)
+    result2 = age_gender_model.predict(mock_image, mock_bbox)
+
+    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]
+    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])
+    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):
+    bboxes = [
+        [50, 50, 150, 150],
+        [200, 200, 350, 350],
+        [400, 400, 550, 550],
+    ]
+
+    results = []
+    for bbox in bboxes:
+        result = age_gender_model.predict(mock_image, bbox)
+        results.append(result)
+
+    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):
+        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):
+    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_draw.py

@@ -0,0 +1,61 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+import numpy as np
+
+from uniface.draw import draw_gaze
+
+
+def _compute_gaze_delta(bbox: np.ndarray, pitch: float, yaw: float) -> tuple[int, int]:
+    """Replicate draw_gaze dx/dy math for verification."""
+    x_min, _, x_max, _ = map(int, bbox[:4])
+    length = x_max - x_min
+    dx = int(-length * np.sin(yaw) * np.cos(pitch))
+    dy = int(-length * np.sin(pitch))
+    return dx, dy
+
+
+def test_draw_gaze_yaw_only_moves_horizontally():
+    """Yaw-only input (pitch=0) should produce horizontal displacement only."""
+    image = np.zeros((200, 200, 3), dtype=np.uint8)
+    bbox = np.array([50, 50, 150, 150], dtype=np.float32)
+
+    yaw = 0.5
+    pitch = 0.0
+    dx, dy = _compute_gaze_delta(bbox, pitch, yaw)
+
+    assert dx != 0, 'Yaw-only should produce horizontal displacement'
+    assert dy == 0, 'Yaw-only should produce zero vertical displacement'
+
+    # Should not raise
+    draw_gaze(image, bbox, pitch, yaw, draw_bbox=False, draw_angles=False)
+
+
+def test_draw_gaze_pitch_only_moves_vertically():
+    """Pitch-only input (yaw=0) should produce vertical displacement only."""
+    image = np.zeros((200, 200, 3), dtype=np.uint8)
+    bbox = np.array([50, 50, 150, 150], dtype=np.float32)
+
+    yaw = 0.0
+    pitch = 0.5
+    dx, dy = _compute_gaze_delta(bbox, pitch, yaw)
+
+    assert dx == 0, 'Pitch-only should produce zero horizontal displacement'
+    assert dy != 0, 'Pitch-only should produce vertical displacement'
+
+    # Should not raise
+    draw_gaze(image, bbox, pitch, yaw, draw_bbox=False, draw_angles=False)
+
+
+def test_draw_gaze_modifies_image():
+    """draw_gaze should modify the image in place."""
+    image = np.zeros((200, 200, 3), dtype=np.uint8)
+    bbox = np.array([50, 50, 150, 150], dtype=np.float32)
+
+    original = image.copy()
+    draw_gaze(image, bbox, 0.3, 0.3)
+
+    assert not np.array_equal(image, original), 'draw_gaze should modify the image'

tests/test_factory.py

@@ -0,0 +1,238 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+from __future__ import annotations
+
+import numpy as np
+import pytest
+
+from uniface import (
+    create_detector,
+    create_landmarker,
+    create_recognizer,
+    list_available_detectors,
+)
+from uniface.constants import RetinaFaceWeights, SCRFDWeights
+from uniface.spoofing import MiniFASNet, create_spoofer
+
+
+# create_detector tests
+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'
+
+
+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'
+
+
+def test_create_detector_with_config():
+    """
+    Test creating detector with custom configuration.
+    """
+    detector = create_detector(
+        'retinaface',
+        model_name=RetinaFaceWeights.MNET_V2,
+        confidence_threshold=0.8,
+        nms_threshold=0.3,
+    )
+    assert detector is not None, 'Failed to create detector with custom config'
+
+
+def test_create_detector_invalid_method():
+    """
+    Test that invalid detector method raises an error.
+    """
+    with pytest.raises((ValueError, KeyError)):
+        create_detector('invalid_method')
+
+
+def test_create_detector_scrfd_with_model():
+    """
+    Test creating SCRFD detector 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
+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'
+
+
+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'
+
+
+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'
+
+
+def test_create_recognizer_invalid_method():
+    """
+    Test that invalid recognizer method raises an error.
+    """
+    with pytest.raises((ValueError, KeyError)):
+        create_recognizer('invalid_method')
+
+
+# create_landmarker tests
+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'
+
+
+def test_create_landmarker_default():
+    """
+    Test creating landmarker with default parameters.
+    """
+    landmarker = create_landmarker()
+    assert landmarker is not None, 'Failed to create default landmarker'
+
+
+def test_create_landmarker_invalid_method():
+    """
+    Test that invalid landmarker method raises an error.
+    """
+    with pytest.raises((ValueError, KeyError)):
+        create_landmarker('invalid_method')
+
+
+# list_available_detectors tests
+def test_list_available_detectors():
+    """
+    Test that list_available_detectors returns a dictionary.
+    """
+    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'
+
+
+def test_list_available_detectors_contents():
+    """
+    Test that list includes known detectors.
+    """
+    detectors = list_available_detectors()
+
+    # Should include at least these detectors
+    assert 'retinaface' in detectors, "Should include 'retinaface'"
+    assert 'scrfd' in detectors, "Should include 'scrfd'"
+
+
+# Integration tests
+def test_detector_inference_from_factory():
+    """
+    Test that detector created from factory can perform inference.
+    """
+    detector = create_detector('retinaface')
+    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'
+
+
+def test_recognizer_inference_from_factory():
+    """
+    Test that recognizer created from factory can perform inference.
+    """
+    recognizer = create_recognizer('arcface')
+    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'
+
+
+def test_landmarker_inference_from_factory():
+    """
+    Test that landmarker created from factory can perform inference.
+    """
+    landmarker = create_landmarker('2d106det')
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    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'
+
+
+def test_multiple_detector_creation():
+    """
+    Test that multiple detectors can be created independently.
+    """
+    detector1 = create_detector('retinaface')
+    detector2 = create_detector('scrfd')
+
+    assert detector1 is not None
+    assert detector2 is not None
+    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', 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)
+
+    faces_high = detector_high_thresh.detect(mock_image)
+    faces_low = detector_low_thresh.detect(mock_image)
+
+    # Both should work
+    assert isinstance(faces_high, list)
+    assert isinstance(faces_low, list)
+
+
+def test_factory_returns_correct_types():
+    """
+    Test that factory functions return instances of the correct types.
+    """
+    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'
+
+
+# create_spoofer tests
+def test_create_spoofer_default():
+    """Test creating a spoofer with default parameters."""
+    spoofer = create_spoofer()
+    assert isinstance(spoofer, MiniFASNet), 'Should return MiniFASNet instance'
+
+
+def test_create_spoofer_with_providers():
+    """Test that create_spoofer forwards providers kwarg without TypeError."""
+    spoofer = create_spoofer(providers=['CPUExecutionProvider'])
+    assert isinstance(spoofer, MiniFASNet), 'Should return MiniFASNet instance'

tests/test_landmark.py

@@ -0,0 +1,114 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+from __future__ import annotations
+
+import numpy as np
+import pytest
+
+from uniface.landmark import Landmark106
+
+
+@pytest.fixture
+def landmark_model():
+    return Landmark106()
+
+
+@pytest.fixture
+def mock_image():
+    return np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+def mock_bbox():
+    return [100, 100, 300, 300]
+
+
+def test_model_initialization(landmark_model):
+    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}'
+
+
+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}'
+
+
+def test_landmark_coordinates_within_image(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(mock_image, mock_bbox)
+
+    x_coords = landmarks[:, 0]
+    y_coords = landmarks[:, 1]
+
+    x1, y1, x2, y2 = mock_bbox
+    margin = 50
+
+    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'
+
+
+def test_different_bbox_sizes(landmark_model, mock_image):
+    test_bboxes = [
+        [50, 50, 150, 150],
+        [100, 100, 300, 300],
+        [50, 50, 400, 400],
+    ]
+
+    for bbox in test_bboxes:
+        landmarks = landmark_model.get_landmarks(mock_image, 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'
+
+
+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'
+
+
+def test_different_image_sizes(landmark_model, mock_bbox):
+    test_sizes = [(480, 640, 3), (720, 1280, 3), (1080, 1920, 3)]
+
+    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}'
+
+
+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'
+
+
+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'
+
+
+def test_landmark_distribution(landmark_model, mock_image, mock_bbox):
+    landmarks = landmark_model.get_landmarks(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'

tests/test_parsing.py

@@ -0,0 +1,269 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+from __future__ import annotations
+
+import numpy as np
+import pytest
+
+from uniface.constants import ParsingWeights, XSegWeights
+from uniface.parsing import BiSeNet, XSeg, 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
+
+
+# XSeg Tests
+
+
+def test_xseg_initialization():
+    """Test XSeg initialization."""
+    parser = XSeg()
+    assert parser is not None
+    assert parser.input_size == (256, 256)
+    assert parser.align_size == 256
+    assert parser.blur_sigma == 0
+
+
+def test_xseg_with_custom_params():
+    """Test XSeg with custom parameters."""
+    parser = XSeg(align_size=512, blur_sigma=5)
+    assert parser.align_size == 512
+    assert parser.blur_sigma == 5
+
+
+def test_xseg_preprocess():
+    """Test XSeg preprocessing."""
+    parser = XSeg()
+
+    # Create a dummy aligned face crop
+    face_crop = np.random.randint(0, 255, (256, 256, 3), dtype=np.uint8)
+
+    # Preprocess
+    preprocessed = parser.preprocess(face_crop)
+
+    assert preprocessed.shape == (1, 256, 256, 3)  # NHWC format
+    assert preprocessed.dtype == np.float32
+    assert preprocessed.min() >= 0
+    assert preprocessed.max() <= 1
+
+
+def test_xseg_postprocess():
+    """Test XSeg postprocessing."""
+    parser = XSeg()
+
+    # Create dummy model output (NHWC format)
+    dummy_output = np.random.rand(1, 256, 256, 1).astype(np.float32)
+
+    # Postprocess
+    mask = parser.postprocess(dummy_output, crop_size=(256, 256))
+
+    assert mask.shape == (256, 256)
+    assert mask.dtype == np.float32
+    assert mask.min() >= 0
+    assert mask.max() <= 1
+
+
+def test_xseg_parse_aligned():
+    """Test XSeg parse_aligned method."""
+    parser = XSeg()
+
+    # Create a dummy aligned face crop
+    face_crop = np.random.randint(0, 255, (256, 256, 3), dtype=np.uint8)
+
+    # Parse
+    mask = parser.parse_aligned(face_crop)
+
+    assert mask.shape == (256, 256)
+    assert mask.dtype == np.float32
+    assert mask.min() >= 0
+    assert mask.max() <= 1
+
+
+def test_xseg_parse_with_landmarks():
+    """Test XSeg parse method with landmarks."""
+    parser = XSeg()
+
+    # Create a dummy image
+    image = np.random.randint(0, 255, (480, 640, 3), dtype=np.uint8)
+
+    # Create dummy 5-point landmarks
+    landmarks = np.array(
+        [
+            [250, 200],  # left eye
+            [390, 200],  # right eye
+            [320, 280],  # nose
+            [260, 350],  # left mouth
+            [380, 350],  # right mouth
+        ],
+        dtype=np.float32,
+    )
+
+    # Parse
+    mask = parser.parse(image, landmarks=landmarks)
+
+    assert mask.shape == (480, 640)
+    assert mask.dtype == np.float32
+    assert mask.min() >= 0
+    assert mask.max() <= 1
+
+
+def test_xseg_parse_invalid_landmarks():
+    """Test XSeg parse with invalid landmarks shape."""
+    parser = XSeg()
+    image = np.random.randint(0, 255, (256, 256, 3), dtype=np.uint8)
+
+    # Wrong shape
+    invalid_landmarks = np.array([[0, 0], [1, 1], [2, 2]])
+
+    with pytest.raises(ValueError, match='Landmarks must have shape'):
+        parser.parse(image, landmarks=invalid_landmarks)
+
+
+def test_xseg_parse_with_inverse():
+    """Test XSeg parse_with_inverse method."""
+    parser = XSeg()
+
+    # Create a dummy image
+    image = np.random.randint(0, 255, (480, 640, 3), dtype=np.uint8)
+
+    # Create dummy 5-point landmarks
+    landmarks = np.array(
+        [
+            [250, 200],
+            [390, 200],
+            [320, 280],
+            [260, 350],
+            [380, 350],
+        ],
+        dtype=np.float32,
+    )
+
+    # Parse with inverse
+    mask, face_crop, inverse_matrix = parser.parse_with_inverse(image, landmarks)
+
+    assert mask.shape == (256, 256)
+    assert face_crop.shape == (256, 256, 3)
+    assert inverse_matrix.shape == (2, 3)
+
+
+def test_create_face_parser_xseg_enum():
+    """Test factory function with XSeg enum."""
+    parser = create_face_parser(XSegWeights.DEFAULT)
+    assert parser is not None
+    assert isinstance(parser, XSeg)
+
+
+def test_create_face_parser_xseg_string():
+    """Test factory function with XSeg string."""
+    parser = create_face_parser('xseg')
+    assert parser is not None
+    assert isinstance(parser, XSeg)

tests/test_recognition.py

@@ -0,0 +1,222 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+from __future__ import annotations
+
+import numpy as np
+import pytest
+
+from uniface.recognition import ArcFace, MobileFace, SphereFace
+
+
+@pytest.fixture
+def arcface_model():
+    """
+    Fixture to initialize the ArcFace model for testing.
+    """
+    return ArcFace()
+
+
+@pytest.fixture
+def mobileface_model():
+    """
+    Fixture to initialize the MobileFace model for testing.
+    """
+    return MobileFace()
+
+
+@pytest.fixture
+def sphereface_model():
+    """
+    Fixture to initialize the SphereFace model for testing.
+    """
+    return SphereFace()
+
+
+@pytest.fixture
+def mock_aligned_face():
+    """
+    Create a mock 112x112 aligned face image.
+    """
+    return np.random.randint(0, 255, (112, 112, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+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,
+    )
+
+
+# ArcFace Tests
+def test_arcface_initialization(arcface_model):
+    """
+    Test that the ArcFace model initializes correctly.
+    """
+    assert arcface_model is not None, 'ArcFace model initialization failed.'
+
+
+def test_arcface_embedding_shape(arcface_model, mock_aligned_face):
+    """
+    Test that ArcFace produces embeddings with the correct shape.
+    """
+    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'
+
+
+def test_arcface_normalized_embedding(arcface_model, mock_landmarks):
+    """
+    Test that normalized embeddings have unit length.
+    """
+    # Create a larger mock image for alignment
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    embedding = arcface_model.get_normalized_embedding(mock_image, 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}'
+
+
+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}'
+
+
+def test_arcface_consistency(arcface_model, mock_aligned_face):
+    """
+    Test that the same input produces the same embedding.
+    """
+    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'
+
+
+# MobileFace Tests
+def test_mobileface_initialization(mobileface_model):
+    """
+    Test that the MobileFace model initializes correctly.
+    """
+    assert mobileface_model is not None, 'MobileFace model initialization failed.'
+
+
+def test_mobileface_embedding_shape(mobileface_model, mock_aligned_face):
+    """
+    Test that MobileFace produces embeddings with the correct shape.
+    """
+    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'
+
+
+def test_mobileface_normalized_embedding(mobileface_model, mock_landmarks):
+    """
+    Test that MobileFace normalized embeddings have unit length.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    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}'
+
+
+# SphereFace Tests
+def test_sphereface_initialization(sphereface_model):
+    """
+    Test that the SphereFace model initializes correctly.
+    """
+    assert sphereface_model is not None, 'SphereFace model initialization failed.'
+
+
+def test_sphereface_embedding_shape(sphereface_model, mock_aligned_face):
+    """
+    Test that SphereFace produces embeddings with the correct shape.
+    """
+    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'
+
+
+def test_sphereface_normalized_embedding(sphereface_model, mock_landmarks):
+    """
+    Test that SphereFace normalized embeddings have unit length.
+    """
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+    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}'
+
+
+# Cross-model comparison tests
+def test_different_models_different_embeddings(arcface_model, mobileface_model, mock_aligned_face):
+    """
+    Test that different models produce different embeddings for the same input.
+    """
+    arcface_emb = arcface_model.get_embedding(mock_aligned_face)
+    mobileface_emb = mobileface_model.get_embedding(mock_aligned_face)
+
+    # 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'
+
+
+def test_embedding_similarity_computation(arcface_model, mock_aligned_face):
+    """
+    Test computing similarity between embeddings.
+    """
+    # Get two embeddings
+    emb1 = arcface_model.get_embedding(mock_aligned_face)
+
+    # Create a slightly different image
+    mock_aligned_face2 = mock_aligned_face.copy()
+    mock_aligned_face2[:10, :10] = 0  # Modify a small region
+    emb2 = arcface_model.get_embedding(mock_aligned_face2)
+
+    # 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}'
+
+
+def test_same_face_high_similarity(arcface_model, mock_aligned_face):
+    """
+    Test that the same face produces high similarity.
+    """
+    emb1 = arcface_model.get_embedding(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}'

tests/test_retinaface.py

@@ -1,78 +1,62 @@
-import pytest
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+from __future__ import annotations
+
 import numpy as np
-from uniface import RetinaFace
+import pytest
+
+from uniface.constants import RetinaFaceWeights
+from uniface.detection import RetinaFace
 
 
 @pytest.fixture
 def retinaface_model():
-    """
-    Fixture to initialize the RetinaFace model for testing.
-    """
     return RetinaFace(
-        model="retinaface_mnet_v2",
-        conf_thresh=0.5,
+        model_name=RetinaFaceWeights.MNET_V2,
+        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):
-    """
-    Test that the RetinaFace model initializes correctly.
-    """
-    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):
-    """
-    Test inference on a 640x640 BGR image.
-    """
-    # Generate a mock 640x640 BGR image
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = retinaface_model.detect(mock_image)
 
-    # Run inference
-    detections, landmarks = retinaface_model.detect(mock_image)
+    assert isinstance(faces, list), 'Detections should be a list.'
 
-    # Check output types
-    assert isinstance(detections, np.ndarray), "Detections should be a numpy array."
-    assert isinstance(landmarks, np.ndarray), "Landmarks should be a numpy array."
+    for face in faces:
+        # 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."
 
-    # Check that detections have the expected shape
-    if detections.size > 0:  # If faces are detected
-        assert detections.shape[1] == 5, "Each detection should have 5 values (x1, y1, x2, y2, score)."
+        bbox = face.bbox
+        assert len(bbox) == 4, 'BBox should have 4 values (x1, y1, x2, y2).'
 
-    # Check landmarks shape
-    if landmarks.size > 0:
-        assert landmarks.shape[1:] == (5, 2), "Landmarks should have shape (N, 5, 2)."
+        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):
-    """
-    Test that detections respect the confidence threshold.
-    """
-    # Generate a mock 640x640 BGR image
     mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    faces = retinaface_model.detect(mock_image)
 
-    # Run inference
-    detections, _ = retinaface_model.detect(mock_image)
-
-    # Ensure all detections have confidence scores above the threshold
-    if detections.size > 0:  # If faces are detected
-        confidence_scores = detections[:, 4]
-        assert (confidence_scores >= 0.5).all(), "Some detections have confidence below the threshold."
+    for face in faces:
+        confidence = face.confidence
+        assert confidence >= 0.5, f'Detection has confidence {confidence} below threshold 0.5'
 
 
 def test_no_faces_detected(retinaface_model):
-    """
-    Test inference on an image without detectable faces.
-    """
-    # Generate an empty (black) 640x640 image
     empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
-
-    # Run inference
-    detections, landmarks = retinaface_model.detect(empty_image)
-
-    # Ensure no detections or landmarks are found
-    assert detections.size == 0, "Detections should be empty for a blank image."
-    assert landmarks.size == 0, "Landmarks should be empty for a blank image."
+    faces = retinaface_model.detect(empty_image)
+    assert len(faces) == 0, 'Should detect no faces in a blank image.'

tests/test_scrfd.py

@@ -0,0 +1,78 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+from __future__ import annotations
+
+import numpy as np
+import pytest
+
+from uniface.constants import SCRFDWeights
+from uniface.detection import SCRFD
+
+
+@pytest.fixture
+def scrfd_model():
+    return SCRFD(
+        model_name=SCRFDWeights.SCRFD_500M_KPS,
+        confidence_threshold=0.5,
+        nms_threshold=0.4,
+    )
+
+
+def test_model_initialization(scrfd_model):
+    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.'
+
+    for face in faces:
+        # 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).'
+
+        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):
+    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+    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'
+
+
+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.'
+
+
+def test_different_input_sizes(scrfd_model):
+    test_sizes = [(480, 640, 3), (720, 1280, 3), (1080, 1920, 3)]
+
+    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}'
+
+
+def test_scrfd_10g_model():
+    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.'

tests/test_types.py

@@ -0,0 +1,281 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+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

@@ -0,0 +1,269 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+
+from __future__ import annotations
+
+import numpy as np
+import pytest
+
+from uniface import compute_similarity, face_alignment
+
+
+@pytest.fixture
+def mock_image():
+    """
+    Create a mock 640x640 BGR image.
+    """
+    return np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
+
+
+@pytest.fixture
+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,
+    )
+
+
+# compute_similarity tests
+def test_compute_similarity_same_embedding():
+    """
+    Test that similarity of an embedding with itself is 1.0.
+    """
+    embedding = np.random.randn(1, 512).astype(np.float32)
+    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}'
+
+
+def test_compute_similarity_range():
+    """
+    Test that similarity is always in the range [-1, 1].
+    """
+    # Test with multiple random embeddings
+    for _ in range(10):
+        emb1 = np.random.randn(1, 512).astype(np.float32)
+        emb2 = np.random.randn(1, 512).astype(np.float32)
+
+        # Normalize
+        emb1 = emb1 / np.linalg.norm(emb1)
+        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}'
+
+
+def test_compute_similarity_orthogonal():
+    """
+    Test that orthogonal embeddings have similarity close to 0.
+    """
+    # Create orthogonal embeddings
+    emb1 = np.zeros((1, 512), dtype=np.float32)
+    emb1[0, 0] = 1.0  # [1, 0, 0, ..., 0]
+
+    emb2 = np.zeros((1, 512), dtype=np.float32)
+    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}'
+
+
+def test_compute_similarity_opposite():
+    """
+    Test that opposite embeddings have similarity close to -1.
+    """
+    emb1 = np.ones((1, 512), dtype=np.float32)
+    emb1 = emb1 / np.linalg.norm(emb1)
+
+    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}'
+
+
+def test_compute_similarity_symmetry():
+    """
+    Test that similarity(A, B) == similarity(B, A).
+    """
+    emb1 = np.random.randn(1, 512).astype(np.float32)
+    emb2 = np.random.randn(1, 512).astype(np.float32)
+
+    # Normalize
+    emb1 = emb1 / np.linalg.norm(emb1)
+    emb2 = emb2 / np.linalg.norm(emb2)
+
+    sim_12 = compute_similarity(emb1, emb2)
+    sim_21 = compute_similarity(emb2, emb1)
+
+    assert np.isclose(sim_12, sim_21), 'Similarity should be symmetric'
+
+
+def test_compute_similarity_dtype():
+    """
+    Test that compute_similarity returns a float.
+    """
+    emb1 = np.random.randn(1, 512).astype(np.float32)
+    emb2 = np.random.randn(1, 512).astype(np.float32)
+
+    # Normalize
+    emb1 = emb1 / np.linalg.norm(emb1)
+    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)}'
+
+
+# face_alignment tests
+def test_face_alignment_output_shape(mock_image, mock_landmarks):
+    """
+    Test that face_alignment produces output with the correct shape.
+    """
+    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}'
+
+
+def test_face_alignment_dtype(mock_image, mock_landmarks):
+    """
+    Test that aligned face has the correct data type.
+    """
+    aligned, _ = face_alignment(mock_image, mock_landmarks, image_size=(112, 112))
+
+    assert aligned.dtype == np.uint8, f'Expected uint8, got {aligned.dtype}'
+
+
+def test_face_alignment_different_sizes(mock_image, mock_landmarks):
+    """
+    Test face alignment with different output sizes.
+    """
+    # Only test sizes that are multiples of 112 or 128 as required by the function
+    test_sizes = [(112, 112), (128, 128), (224, 224)]
+
+    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}'
+
+
+def test_face_alignment_consistency(mock_image, mock_landmarks):
+    """
+    Test that the same input produces the same aligned face.
+    """
+    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'
+
+
+def test_face_alignment_landmarks_as_list(mock_image):
+    """
+    Test that landmarks can be passed as a list of lists (converted to array).
+    """
+    landmarks_list = [
+        [38.2946, 51.6963],
+        [73.5318, 51.5014],
+        [56.0252, 71.7366],
+        [41.5493, 92.3655],
+        [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'
+
+
+def test_face_alignment_value_range(mock_image, mock_landmarks):
+    """
+    Test that aligned face pixel values are in valid range [0, 255].
+    """
+    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'
+
+
+def test_face_alignment_not_all_zeros(mock_image, mock_landmarks):
+    """
+    Test that aligned face is not all zeros (actual transformation occurred).
+    """
+    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'
+
+
+def test_face_alignment_from_different_positions(mock_image):
+    """
+    Test alignment with landmarks at different positions in the 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,
+        ),
+    ]
+
+    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]}'
+
+
+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,
+    )
+
+    aligned, _ = face_alignment(mock_image, landmarks_5pt, image_size=(112, 112))
+    assert aligned.shape == (112, 112, 3), 'Should work with 5-point landmarks'
+
+
+def test_compute_similarity_with_recognition_embeddings():
+    """
+    Test compute_similarity with realistic embedding dimensions.
+    """
+    # Simulate ArcFace/MobileFace/SphereFace embeddings (512-dim)
+    emb1 = np.random.randn(1, 512).astype(np.float32)
+    emb2 = np.random.randn(1, 512).astype(np.float32)
+
+    # Normalize (as done in get_normalized_embedding)
+    emb1 = emb1 / np.linalg.norm(emb1)
+    emb2 = emb2 / np.linalg.norm(emb2)
+
+    similarity = compute_similarity(emb1, emb2)
+
+    # Should be a valid similarity score
+    assert -1.0 <= similarity <= 1.0
+    assert isinstance(similarity, float | np.floating)

tools/README.md

@@ -0,0 +1,127 @@
+# Tools
+
+CLI utilities for testing and running UniFace features.
+
+## Available Tools
+
+| Tool | Description |
+|------|-------------|
+| `detect.py` | Face detection on image, video, or webcam |
+| `track.py` | Face tracking on video with ByteTrack |
+| `analyze.py` | Complete face analysis (detection + recognition + attributes) |
+| `anonymize.py` | Face anonymization/blurring for privacy |
+| `emotion.py` | Emotion detection (7 or 8 emotions) |
+| `gaze.py` | Gaze direction estimation |
+| `landmarks.py` | 106-point facial landmark detection |
+| `recognize.py` | Face embedding extraction and comparison |
+| `search.py` | Real-time face matching against reference |
+| `fairface.py` | FairFace attribute prediction (race, gender, age) |
+| `attribute.py` | Age and gender prediction |
+| `spoofing.py` | Face anti-spoofing detection |
+| `parse.py` | Face semantic segmentation (BiSeNet) |
+| `xseg.py` | Face segmentation (XSeg) |
+| `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
+
+Most 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/detect.py --source assets/test.jpg           # image
+python tools/detect.py --source video.mp4                  # video
+python tools/detect.py --source 0                          # webcam
+
+# Face tracking
+python tools/track.py --source video.mp4
+python tools/track.py --source video.mp4 --output tracked.mp4
+python tools/track.py --source 0                           # webcam
+
+# Face anonymization
+python tools/anonymize.py --source assets/test.jpg --method pixelate
+python tools/anonymize.py --source video.mp4 --method gaussian
+python tools/anonymize.py --source 0 --method pixelate
+
+# Age and gender
+python tools/attribute.py --source assets/test.jpg
+python tools/attribute.py --source 0
+
+# Emotion detection
+python tools/emotion.py --source assets/test.jpg
+python tools/emotion.py --source 0
+
+# Gaze estimation
+python tools/gaze.py --source assets/test.jpg
+python tools/gaze.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 (BiSeNet)
+python tools/parse.py --source assets/test.jpg
+python tools/parse.py --source 0
+
+# Face segmentation (XSeg)
+python tools/xseg.py --source assets/test.jpg
+python tools/xseg.py --source 0
+
+# Face anti-spoofing
+python tools/spoofing.py --source assets/test.jpg
+python tools/spoofing.py --source 0
+
+# Face analyzer
+python tools/analyze.py --source assets/test.jpg
+python tools/analyze.py --source 0
+
+# Face recognition (extract embedding)
+python tools/recognize.py --image assets/test.jpg
+
+# Face comparison
+python tools/recognize.py --image1 face1.jpg --image2 face2.jpg
+
+# Face search (match against reference)
+python tools/search.py --reference person.jpg --source 0
+python tools/search.py --reference person.jpg --source video.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/detect.py --source assets/test.jpg
+```

tools/_common.py

@@ -0,0 +1,29 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+from pathlib import Path
+
+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.
+
+    Args:
+        source: File path or camera ID string (e.g. ``"0"``).
+
+    Returns:
+        One of ``"image"``, ``"video"``, ``"camera"``, or ``"unknown"``.
+    """
+    if source.isdigit():
+        return 'camera'
+    suffix = Path(source).suffix.lower()
+    if suffix in IMAGE_EXTENSIONS:
+        return 'image'
+    if suffix in VIDEO_EXTENSIONS:
+        return 'video'
+    return 'unknown'

tools/analyze.py

@@ -0,0 +1,226 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face analysis using FaceAnalyzer.
+
+Usage:
+    python tools/analyze.py --source path/to/image.jpg
+    python tools/analyze.py --source path/to/video.mp4
+    python tools/analyze.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+from _common import get_source_type
+import cv2
+import numpy as np
+
+from uniface.analyzer import FaceAnalyzer
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
+from uniface.draw import draw_detections
+from uniface.recognition import ArcFace
+
+
+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, corner_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, corner_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, corner_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/anonymize.py

@@ -0,0 +1,265 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face anonymization/blurring for privacy.
+
+Usage:
+    python tools/anonymize.py --source path/to/image.jpg --method pixelate
+    python tools/anonymize.py --source path/to/video.mp4 --method gaussian
+    python tools/anonymize.py --source 0 --method pixelate  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+from _common import get_source_type
+import cv2
+
+from uniface.detection import RetinaFace
+from uniface.privacy import BlurFace
+
+
+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.draw 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 tools/anonymize.py --source photo.jpg
+
+  # Use Gaussian blur with custom strength
+  python tools/anonymize.py --source photo.jpg --method gaussian --blur-strength 5.0
+
+  # Real-time webcam anonymization
+  python tools/anonymize.py --source 0 --method pixelate
+
+  # Black boxes for maximum privacy
+  python tools/anonymize.py --source photo.jpg --method blackout
+
+  # Custom pixelation intensity
+  python tools/anonymize.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/attribute.py

@@ -0,0 +1,198 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Age and gender prediction on detected faces.
+
+Usage:
+    python tools/attribute.py --source path/to/image.jpg
+    python tools/attribute.py --source path/to/video.mp4
+    python tools/attribute.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+from _common import get_source_type
+import cv2
+
+from uniface.attribute import AgeGender
+from uniface.detection import SCRFD, RetinaFace
+from uniface.draw import draw_detections
+
+
+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, corner_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, corner_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, corner_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 2025-2026 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.detection import SCRFD, RetinaFace
+from uniface.draw 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, corner_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/detect.py

@@ -0,0 +1,226 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face detection on image, video, or webcam.
+
+Usage:
+    python tools/detect.py --source path/to/image.jpg
+    python tools/detect.py --source path/to/video.mp4
+    python tools/detect.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+import time
+
+from _common import get_source_type
+import cv2
+from tqdm import tqdm
+
+from uniface.detection import SCRFD, RetinaFace, YOLOv5Face, YOLOv8Face
+from uniface.draw import draw_detections
+
+
+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=image, bboxes=bboxes, scores=scores, landmarks=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,
+    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
+
+        t0 = time.perf_counter()
+        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,
+            draw_score=True,
+            corner_bbox=True,
+        )
+
+        inference_fps = 1.0 / max(time.perf_counter() - t0, 1e-9)
+        cv2.putText(frame, f'FPS: {inference_fps:.1f}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 65), 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")
+
+    prev_time = time.perf_counter()
+    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,
+            draw_score=True,
+            corner_bbox=True,
+        )
+
+        curr_time = time.perf_counter()
+        fps = 1.0 / max(curr_time - prev_time, 1e-9)
+        prev_time = curr_time
+        cv2.putText(frame, f'FPS: {fps:.1f}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 65), 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(
+        '--detector',
+        '--method',
+        type=str,
+        default='retinaface',
+        choices=['retinaface', 'scrfd', 'yolov5face', 'yolov8face'],
+    )
+    parser.add_argument('--threshold', type=float, default=0.25, help='Visualization threshold')
+    parser.add_argument('--preview', action='store_true', help='Show live preview during video processing')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    parser.add_argument('--output', type=str, default=None, help='Output video path (auto-generated if not specified)')
+    args = parser.parse_args()
+
+    # Initialize detector
+    if args.detector == 'retinaface':
+        detector = RetinaFace()
+    elif args.detector == 'scrfd':
+        detector = SCRFD()
+    elif args.detector == 'yolov5face':
+        from uniface.constants import YOLOv5FaceWeights
+
+        detector = YOLOv5Face(model_name=YOLOv5FaceWeights.YOLOV5M)
+    else:  # yolov8face
+        from uniface.constants import YOLOv8FaceWeights
+
+        detector = YOLOv8Face(model_name=YOLOv8FaceWeights.YOLOV8N)
+
+    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
+        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: 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/emotion.py

@@ -0,0 +1,198 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Emotion detection on detected faces.
+
+Usage:
+    python tools/emotion.py --source path/to/image.jpg
+    python tools/emotion.py --source path/to/video.mp4
+    python tools/emotion.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+from _common import get_source_type
+import cv2
+
+from uniface.attribute import Emotion
+from uniface.detection import SCRFD, RetinaFace
+from uniface.draw import draw_detections
+
+
+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, corner_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, corner_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, corner_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/fairface.py

@@ -0,0 +1,198 @@
+# Copyright 2025-2026 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
+
+from _common import get_source_type
+import cv2
+
+from uniface.attribute import FairFace
+from uniface.detection import SCRFD, RetinaFace
+from uniface.draw import draw_detections
+
+
+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, corner_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, corner_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, corner_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/faiss_search.py

@@ -0,0 +1,208 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""FAISS index build and multi-identity face search.
+
+Build a vector index from a directory of person sub-folders, then search
+against it in a video or webcam stream.
+
+Usage:
+    python tools/faiss_search.py build --faces-dir dataset/ --db-path ./vector_index
+    python tools/faiss_search.py run   --db-path ./vector_index --source video.mp4
+    python tools/faiss_search.py run   --db-path ./vector_index --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+from _common import IMAGE_EXTENSIONS, get_source_type
+import cv2
+
+from uniface import create_detector, create_recognizer
+from uniface.draw import draw_corner_bbox, draw_text_label
+from uniface.indexing import FAISS
+
+
+def _draw_face(image, bbox, text: str, color: tuple[int, int, int]) -> None:
+    x1, y1, x2, y2 = map(int, bbox[:4])
+    thickness = max(round(sum(image.shape[:2]) / 2 * 0.003), 2)
+    font_scale = max(0.4, min(0.7, (y2 - y1) / 200))
+    draw_corner_bbox(image, (x1, y1, x2, y2), color=color, thickness=thickness)
+    draw_text_label(image, text, x1, y1, bg_color=color, font_scale=font_scale)
+
+
+def process_frame(frame, detector, recognizer, store: FAISS, threshold: float = 0.4):
+    faces = detector.detect(frame)
+    if not faces:
+        return frame
+
+    for face in faces:
+        embedding = recognizer.get_normalized_embedding(frame, face.landmarks)
+        result, sim = store.search(embedding, threshold=threshold)
+
+        text = f'{result["person_id"]} ({sim:.2f})' if result else f'Unknown ({sim:.2f})'
+        color = (0, 255, 0) if result else (0, 0, 255)
+        _draw_face(frame, face.bbox, text, color)
+
+    return frame
+
+
+def process_video(detector, recognizer, store: FAISS, video_path: str, save_dir: str, threshold: float = 0.4):
+    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}_faiss_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, store, 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, store: FAISS, camera_id: int = 0, threshold: float = 0.4):
+    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, store, threshold)
+
+        cv2.imshow('Vector Search', frame)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def build(args: argparse.Namespace) -> None:
+    faces_dir = Path(args.faces_dir)
+    if not faces_dir.is_dir():
+        print(f"Error: '{faces_dir}' is not a directory")
+        return
+
+    detector = create_detector()
+    recognizer = create_recognizer()
+    store = FAISS(db_path=args.db_path)
+
+    persons = sorted(p.name for p in faces_dir.iterdir() if p.is_dir())
+    if not persons:
+        print(f"Error: No sub-folders found in '{faces_dir}'")
+        return
+
+    print(f'Found {len(persons)} persons: {", ".join(persons)}')
+
+    total_added = 0
+    for person_id in persons:
+        person_dir = faces_dir / person_id
+        images = [f for f in person_dir.iterdir() if f.suffix.lower() in IMAGE_EXTENSIONS]
+
+        added = 0
+        for img_path in images:
+            image = cv2.imread(str(img_path))
+            if image is None:
+                print(f'  Warning: Failed to read {img_path}, skipping')
+                continue
+
+            faces = detector.detect(image)
+            if not faces:
+                print(f'  Warning: No face detected in {img_path}, skipping')
+                continue
+
+            embedding = recognizer.get_normalized_embedding(image, faces[0].landmarks)
+            store.add(embedding, {'person_id': person_id, 'source': str(img_path)})
+            added += 1
+
+        total_added += added
+        if added:
+            print(f'  {person_id}: {added} embeddings added')
+        else:
+            print(f'  {person_id}: no valid faces found')
+
+    store.save()
+    print(f'\nIndex saved to {args.db_path} ({total_added} vectors, {len(persons)} persons)')
+
+
+def run(args: argparse.Namespace) -> None:
+    detector = create_detector()
+    recognizer = create_recognizer()
+
+    store = FAISS(db_path=args.db_path)
+    if not store.load():
+        print(f"Error: No index found at '{args.db_path}'")
+        return
+    print(f'Loaded FAISS index: {store}')
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, recognizer, store, 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, store, args.source, args.save_dir, args.threshold)
+    else:
+        print(f"Error: Source must be a video file or camera ID, not '{args.source}'")
+
+
+def main():
+    parser = argparse.ArgumentParser(description='FAISS vector search')
+    sub = parser.add_subparsers(dest='command', required=True)
+
+    build_p = sub.add_parser('build', help='Build a FAISS index from person sub-folders')
+    build_p.add_argument('--faces-dir', type=str, required=True, help='Directory with person sub-folders')
+    build_p.add_argument('--db-path', type=str, default='./vector_index', help='Where to save the index')
+
+    run_p = sub.add_parser('run', help='Search faces against a FAISS index')
+    run_p.add_argument('--db-path', type=str, required=True, help='Path to saved FAISS index')
+    run_p.add_argument('--source', type=str, required=True, help='Video path or camera ID')
+    run_p.add_argument('--threshold', type=float, default=0.4, help='Similarity threshold')
+    run_p.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+
+    args = parser.parse_args()
+
+    if args.command == 'build':
+        build(args)
+    elif args.command == 'run':
+        run(args)
+
+
+if __name__ == '__main__':
+    main()

tools/gaze.py

@@ -0,0 +1,174 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Gaze estimation on detected faces.
+
+Usage:
+    python tools/gaze.py --source path/to/image.jpg
+    python tools/gaze.py --source path/to/video.mp4
+    python tools/gaze.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+from _common import get_source_type
+import cv2
+import numpy as np
+
+from uniface.detection import RetinaFace
+from uniface.draw import draw_gaze
+from uniface.gaze import MobileGaze
+
+
+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 +1,172 @@
+# Copyright 2025-2026 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
+
+from _common import get_source_type
+import cv2
+
+from uniface.detection import SCRFD, RetinaFace
+from uniface.landmark import Landmark106
+
+
+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/parse.py

@@ -0,0 +1,234 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face parsing on detected faces.
+
+Usage:
+    python tools/parse.py --source path/to/image.jpg
+    python tools/parse.py --source path/to/video.mp4
+    python tools/parse.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+from _common import get_source_type
+import cv2
+import numpy as np
+
+from uniface.constants import ParsingWeights
+from uniface.detection import RetinaFace
+from uniface.draw import vis_parsing_maps
+from uniface.parsing import BiSeNet
+
+
+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=args.model)
+
+    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/recognize.py

@@ -0,0 +1,110 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face recognition: extract embeddings or compare two faces.
+
+Usage:
+    python tools/recognize.py --image path/to/image.jpg
+    python tools/recognize.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()