feat: Update API format and gaze estimation models (#82)

* docs: Update documentation

* fix: Update several missing docs and tests

* docs: Clean up and remove redundants

* fix: Fix the gaze output formula and change the output order

* chore: Update model weights for gaze estimation

* release: Update release version to v3.0.0

.github/workflows/ci.yml

@@ -1,4 +1,4 @@
-name: CI
+name: Build
 
 on:
   push:

.gitignore

@@ -1,4 +1,5 @@
 tmp_*
+.vscode/
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

CONTRIBUTING.md

@@ -59,12 +59,12 @@ This project uses [Ruff](https://docs.astral.sh/ruff/) for linting and formattin
 #### General Rules
 
 - **Line length:** 120 characters maximum
-- **Python version:** 3.11+ (use modern syntax)
+- **Python version:** 3.10+ (use modern syntax)
 - **Quote style:** Single quotes for strings, double quotes for docstrings
 
 #### Type Hints
 
-Use modern Python 3.11+ type hints (PEP 585 and PEP 604):
+Use modern Python 3.10+ type hints (PEP 585 and PEP 604):
 
 ```python
 # Preferred (modern)
@@ -82,23 +82,23 @@ def process(items: List[str], config: Optional[Dict[str, int]] = None) -> Tuple[
 Use [Google-style docstrings](https://google.github.io/styleguide/pyguide.html#38-comments-and-docstrings) for all public APIs:
 
 ```python
-def detect_faces(image: np.ndarray, threshold: float = 0.5) -> list[Face]:
-    """Detect faces in an image.
+def create_detector(method: str = 'retinaface', **kwargs: Any) -> BaseDetector:
+    """Factory function to create face detectors.
 
     Args:
-        image: Input image as a numpy array with shape (H, W, C) in BGR format.
-        threshold: Confidence threshold for filtering detections. Defaults to 0.5.
+        method: Detection method. Options: 'retinaface', 'scrfd', 'yolov5face', 'yolov8face'.
+        **kwargs: Detector-specific parameters.
 
     Returns:
-        List of Face objects containing bounding boxes, confidence scores,
-        and facial landmarks.
+        Initialized detector instance.
 
     Raises:
-        ValueError: If the input image has invalid dimensions.
+        ValueError: If method is not supported.
 
     Example:
-        >>> from uniface import detect_faces
-        >>> faces = detect_faces(image, threshold=0.8)
+        >>> from uniface import create_detector
+        >>> detector = create_detector('retinaface', confidence_threshold=0.8)
+        >>> faces = detector.detect(image)
         >>> print(f"Found {len(faces)} faces")
     """
 ```
@@ -174,16 +174,16 @@ When adding a new model or feature:
 
 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) |
+| 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) |
+| Gaze Estimation    | [08_gaze_estimation.ipynb](examples/08_gaze_estimation.ipynb)       |
 
 ## Questions?
 

README.md

@@ -1,32 +1,35 @@
-# UniFace: All-in-One Face Analysis Library
+<h1 align="center">UniFace: All-in-One Face Analysis Library</h1>
 
 <div align="center">
 
-[![PyPI](https://img.shields.io/pypi/v/uniface.svg?label=PyPI)](https://pypi.org/project/uniface/)
-[![Python](https://img.shields.io/badge/Python-3.10%2B-blue)](https://www.python.org/)
+[![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)
-[![CI](https://github.com/yakhyo/uniface/actions/workflows/ci.yml/badge.svg)](https://github.com/yakhyo/uniface/actions)
+[![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)
-[![Docs](https://img.shields.io/badge/Docs-UniFace-blue.svg)](https://yakhyo.github.io/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>
 
 <div align="center">
-    <img src=".github/logos/logo_web.webp" width=80%>
+    <img src="https://raw.githubusercontent.com/yakhyo/uniface/main/.github/logos/new/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.
 
-> 💬 **Have questions?** [Chat with this codebase on DeepWiki](https://deepwiki.com/yakhyo/uniface) - AI-powered docs that let you ask anything about UniFace.
-
 ---
 
 ## Features
 
 - **Face Detection** — RetinaFace, SCRFD, YOLOv5-Face, and YOLOv8-Face with 5-point landmarks
 - **Face Recognition** — ArcFace, MobileFace, and SphereFace embeddings
-- **Facial Landmarks** — 106-point landmark localization
-- **Face Parsing** — BiSeNet semantic segmentation (19 classes)
+- **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
 - **Anti-Spoofing** — Face liveness detection with MiniFASNet
@@ -37,31 +40,66 @@
 
 ## Installation
 
+**Standard installation**
+
 ```bash
-# Standard installation
 pip install uniface
+```
 
-# GPU support (CUDA)
+**GPU support (CUDA)**
+
+```bash
 pip install uniface[gpu]
+```
 
-# From source
+**From source (latest version)**
+
+```bash
 git clone https://github.com/yakhyo/uniface.git
 cd uniface && pip install -e .
 ```
 
+**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'`
+
 ---
 
-## Quick Example
+## 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 Example (Detection)
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
-# Initialize detector (models auto-download on first use)
 detector = RetinaFace()
 
-# Detect faces
 image = cv2.imread("photo.jpg")
+if image is None:
+    raise ValueError("Failed to load image. Check the path to 'photo.jpg'.")
+
 faces = detector.detect(image)
 
 for face in faces:
@@ -71,14 +109,54 @@ for face in faces:
 ```
 
 <div align="center">
-    <img src="assets/test_result.png">
+    <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.analyzer import FaceAnalyzer
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+
+detector = RetinaFace()
+recognizer = ArcFace()
+
+analyzer = FaceAnalyzer(detector, recognizer=recognizer)
+
+image = cv2.imread("photo.jpg")
+if image is None:
+    raise ValueError("Failed to load image. Check the path to 'photo.jpg'.")
+
+faces = analyzer.analyze(image)
+
+for face in faces:
+    print(face.bbox, face.embedding.shape if face.embedding is not None else None)
+```
+
+---
+
+## Execution Providers (ONNX Runtime)
+
+```python
+from uniface.detection import RetinaFace
+
+# Force CPU-only inference
+detector = RetinaFace(providers=["CPUExecutionProvider"])
+```
+
+See more in the docs:
+https://yakhyo.github.io/uniface/concepts/execution-providers/
+
+---
+
 ## Documentation
 
-📚 **Full documentation**: [yakhyo.github.io/uniface](https://yakhyo.github.io/uniface/)
+Full documentation: https://yakhyo.github.io/uniface/
 
 | Resource | Description |
 |----------|-------------|
@@ -88,7 +166,9 @@ for face in faces:
 | [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 |
 
-### Jupyter Notebooks
+---
+
+## Jupyter Notebooks
 
 | Example | Colab | Description |
 |---------|:-----:|-------------|
@@ -100,26 +180,54 @@ for face in faces:
 | [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 |
+
+---
+
+## 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
 
-- [yakhyo/retinaface-pytorch](https://github.com/yakhyo/retinaface-pytorch) — RetinaFace training
-- [yakhyo/yolov5-face-onnx-inference](https://github.com/yakhyo/yolov5-face-onnx-inference) — YOLOv5-Face ONNX
-- [yakhyo/yolov8-face-onnx-inference](https://github.com/yakhyo/yolov8-face-onnx-inference) — YOLOv8-Face ONNX
-- [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition) — ArcFace, MobileFace, SphereFace
-- [yakhyo/face-parsing](https://github.com/yakhyo/face-parsing) — BiSeNet face parsing
-- [yakhyo/gaze-estimation](https://github.com/yakhyo/gaze-estimation) — MobileGaze training
-- [yakhyo/face-anti-spoofing](https://github.com/yakhyo/face-anti-spoofing) — MiniFASNet inference
-- [yakhyo/fairface-onnx](https://github.com/yakhyo/fairface-onnx) — FairFace attributes
-- [deepinsight/insightface](https://github.com/deepinsight/insightface) — Model architectures
+| 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
 
-Contributions are welcome! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
+Contributions are welcome. Please see [CONTRIBUTING.md](CONTRIBUTING.md).
+
+## 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
 

docs/concepts/coordinate-systems.md

@@ -93,7 +93,7 @@ landmarks = face.landmarks  # Shape: (5, 2)
 Returned by `Landmark106`:
 
 ```python
-from uniface import Landmark106
+from uniface.landmark import Landmark106
 
 landmarker = Landmark106()
 landmarks = landmarker.get_landmarks(image, face.bbox)
@@ -174,7 +174,7 @@ yaw = -90° ────┼──── yaw = +90°
 Face alignment uses 5-point landmarks to normalize face orientation:
 
 ```python
-from uniface import face_alignment
+from uniface.face_utils import face_alignment
 
 # Align face to standard template
 aligned_face = face_alignment(image, face.landmarks)

docs/concepts/execution-providers.md

@@ -9,7 +9,7 @@ UniFace uses ONNX Runtime for model inference, which supports multiple hardware
 UniFace automatically selects the optimal execution provider based on available hardware:
 
 ```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 # Automatically uses best available provider
 detector = RetinaFace()
@@ -17,12 +17,40 @@ detector = RetinaFace()
 
 **Priority order:**
 
-1. **CUDAExecutionProvider** - NVIDIA GPU
-2. **CoreMLExecutionProvider** - Apple Silicon
+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
@@ -147,7 +175,7 @@ pip install uniface[gpu]
 Smaller input sizes are faster but may reduce accuracy:
 
 ```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 # Faster, lower accuracy
 detector = RetinaFace(input_size=(320, 320))

docs/concepts/inputs-outputs.md

@@ -53,6 +53,7 @@ class Face:
     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
@@ -177,7 +178,7 @@ print(f"Norm: {np.linalg.norm(embedding):.4f}")  # ~1.0
 ### Similarity Computation
 
 ```python
-from uniface import compute_similarity
+from uniface.face_utils import compute_similarity
 
 similarity = compute_similarity(embedding1, embedding2)
 # Returns: float between -1 and 1 (cosine similarity)
@@ -199,16 +200,16 @@ print(f"Classes: {np.unique(mask)}")  # [0, 1, 2, ...]
 
 | ID | Class | ID | Class |
 |----|-------|----|-------|
-| 0 | Background | 10 | Ear Ring |
-| 1 | Skin | 11 | Nose |
-| 2 | Left Eyebrow | 12 | Mouth |
-| 3 | Right Eyebrow | 13 | Upper Lip |
-| 4 | Left Eye | 14 | Lower Lip |
-| 5 | Right Eye | 15 | Neck |
-| 6 | Eye Glasses | 16 | Neck Lace |
-| 7 | Left Ear | 17 | Cloth |
-| 8 | Right Ear | 18 | Hair |
-| 9 | Hat | | |
+| 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 | | |
 
 ---
 

docs/concepts/model-cache-offline.md

@@ -9,7 +9,7 @@ UniFace automatically downloads and caches models. This page explains how model
 Models are downloaded on first use:
 
 ```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 # First run: downloads model to cache
 detector = RetinaFace()  # ~3.5 MB download
@@ -32,9 +32,9 @@ Default cache directory:
 
 ```
 ~/.uniface/models/
-├── retinaface_mv2.onnx
-├── w600k_mbf.onnx
-├── 2d106det.onnx
+├── retinaface_mnet_v2.onnx
+├── arcface_mnet.onnx
+├── 2d_106.onnx
 ├── gaze_resnet34.onnx
 ├── parsing_resnet18.onnx
 └── ...
@@ -44,44 +44,57 @@ Default cache directory:
 
 ## Custom Cache Directory
 
-Specify a custom cache location:
+Use the programmatic API to change the cache location at runtime:
 
 ```python
-from uniface.model_store import verify_model_weights
-from uniface.constants import RetinaFaceWeights
+from uniface.model_store import get_cache_dir, set_cache_dir
 
-# Download to custom directory
-model_path = verify_model_weights(
-    RetinaFaceWeights.MNET_V2,
-    root='./my_models'
-)
-print(f"Model at: {model_path}")
+# 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:
+Download models before deployment using the concurrent downloader:
 
 ```python
-from uniface.model_store import verify_model_weights
+from uniface.model_store import download_models
 from uniface.constants import (
     RetinaFaceWeights,
     ArcFaceWeights,
     AgeGenderWeights,
 )
 
-# Download all needed models
-models = [
+# Download multiple models concurrently (up to 4 threads by default)
+paths = download_models([
     RetinaFaceWeights.MNET_V2,
     ArcFaceWeights.MNET,
     AgeGenderWeights.DEFAULT,
-]
+])
 
-for model in models:
-    path = verify_model_weights(model)
-    print(f"Downloaded: {path}")
+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:
@@ -115,11 +128,20 @@ print(f"Copy from: {path}")
 scp -r ~/.uniface/models/ user@offline-machine:~/.uniface/models/
 ```
 
-### 3. Use normally
+### 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 import RetinaFace
+from uniface.detection import RetinaFace
 detector = RetinaFace()  # No network required
 ```
 
@@ -182,7 +204,12 @@ If a model fails verification, it's re-downloaded automatically.
 
 ## Clear Cache
 
-Remove cached models:
+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
@@ -198,20 +225,35 @@ Models will be re-downloaded on next use.
 
 ## Environment Variables
 
-Set custom cache location via environment variable:
+There are three equivalent ways to configure the cache directory:
 
-```bash
-export UNIFACE_CACHE_DIR=/path/to/custom/cache
+**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 import RetinaFace
+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

docs/concepts/overview.md

@@ -28,6 +28,10 @@ graph TB
         PRIV[Privacy]
     end
 
+    subgraph Tracking
+        TRK[BYTETracker]
+    end
+
     subgraph Output
         FACE[Face Objects]
     end
@@ -40,9 +44,11 @@ graph TB
     DET --> PARSE
     DET --> SPOOF
     DET --> PRIV
+    DET --> TRK
     REC --> FACE
     LMK --> FACE
     ATTR --> FACE
+    TRK --> FACE
 ```
 
 ---
@@ -74,12 +80,14 @@ tqdm          # Progress bars
 Factory functions and direct instantiation:
 
 ```python
-# Factory function
-detector = create_detector('retinaface')
+from uniface.detection import RetinaFace
 
-# Direct instantiation (recommended)
-from uniface import RetinaFace
 detector = RetinaFace()
+
+# Or via factory function
+from uniface.detection import create_detector
+
+detector = create_detector('retinaface')
 ```
 
 ### 4. Type Safety
@@ -99,6 +107,7 @@ def detect(self, image: np.ndarray) -> list[Face]:
 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
@@ -109,7 +118,7 @@ uniface/
 ├── constants.py    # Model weights and URLs
 ├── model_store.py  # Model download and caching
 ├── onnx_utils.py   # ONNX Runtime utilities
-└── visualization.py # Drawing utilities
+└── draw.py         # Drawing utilities
 ```
 
 ---
@@ -120,7 +129,9 @@ A typical face analysis workflow:
 
 ```python
 import cv2
-from uniface import RetinaFace, ArcFace, AgeGender
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
 
 # 1. Initialize models
 detector = RetinaFace()
@@ -151,12 +162,21 @@ for face in faces:
 For convenience, `FaceAnalyzer` combines multiple modules:
 
 ```python
-from uniface import FaceAnalyzer
+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(
-    detect=True,
-    recognize=True,
-    attributes=True
+    detector,
+    recognizer=recognizer,
+    age_gender=age_gender,
+    fairface=fairface,
 )
 
 faces = analyzer.analyze(image)
@@ -170,7 +190,7 @@ for face in faces:
 ## Model Lifecycle
 
 1. **First use**: Model is downloaded from GitHub releases
-2. **Cached**: Stored in `~/.uniface/models/`
+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
@@ -179,6 +199,11 @@ for face in faces:
 # 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

docs/concepts/thresholds-calibration.md

@@ -11,7 +11,7 @@ This page explains how to tune detection and recognition thresholds for your use
 Controls minimum confidence for face detection:
 
 ```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 # Default (balanced)
 detector = RetinaFace(confidence_threshold=0.5)
@@ -81,7 +81,7 @@ For identity verification (same person check):
 
 ```python
 import numpy as np
-from uniface import compute_similarity
+from uniface.face_utils import compute_similarity
 
 similarity = compute_similarity(embedding1, embedding2)
 
@@ -199,7 +199,7 @@ else:
 For drawing detections, filter by confidence:
 
 ```python
-from uniface.visualization import draw_detections
+from uniface.draw import draw_detections
 
 # Only draw high-confidence detections
 bboxes = [f.bbox for f in faces if f.confidence > 0.7]

docs/contributing.md

@@ -32,7 +32,7 @@ ruff check . --fix
 **Guidelines:**
 
 - Line length: 120
-- Python 3.11+ type hints
+- Python 3.10+ type hints
 - Google-style docstrings
 
 ---

docs/index.md

@@ -10,12 +10,17 @@ template: home.html
 
 # UniFace { .hero-title }
 
-<p class="hero-subtitle">A lightweight, production-ready face analysis library built on ONNX Runtime</p>
+<p class="hero-subtitle">All-in-One Open-Source Face Analysis Library</p>
 
-[![PyPI](https://img.shields.io/pypi/v/uniface.svg?label=PyPI)](https://pypi.org/project/uniface/)
-[![Python](https://img.shields.io/badge/Python-3.10%2B-blue)](https://www.python.org/)
+[![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/new/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 }
@@ -54,6 +59,11 @@ BiSeNet semantic segmentation with 19 facial component classes.
 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.

docs/installation.md

@@ -6,7 +6,7 @@ This guide covers all installation options for UniFace.
 
 ## Requirements
 
-- **Python**: 3.11 or higher
+- **Python**: 3.10 or higher
 - **Operating Systems**: macOS, Linux, Windows
 
 ---
@@ -107,7 +107,9 @@ UniFace has minimal dependencies:
 |---------|---------|
 | `numpy` | Array operations |
 | `opencv-python` | Image processing |
+| `onnx` | ONNX model format support |
 | `onnxruntime` | Model inference |
+| `scikit-image` | Geometric transforms |
 | `requests` | Model download |
 | `tqdm` | Progress bars |
 
@@ -126,7 +128,7 @@ import onnxruntime as ort
 print(f"Available providers: {ort.get_available_providers()}")
 
 # Quick test
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 detector = RetinaFace()
 print("Installation successful!")
 ```
@@ -137,11 +139,11 @@ print("Installation successful!")
 
 ### Import Errors
 
-If you encounter import errors, ensure you're using Python 3.11+:
+If you encounter import errors, ensure you're using Python 3.10+:
 
 ```bash
 python --version
-# Should show: Python 3.11.x or higher
+# Should show: Python 3.10.x or higher
 ```
 
 ### Model Download Issues

docs/models.md

@@ -22,7 +22,7 @@ RetinaFace models are trained on the WIDER FACE dataset.
 !!! 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/detection.py --source <image> --iterations 100`
+    **Speed**: Benchmark on your own hardware using `python tools/detect.py --source <image>`
 
 ---
 
@@ -32,13 +32,13 @@ SCRFD (Sample and Computation Redistribution for Efficient Face Detection) model
 
 | Model Name       | Params | Size  | Easy   | Medium | Hard   |
 | ---------------- | ------ | ----- | ------ | ------ | ------ |
-| `SCRFD_500M`   | 0.6M   | 2.5MB | 90.57% | 88.12% | 68.51% |
-| `SCRFD_10G` :material-check-circle: | 4.2M   | 17MB  | 95.16% | 93.87% | 83.05% |
+| `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/detection.py --source <image> --iterations 100`
+    **Speed**: Benchmark on your own hardware using `python tools/detect.py --source <image>`
 
 ---
 
@@ -55,7 +55,7 @@ YOLOv5-Face models provide detection with 5-point facial landmarks, trained on W
 !!! 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/detection.py --source <image> --iterations 100`
+    **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.
@@ -74,7 +74,7 @@ YOLOv8-Face models use anchor-free design with DFL (Distribution Focal Loss) for
 !!! info "Accuracy & Benchmarks"
     **Accuracy**: WIDER FACE validation set (Easy/Medium/Hard subsets)
 
-    **Speed**: Benchmark on your own hardware using `python tools/detection.py --source <image> --method yolov8face`
+    **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.
@@ -219,7 +219,7 @@ Facial landmark localization model.
 | `AFFECNET7` | 7       | 0.5M   | 2MB  |
 | `AFFECNET8` | 8       | 0.5M   | 2MB  |
 
-**Classes (7)**: Neutral, Happy, Sad, Surprise, Fear, Disgust, Anger
+**Classes (7)**: Neutral, Happy, Sad, Surprise, Fear, Disgust, Angry
 
 **Classes (8)**: Above + Contempt
 
@@ -279,13 +279,13 @@ BiSeNet (Bilateral Segmentation Network) models for semantic face parsing. Segme
 
 | # | Class | # | Class | # | Class |
 |---|-------|---|-------|---|-------|
-| 1 | Background | 8 | Left Ear | 15 | Neck |
-| 2 | Skin | 9 | Right Ear | 16 | Neck Lace |
-| 3 | Left Eyebrow | 10 | Ear Ring | 17 | Cloth |
-| 4 | Right Eyebrow | 11 | Nose | 18 | Hair |
-| 5 | Left Eye | 12 | Mouth | 19 | Hat |
-| 6 | Right Eye | 13 | Upper Lip | | |
-| 7 | Eye Glasses | 14 | Lower Lip | | |
+| 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:**
 
@@ -300,6 +300,32 @@ BiSeNet (Bilateral Segmentation Network) models for semantic face parsing. Segme
 
 ---
 
+### 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
@@ -323,10 +349,14 @@ Face anti-spoofing models for liveness detection. Detect if a face is real (live
 
 Models are automatically downloaded and cached on first use.
 
-- **Cache location**: `~/.uniface/models/`
+- **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
@@ -343,6 +373,7 @@ Models are automatically downloaded and cached on first use.
 - **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

docs/modules/attributes.md

@@ -21,7 +21,8 @@ Predicts exact age and binary gender.
 ### Basic Usage
 
 ```python
-from uniface import RetinaFace, AgeGender
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
 
 detector = RetinaFace()
 age_gender = AgeGender()
@@ -54,7 +55,8 @@ Predicts gender, age group, and race with balanced demographics.
 ### Basic Usage
 
 ```python
-from uniface import RetinaFace, FairFace
+from uniface.attribute import FairFace
+from uniface.detection import RetinaFace
 
 detector = RetinaFace()
 fairface = FairFace()
@@ -120,7 +122,7 @@ Predicts facial emotions. Requires PyTorch.
 ### Basic Usage
 
 ```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.attribute import Emotion
 from uniface.constants import DDAMFNWeights
 
@@ -147,7 +149,7 @@ for face in faces:
     | Surprise |
     | Fear |
     | Disgust |
-    | Anger |
+    | Angry |
 
 === "8-Class (AFFECNET8)"
 
@@ -159,7 +161,7 @@ for face in faces:
     | Surprise |
     | Fear |
     | Disgust |
-    | Anger |
+    | Angry |
     | Contempt |
 
 ### Model Variants
@@ -182,7 +184,8 @@ emotion = Emotion(model_name=DDAMFNWeights.AFFECNET8)
 ### Full Attribute Analysis
 
 ```python
-from uniface import RetinaFace, AgeGender, FairFace
+from uniface.attribute import AgeGender, FairFace
+from uniface.detection import RetinaFace
 
 detector = RetinaFace()
 age_gender = AgeGender()
@@ -206,12 +209,13 @@ for face in faces:
 ### Using FaceAnalyzer
 
 ```python
-from uniface import FaceAnalyzer
+from uniface.analyzer import FaceAnalyzer
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
 
 analyzer = FaceAnalyzer(
-    detect=True,
-    recognize=False,
-    attributes=True  # Uses AgeGender
+    RetinaFace(),
+    age_gender=AgeGender(),
 )
 
 faces = analyzer.analyze(image)

docs/modules/detection.md

@@ -24,7 +24,7 @@ Single-shot face detector with multi-scale feature pyramid.
 ### Basic Usage
 
 ```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 detector = RetinaFace()
 faces = detector.detect(image)
@@ -38,7 +38,7 @@ for face in faces:
 ### Model Variants
 
 ```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.constants import RetinaFaceWeights
 
 # Lightweight (mobile/edge)
@@ -68,7 +68,8 @@ detector = RetinaFace(
     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
+    dynamic_size=False,        # Enable dynamic input size
+    providers=None,            # Auto-detect, or ['CPUExecutionProvider']
 )
 ```
 
@@ -81,7 +82,7 @@ State-of-the-art detection with excellent accuracy-speed tradeoff.
 ### Basic Usage
 
 ```python
-from uniface import SCRFD
+from uniface.detection import SCRFD
 
 detector = SCRFD()
 faces = detector.detect(image)
@@ -90,7 +91,7 @@ faces = detector.detect(image)
 ### Model Variants
 
 ```python
-from uniface import SCRFD
+from uniface.detection import SCRFD
 from uniface.constants import SCRFDWeights
 
 # Real-time (lightweight)
@@ -112,7 +113,8 @@ detector = SCRFD(
     model_name=SCRFDWeights.SCRFD_10G_KPS,
     confidence_threshold=0.5,
     nms_threshold=0.4,
-    input_size=(640, 640)
+    input_size=(640, 640),
+    providers=None,  # Auto-detect, or ['CPUExecutionProvider']
 )
 ```
 
@@ -125,7 +127,7 @@ YOLO-based detection optimized for faces.
 ### Basic Usage
 
 ```python
-from uniface import YOLOv5Face
+from uniface.detection import YOLOv5Face
 
 detector = YOLOv5Face()
 faces = detector.detect(image)
@@ -134,7 +136,7 @@ faces = detector.detect(image)
 ### Model Variants
 
 ```python
-from uniface import YOLOv5Face
+from uniface.detection import YOLOv5Face
 from uniface.constants import YOLOv5FaceWeights
 
 # Lightweight
@@ -163,7 +165,8 @@ detector = YOLOv5Face(
     model_name=YOLOv5FaceWeights.YOLOV5S,
     confidence_threshold=0.6,
     nms_threshold=0.5,
-    nms_mode='numpy'  # or 'torchvision' for faster NMS
+    nms_mode='numpy',  # or 'torchvision' for faster NMS
+    providers=None,    # Auto-detect, or ['CPUExecutionProvider']
 )
 ```
 
@@ -176,7 +179,7 @@ Anchor-free detection with DFL (Distribution Focal Loss) for accurate bbox regre
 ### Basic Usage
 
 ```python
-from uniface import YOLOv8Face
+from uniface.detection import YOLOv8Face
 
 detector = YOLOv8Face()
 faces = detector.detect(image)
@@ -185,7 +188,7 @@ faces = detector.detect(image)
 ### Model Variants
 
 ```python
-from uniface import YOLOv8Face
+from uniface.detection import YOLOv8Face
 from uniface.constants import YOLOv8FaceWeights
 
 # Lightweight
@@ -210,7 +213,8 @@ detector = YOLOv8Face(
     model_name=YOLOv8FaceWeights.YOLOV8N,
     confidence_threshold=0.5,
     nms_threshold=0.45,
-    nms_mode='numpy'  # or 'torchvision' for faster NMS
+    nms_mode='numpy',  # or 'torchvision' for faster NMS
+    providers=None,    # Auto-detect, or ['CPUExecutionProvider']
 )
 ```
 
@@ -221,7 +225,7 @@ detector = YOLOv8Face(
 Create detectors dynamically:
 
 ```python
-from uniface import create_detector
+from uniface.detection import create_detector
 
 detector = create_detector('retinaface')
 # or
@@ -234,22 +238,6 @@ detector = create_detector('yolov8face')
 
 ---
 
-## High-Level API
-
-One-line detection:
-
-```python
-from uniface import detect_faces
-
-# Using RetinaFace (default)
-faces = detect_faces(image, method='retinaface', confidence_threshold=0.5)
-
-# Using YOLOv8-Face
-faces = detect_faces(image, method='yolov8face', confidence_threshold=0.5)
-```
-
----
-
 ## Output Format
 
 All detectors return `list[Face]`:
@@ -272,7 +260,7 @@ for face in faces:
 ## Visualization
 
 ```python
-from uniface.visualization import draw_detections
+from uniface.draw import draw_detections
 
 draw_detections(
     image=image,
@@ -292,7 +280,7 @@ cv2.imwrite("result.jpg", image)
 Benchmark on your hardware:
 
 ```bash
-python tools/detection.py --source image.jpg --iterations 100
+python tools/detect.py --source image.jpg
 ```
 
 ---

docs/modules/gaze.md

@@ -23,7 +23,8 @@ Gaze estimation predicts where a person is looking (pitch and yaw angles).
 ```python
 import cv2
 import numpy as np
-from uniface import RetinaFace, MobileGaze
+from uniface.detection import RetinaFace
+from uniface.gaze import MobileGaze
 
 detector = RetinaFace()
 gaze_estimator = MobileGaze()
@@ -52,7 +53,7 @@ for face in faces:
 ## Model Variants
 
 ```python
-from uniface import MobileGaze
+from uniface.gaze import MobileGaze
 from uniface.constants import GazeWeights
 
 # Default (ResNet34, recommended)
@@ -102,7 +103,7 @@ yaw = -90° ────┼──── yaw = +90°
 ## Visualization
 
 ```python
-from uniface.visualization import draw_gaze
+from uniface.draw import draw_gaze
 
 # Detect faces
 faces = detector.detect(image)
@@ -154,8 +155,9 @@ def draw_gaze_custom(image, bbox, pitch, yaw, length=100, color=(0, 255, 0)):
 ```python
 import cv2
 import numpy as np
-from uniface import RetinaFace, MobileGaze
-from uniface.visualization import draw_gaze
+from uniface.detection import RetinaFace
+from uniface.gaze import MobileGaze
+from uniface.draw import draw_gaze
 
 detector = RetinaFace()
 gaze_estimator = MobileGaze()
@@ -256,7 +258,7 @@ print(f"Looking: {direction}")
 ## Factory Function
 
 ```python
-from uniface import create_gaze_estimator
+from uniface.gaze import create_gaze_estimator
 
 gaze = create_gaze_estimator()  # Returns MobileGaze
 ```

docs/modules/landmarks.md

@@ -20,7 +20,8 @@ Facial landmark detection provides precise localization of facial features.
 ### Basic Usage
 
 ```python
-from uniface import RetinaFace, Landmark106
+from uniface.detection import RetinaFace
+from uniface.landmark import Landmark106
 
 detector = RetinaFace()
 landmarker = Landmark106()
@@ -78,7 +79,7 @@ mouth = landmarks[87:106]
 All detection models provide 5-point landmarks:
 
 ```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 detector = RetinaFace()
 faces = detector.detect(image)
@@ -152,7 +153,7 @@ def draw_landmarks_with_connections(image, landmarks):
 ### Face Alignment
 
 ```python
-from uniface import face_alignment
+from uniface.face_utils import face_alignment
 
 # Align face using 5-point landmarks
 aligned = face_alignment(image, faces[0].landmarks)
@@ -236,7 +237,7 @@ def estimate_head_pose(landmarks, image_shape):
 ## Factory Function
 
 ```python
-from uniface import create_landmarker
+from uniface.landmark import create_landmarker
 
 landmarker = create_landmarker()  # Returns Landmark106
 ```

docs/modules/parsing.md

@@ -1,15 +1,16 @@
 # Parsing
 
-Face parsing segments faces into semantic components (skin, eyes, nose, mouth, hair, etc.).
+Face parsing segments faces into semantic components or face regions.
 
 ---
 
 ## Available Models
 
-| Model | Backbone | Size | Classes |
-|-------|----------|------|---------|
-| **BiSeNet ResNet18** :material-check-circle: | ResNet18 | 51 MB | 19 |
-| BiSeNet ResNet34 | ResNet34 | 89 MB | 19 |
+| 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 |
 
 ---
 
@@ -18,7 +19,7 @@ Face parsing segments faces into semantic components (skin, eyes, nose, mouth, h
 ```python
 import cv2
 from uniface.parsing import BiSeNet
-from uniface.visualization import vis_parsing_maps
+from uniface.draw import vis_parsing_maps
 
 # Initialize parser
 parser = BiSeNet()
@@ -45,16 +46,16 @@ cv2.imwrite("parsed.jpg", vis_bgr)
 
 | ID | Class | ID | Class |
 |----|-------|----|-------|
-| 0 | Background | 10 | Ear Ring |
-| 1 | Skin | 11 | Nose |
-| 2 | Left Eyebrow | 12 | Mouth |
-| 3 | Right Eyebrow | 13 | Upper Lip |
-| 4 | Left Eye | 14 | Lower Lip |
-| 5 | Right Eye | 15 | Neck |
-| 6 | Eye Glasses | 16 | Neck Lace |
-| 7 | Left Ear | 17 | Cloth |
-| 8 | Right Ear | 18 | Hair |
-| 9 | Hat | | |
+| 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 | | |
 
 ---
 
@@ -84,9 +85,9 @@ parser = BiSeNet(model_name=ParsingWeights.RESNET34)
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.parsing import BiSeNet
-from uniface.visualization import vis_parsing_maps
+from uniface.draw import vis_parsing_maps
 
 detector = RetinaFace()
 parser = BiSeNet()
@@ -125,7 +126,7 @@ mask = parser.parse(face_image)
 
 # Extract specific component
 SKIN = 1
-HAIR = 18
+HAIR = 17
 LEFT_EYE = 4
 RIGHT_EYE = 5
 
@@ -148,10 +149,10 @@ mask = parser.parse(face_image)
 
 component_names = {
     0: 'Background', 1: 'Skin', 2: 'L-Eyebrow', 3: 'R-Eyebrow',
-    4: 'L-Eye', 5: 'R-Eye', 6: 'Glasses', 7: 'L-Ear', 8: 'R-Ear',
-    9: 'Hat', 10: 'Earring', 11: 'Nose', 12: 'Mouth',
-    13: 'U-Lip', 14: 'L-Lip', 15: 'Neck', 16: 'Necklace',
-    17: 'Cloth', 18: 'Hair'
+    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):
@@ -176,23 +177,19 @@ def apply_lip_color(image, mask, color=(180, 50, 50)):
     """Apply lip color using parsing mask."""
     result = image.copy()
 
-    # Get lip mask (upper + lower lip)
-    lip_mask = ((mask == 13) | (mask == 14)).astype(np.uint8)
+    # 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
 
-    # Blend with original
-    lip_region = cv2.bitwise_and(overlay, overlay, mask=lip_mask)
-    non_lip = cv2.bitwise_and(result, result, mask=1 - lip_mask)
-
-    # Combine with alpha blending
+    # Alpha blend lip region
     alpha = 0.4
-    result = cv2.addWeighted(result, 1 - alpha * lip_mask[:,:,np.newaxis] / 255,
-                             lip_region, alpha, 0)
+    mask_3ch = lip_mask[:, :, np.newaxis]
+    result = np.where(mask_3ch, (image * (1 - alpha) + overlay * alpha).astype(np.uint8), result)
 
-    return result.astype(np.uint8)
+    return result
 ```
 
 ### Background Replacement
@@ -218,7 +215,7 @@ def replace_background(image, mask, background):
 ```python
 def get_hair_mask(mask):
     """Extract clean hair mask."""
-    hair_mask = (mask == 18).astype(np.uint8) * 255
+    hair_mask = (mask == 17).astype(np.uint8) * 255
 
     # Clean up with morphological operations
     kernel = np.ones((5, 5), np.uint8)
@@ -233,7 +230,7 @@ def get_hair_mask(mask):
 ## Visualization Options
 
 ```python
-from uniface.visualization import vis_parsing_maps
+from uniface.draw import vis_parsing_maps
 
 # Default visualization
 vis_result = vis_parsing_maps(face_rgb, mask)
@@ -248,12 +245,83 @@ vis_result = vis_parsing_maps(
 
 ---
 
+## 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 import create_face_parser
+from uniface.parsing import create_face_parser
+from uniface.constants import ParsingWeights, XSegWeights
 
-parser = create_face_parser()  # Returns BiSeNet
+# BiSeNet (default)
+parser = create_face_parser()
+
+# XSeg
+parser = create_face_parser(XSegWeights.DEFAULT)
 ```
 
 ---

docs/modules/privacy.md

@@ -18,25 +18,8 @@ Face anonymization protects privacy by blurring or obscuring faces in images and
 
 ## Quick Start
 
-### One-Line Anonymization
-
 ```python
-from uniface.privacy import anonymize_faces
-import cv2
-
-image = cv2.imread("group_photo.jpg")
-anonymized = anonymize_faces(image, method='pixelate')
-cv2.imwrite("anonymized.jpg", anonymized)
-```
-
----
-
-## BlurFace Class
-
-For more control, use the `BlurFace` class:
-
-```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.privacy import BlurFace
 import cv2
 
@@ -59,12 +42,12 @@ cv2.imwrite("anonymized.jpg", anonymized)
 Blocky pixelation effect (common in news media):
 
 ```python
-blurrer = BlurFace(method='pixelate', pixel_blocks=10)
+blurrer = BlurFace(method='pixelate', pixel_blocks=15)
 ```
 
 | Parameter | Default | Description |
 |-----------|---------|-------------|
-| `pixel_blocks` | 10 | Number of blocks (lower = more pixelated) |
+| `pixel_blocks` | 15 | Number of blocks (lower = more pixelated) |
 
 ### Gaussian
 
@@ -137,7 +120,7 @@ result = blurrer.anonymize(image, faces, inplace=True)
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.privacy import BlurFace
 
 detector = RetinaFace()
@@ -166,7 +149,7 @@ cv2.destroyAllWindows()
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.privacy import BlurFace
 
 detector = RetinaFace()
@@ -238,7 +221,7 @@ def anonymize_low_confidence(image, faces, blurrer, confidence_threshold=0.8):
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.privacy import BlurFace
 
 detector = RetinaFace()
@@ -259,13 +242,13 @@ for method in methods:
 
 ```bash
 # Anonymize image with pixelation
-python tools/face_anonymize.py --source photo.jpg
+python tools/anonymize.py --source photo.jpg
 
 # Real-time webcam
-python tools/face_anonymize.py --source 0 --method gaussian
+python tools/anonymize.py --source 0 --method gaussian
 
 # Custom blur strength
-python tools/face_anonymize.py --source photo.jpg --method gaussian --blur-strength 5.0
+python tools/anonymize.py --source photo.jpg --method gaussian --blur-strength 5.0
 ```
 
 ---

docs/modules/recognition.md

@@ -22,7 +22,8 @@ Face recognition using adaptive margin based on image quality.
 ### Basic Usage
 
 ```python
-from uniface import RetinaFace, AdaFace
+from uniface.detection import RetinaFace
+from uniface.recognition import AdaFace
 
 detector = RetinaFace()
 recognizer = AdaFace()
@@ -39,7 +40,7 @@ if faces:
 ### Model Variants
 
 ```python
-from uniface import AdaFace
+from uniface.recognition import AdaFace
 from uniface.constants import AdaFaceWeights
 
 # Lightweight (default)
@@ -47,6 +48,9 @@ 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 |
@@ -66,7 +70,8 @@ Face recognition using additive angular margin loss.
 ### Basic Usage
 
 ```python
-from uniface import RetinaFace, ArcFace
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
 
 detector = RetinaFace()
 recognizer = ArcFace()
@@ -83,7 +88,7 @@ if faces:
 ### Model Variants
 
 ```python
-from uniface import ArcFace
+from uniface.recognition import ArcFace
 from uniface.constants import ArcFaceWeights
 
 # Lightweight (default)
@@ -91,6 +96,9 @@ 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 |
@@ -112,7 +120,7 @@ Lightweight face recognition models with MobileNet backbones.
 ### Basic Usage
 
 ```python
-from uniface import MobileFace
+from uniface.recognition import MobileFace
 
 recognizer = MobileFace()
 embedding = recognizer.get_normalized_embedding(image, landmarks)
@@ -121,7 +129,7 @@ embedding = recognizer.get_normalized_embedding(image, landmarks)
 ### Model Variants
 
 ```python
-from uniface import MobileFace
+from uniface.recognition import MobileFace
 from uniface.constants import MobileFaceWeights
 
 # Ultra-lightweight
@@ -150,7 +158,7 @@ Face recognition using angular softmax loss (A-Softmax).
 ### Basic Usage
 
 ```python
-from uniface import SphereFace
+from uniface.recognition import SphereFace
 from uniface.constants import SphereFaceWeights
 
 recognizer = SphereFace(model_name=SphereFaceWeights.SPHERE20)
@@ -169,7 +177,7 @@ embedding = recognizer.get_normalized_embedding(image, landmarks)
 ### Compute Similarity
 
 ```python
-from uniface import compute_similarity
+from uniface.face_utils import compute_similarity
 import numpy as np
 
 # Extract embeddings
@@ -205,7 +213,7 @@ Recognition models require aligned faces. UniFace handles this internally:
 embedding = recognizer.get_normalized_embedding(image, landmarks)
 
 # Or manually align
-from uniface import face_alignment
+from uniface.face_utils import face_alignment
 
 aligned_face = face_alignment(image, landmarks)
 # Returns: 112x112 aligned face image
@@ -217,7 +225,8 @@ aligned_face = face_alignment(image, landmarks)
 
 ```python
 import numpy as np
-from uniface import RetinaFace, ArcFace
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
 
 detector = RetinaFace()
 recognizer = ArcFace()
@@ -276,7 +285,7 @@ else:
 ## Factory Function
 
 ```python
-from uniface import create_recognizer
+from uniface.recognition import create_recognizer
 
 # Available methods: 'arcface', 'adaface', 'mobileface', 'sphereface'
 recognizer = create_recognizer('arcface')

docs/modules/spoofing.md

@@ -17,7 +17,7 @@ Face anti-spoofing detects whether a face is real (live) or fake (photo, video r
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.spoofing import MiniFASNet
 
 detector = RetinaFace()
@@ -69,20 +69,21 @@ spoofer = MiniFASNet(model_name=MiniFASNetWeights.V1SE)
 
 ## Confidence Thresholds
 
-The default threshold is 0.5. Adjust for your use case:
+`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.confidence > HIGH_THRESHOLD:
+if result.is_real and result.confidence > HIGH_THRESHOLD:
     print("Real (high confidence)")
 else:
     print("Suspicious")
 
-# Balanced
-if result.is_real:  # Uses default 0.5 threshold
+# Balanced (argmax decision)
+if result.is_real:
     print("Real")
 else:
     print("Fake")
@@ -127,7 +128,7 @@ cv2.imwrite("spoofing_result.jpg", image)
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.spoofing import MiniFASNet
 
 detector = RetinaFace()
@@ -252,7 +253,7 @@ python tools/spoofing.py --source 0
 ## Factory Function
 
 ```python
-from uniface import create_spoofer
+from uniface.spoofing import create_spoofer
 
 spoofer = create_spoofer()  # Returns MiniFASNet
 ```

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

@@ -16,6 +16,7 @@ Run UniFace examples directly in your browser with Google Colab, or download and
 | [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 |
 
 ---
 

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

@@ -10,7 +10,7 @@ Detect faces in an image:
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 # Load image
 image = cv2.imread("photo.jpg")
@@ -46,8 +46,8 @@ Draw bounding boxes and landmarks:
 
 ```python
 import cv2
-from uniface import RetinaFace
-from uniface.visualization import draw_detections
+from uniface.detection import RetinaFace
+from uniface.draw import draw_detections
 
 # Detect faces
 detector = RetinaFace()
@@ -81,7 +81,8 @@ Compare two faces:
 ```python
 import cv2
 import numpy as np
-from uniface import RetinaFace, ArcFace
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
 
 # Initialize models
 detector = RetinaFace()
@@ -121,7 +122,8 @@ if faces1 and faces2:
 
 ```python
 import cv2
-from uniface import RetinaFace, AgeGender
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
 
 # Initialize models
 detector = RetinaFace()
@@ -152,7 +154,8 @@ Detect race, gender, and age group:
 
 ```python
 import cv2
-from uniface import RetinaFace, FairFace
+from uniface.attribute import FairFace
+from uniface.detection import RetinaFace
 
 detector = RetinaFace()
 fairface = FairFace()
@@ -178,7 +181,8 @@ Face 2: Female, 20-29, White
 
 ```python
 import cv2
-from uniface import RetinaFace, Landmark106
+from uniface.detection import RetinaFace
+from uniface.landmark import Landmark106
 
 detector = RetinaFace()
 landmarker = Landmark106()
@@ -204,8 +208,9 @@ if faces:
 ```python
 import cv2
 import numpy as np
-from uniface import RetinaFace, MobileGaze
-from uniface.visualization import draw_gaze
+from uniface.detection import RetinaFace
+from uniface.gaze import MobileGaze
+from uniface.draw import draw_gaze
 
 detector = RetinaFace()
 gaze_estimator = MobileGaze()
@@ -237,7 +242,7 @@ Segment face into semantic components:
 import cv2
 import numpy as np
 from uniface.parsing import BiSeNet
-from uniface.visualization import vis_parsing_maps
+from uniface.draw import vis_parsing_maps
 
 parser = BiSeNet()
 
@@ -261,26 +266,24 @@ print(f"Detected {len(np.unique(mask))} facial components")
 Blur faces for privacy protection:
 
 ```python
-from uniface.privacy import anonymize_faces
 import cv2
-
-# One-liner: automatic detection and blurring
-image = cv2.imread("group_photo.jpg")
-anonymized = anonymize_faces(image, method='pixelate')
-cv2.imwrite("anonymized.jpg", anonymized)
-```
-
-**Manual control:**
-
-```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.privacy import BlurFace
 
 detector = RetinaFace()
-blurrer = BlurFace(method='gaussian', blur_strength=5.0)
+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:**
@@ -301,7 +304,7 @@ Detect real vs. fake faces:
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.spoofing import MiniFASNet
 
 detector = RetinaFace()
@@ -324,8 +327,8 @@ Real-time face detection:
 
 ```python
 import cv2
-from uniface import RetinaFace
-from uniface.visualization import draw_detections
+from uniface.detection import RetinaFace
+from uniface.draw import draw_detections
 
 detector = RetinaFace()
 cap = cv2.VideoCapture(0)
@@ -355,6 +358,60 @@ 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).
@@ -365,6 +422,7 @@ For detailed model comparisons and benchmarks, see the [Model Zoo](models.md).
 |------|------------------|
 | 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` |
@@ -407,13 +465,17 @@ python -c "import platform; print(platform.machine())"
 ### Import Errors
 
 ```python
-# Correct imports
-from uniface.detection import RetinaFace
-from uniface.recognition import ArcFace
+from uniface.detection import RetinaFace, SCRFD
+from uniface.recognition import ArcFace, AdaFace
+from uniface.attribute import AgeGender, FairFace
 from uniface.landmark import Landmark106
-
-# Also works (re-exported at package level)
-from uniface import RetinaFace, ArcFace, 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.draw import draw_detections, draw_tracks
 ```
 
 ---

docs/recipes/anonymize-stream.md

@@ -11,7 +11,7 @@ Blur faces in real-time video streams for privacy protection.
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.privacy import BlurFace
 
 detector = RetinaFace()
@@ -40,7 +40,7 @@ cv2.destroyAllWindows()
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.privacy import BlurFace
 
 detector = RetinaFace()
@@ -67,14 +67,19 @@ out.release()
 
 ---
 
-## One-Liner for Images
+## Single Image
 
 ```python
-from uniface.privacy import anonymize_faces
 import cv2
+from uniface.detection import RetinaFace
+from uniface.privacy import BlurFace
+
+detector = RetinaFace()
+blurrer = BlurFace(method='pixelate')
 
 image = cv2.imread("photo.jpg")
-result = anonymize_faces(image, method='pixelate')
+faces = detector.detect(image)
+result = blurrer.anonymize(image, faces)
 cv2.imwrite("anonymized.jpg", result)
 ```
 
@@ -84,7 +89,7 @@ cv2.imwrite("anonymized.jpg", result)
 
 | Method | Usage |
 |--------|-------|
-| Pixelate | `BlurFace(method='pixelate', pixel_blocks=10)` |
+| 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)` |

docs/recipes/batch-processing.md

@@ -12,7 +12,7 @@ Process multiple images efficiently.
 ```python
 import cv2
 from pathlib import Path
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 detector = RetinaFace()
 
@@ -54,7 +54,8 @@ for image_path in tqdm(image_files, desc="Processing"):
 ## Extract Embeddings
 
 ```python
-from uniface import RetinaFace, ArcFace
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
 import numpy as np
 
 detector = RetinaFace()

docs/recipes/custom-models.md

@@ -27,29 +27,29 @@ 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)
+        input_tensor = self.preprocess(image)
 
         # 2. Run inference
         outputs = self.session.run(None, {'input': input_tensor})
 
         # 3. Postprocess outputs to Face objects
-        faces = self._postprocess(outputs, image.shape)
-        return faces
-
-    def _preprocess(self, image):
-        # Your preprocessing logic
-        # e.g., resize, normalize, transpose
-        pass
-
-    def _postprocess(self, outputs, shape):
-        # Your postprocessing logic
-        # e.g., decode boxes, apply NMS, create Face objects
-        pass
+        return self.postprocess(outputs, image.shape)
 ```
 
 ---
@@ -57,36 +57,14 @@ class MyDetector(BaseDetector):
 ## Add Custom Recognition Model
 
 ```python
-from uniface.recognition.base import BaseRecognizer
-from uniface.onnx_utils import create_onnx_session
-from uniface import face_alignment
-import numpy as np
+from uniface.recognition.base import BaseRecognizer, PreprocessConfig
 
 class MyRecognizer(BaseRecognizer):
-    def __init__(self, model_path: str):
-        self.session = create_onnx_session(model_path)
+    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)
 
-    def get_normalized_embedding(
-        self,
-        image: np.ndarray,
-        landmarks: np.ndarray
-    ) -> np.ndarray:
-        # 1. Align face
-        aligned = face_alignment(image, landmarks)
-
-        # 2. Preprocess
-        input_tensor = self._preprocess(aligned)
-
-        # 3. Run inference
-        embedding = self.session.run(None, {'input': input_tensor})[0]
-
-        # 4. Normalize
-        embedding = embedding / np.linalg.norm(embedding)
-        return embedding
-
-    def _preprocess(self, image):
-        # Your preprocessing logic
-        pass
+    # Optional: override preprocess() if your model expects custom normalization.
 ```
 
 ---

docs/recipes/face-search.md

@@ -13,7 +13,8 @@ Build a face search system for finding people in images.
 import numpy as np
 import cv2
 from pathlib import Path
-from uniface import RetinaFace, ArcFace
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
 
 class FaceDatabase:
     def __init__(self):

docs/recipes/image-pipeline.md

@@ -8,8 +8,10 @@ A complete pipeline for processing images with detection, recognition, and attri
 
 ```python
 import cv2
-from uniface import RetinaFace, ArcFace, AgeGender
-from uniface.visualization import draw_detections
+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()
@@ -67,14 +69,21 @@ cv2.imwrite("result.jpg", result_image)
 For convenience, use the built-in `FaceAnalyzer`:
 
 ```python
-from uniface import FaceAnalyzer
+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(
-    detect=True,
-    recognize=True,
-    attributes=True
+    detector,
+    recognizer=recognizer,
+    age_gender=age_gender,
 )
 
 # Process image
@@ -97,13 +106,14 @@ Complete pipeline with all modules:
 ```python
 import cv2
 import numpy as np
-from uniface import (
-    RetinaFace, ArcFace, AgeGender, FairFace,
-    Landmark106, MobileGaze
-)
+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.visualization import draw_detections, draw_gaze
+from uniface.draw import draw_detections, draw_gaze
 
 class FaceAnalysisPipeline:
     def __init__(self):
@@ -189,8 +199,10 @@ for i, r in enumerate(results):
 ```python
 import cv2
 import numpy as np
-from uniface import RetinaFace, AgeGender, MobileGaze
-from uniface.visualization import draw_detections, draw_gaze
+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."""

docs/recipes/video-webcam.md

@@ -11,8 +11,8 @@ Real-time face analysis for video streams.
 
 ```python
 import cv2
-from uniface import RetinaFace
-from uniface.visualization import draw_detections
+from uniface.detection import RetinaFace
+from uniface.draw import draw_detections
 
 detector = RetinaFace()
 cap = cv2.VideoCapture(0)
@@ -48,7 +48,7 @@ cv2.destroyAllWindows()
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 def process_video(input_path, output_path):
     """Process a video file."""
@@ -83,6 +83,57 @@ 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
@@ -119,7 +170,8 @@ while True:
 
 ## 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 tracking
+- [Gaze Module](../modules/gaze.md) - Gaze estimation

examples/03_face_verification.ipynb

@@ -53,7 +53,7 @@
     "import matplotlib.pyplot as plt\n",
     "\n",
     "import uniface\n",
-    "from uniface import FaceAnalyzer\n",
+    "from uniface.analyzer import FaceAnalyzer\n",
     "from uniface.detection import RetinaFace\n",
     "from uniface.recognition import ArcFace\n",
     "\n",

examples/04_face_search.ipynb

@@ -58,7 +58,7 @@
     "import matplotlib.pyplot as plt\n",
     "\n",
     "import uniface\n",
-    "from uniface import FaceAnalyzer\n",
+    "from uniface.analyzer import FaceAnalyzer\n",
     "from uniface.detection import RetinaFace\n",
     "from uniface.recognition import ArcFace\n",
     "\n",

examples/05_face_analyzer.ipynb

@@ -60,7 +60,7 @@
     "import matplotlib.pyplot as plt\n",
     "\n",
     "import uniface\n",
-    "from uniface import FaceAnalyzer\n",
+    "from uniface.analyzer import FaceAnalyzer\n",
     "from uniface.detection import RetinaFace\n",
     "from uniface.recognition import ArcFace\n",
     "from uniface.attribute import AgeGender\n",

mkdocs.yml

@@ -48,6 +48,7 @@ theme:
     - content.action.edit
     - content.action.view
     - content.tabs.link
+    - announce.dismiss
     - toc.follow
 
   icon:
@@ -144,6 +145,7 @@ nav:
   - 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

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "uniface"
-version = "2.2.0"
-description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Face Parsing, Gaze Estimation, Age, and Gender Detection"
+version = "3.0.0"
+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" }]
@@ -13,6 +13,7 @@ requires-python = ">=3.10,<3.14"
 keywords = [
     "face-detection",
     "face-recognition",
+    "face-tracking",
     "facial-landmarks",
     "face-parsing",
     "face-segmentation",
@@ -42,9 +43,9 @@ classifiers = [
 dependencies = [
     "numpy>=1.21.0",
     "opencv-python>=4.5.0",
-    "onnx>=1.12.0",
     "onnxruntime>=1.16.0",
     "scikit-image>=0.19.0",
+    "scipy>=1.7.0",
     "requests>=2.28.0",
     "tqdm>=4.64.0",
 ]
@@ -56,9 +57,9 @@ gpu = ["onnxruntime-gpu>=1.16.0"]
 [project.urls]
 Homepage = "https://github.com/yakhyo/uniface"
 Repository = "https://github.com/yakhyo/uniface"
-Documentation = "https://github.com/yakhyo/uniface/blob/main/README.md"
-"Quick Start" = "https://github.com/yakhyo/uniface/blob/main/QUICKSTART.md"
-"Model Zoo" = "https://github.com/yakhyo/uniface/blob/main/MODELS.md"
+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"]

requirements.txt

@@ -1,8 +1,7 @@
 numpy>=1.21.0
 opencv-python>=4.5.0
-onnx>=1.12.0
 onnxruntime>=1.16.0
 scikit-image>=0.19.0
+scipy>=1.7.0
 requests>=2.28.0
-pytest>=7.0.0
 tqdm>=4.64.0

tests/test_age_gender.py

@@ -2,7 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Tests for AgeGender attribute predictor."""
 
 from __future__ import annotations
 

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

@@ -2,7 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Tests for factory functions (create_detector, create_recognizer, etc.)."""
 
 from __future__ import annotations
 
@@ -13,10 +12,10 @@ from uniface import (
     create_detector,
     create_landmarker,
     create_recognizer,
-    detect_faces,
     list_available_detectors,
 )
 from uniface.constants import RetinaFaceWeights, SCRFDWeights
+from uniface.spoofing import MiniFASNet, create_spoofer
 
 
 # create_detector tests
@@ -123,62 +122,6 @@ def test_create_landmarker_invalid_method():
         create_landmarker('invalid_method')
 
 
-# detect_faces tests
-def test_detect_faces_retinaface():
-    """
-    Test high-level detect_faces function with RetinaFace.
-    """
-    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-    faces = detect_faces(mock_image, method='retinaface')
-
-    assert isinstance(faces, list), 'detect_faces should return a list'
-
-
-def test_detect_faces_scrfd():
-    """
-    Test high-level detect_faces function with SCRFD.
-    """
-    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-    faces = detect_faces(mock_image, method='scrfd')
-
-    assert isinstance(faces, list), 'detect_faces should return a list'
-
-
-def test_detect_faces_with_threshold():
-    """
-    Test detect_faces with custom confidence threshold.
-    """
-    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-    faces = detect_faces(mock_image, method='retinaface', confidence_threshold=0.8)
-
-    assert isinstance(faces, list), 'detect_faces should return a list'
-
-    # All detections should respect threshold
-    for face in faces:
-        assert face.confidence >= 0.8, 'All detections should meet confidence threshold'
-
-
-def test_detect_faces_default_method():
-    """
-    Test detect_faces with default method (should use retinaface).
-    """
-    mock_image = np.random.randint(0, 255, (640, 640, 3), dtype=np.uint8)
-    faces = detect_faces(mock_image)  # No method specified
-
-    assert isinstance(faces, list), 'detect_faces should return a list with default method'
-
-
-def test_detect_faces_empty_image():
-    """
-    Test detect_faces on a blank image.
-    """
-    empty_image = np.zeros((640, 640, 3), dtype=np.uint8)
-    faces = detect_faces(empty_image, method='retinaface')
-
-    assert isinstance(faces, list), 'Should return a list even for empty image'
-    assert len(faces) == 0, 'Should detect no faces in blank image'
-
-
 # list_available_detectors tests
 def test_list_available_detectors():
     """
@@ -280,3 +223,16 @@ def test_factory_returns_correct_types():
     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

@@ -2,7 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Tests for 106-point facial landmark detector."""
 
 from __future__ import annotations
 

tests/test_parsing.py

@@ -2,15 +2,14 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Tests for BiSeNet face parsing model."""
 
 from __future__ import annotations
 
 import numpy as np
 import pytest
 
-from uniface.constants import ParsingWeights
-from uniface.parsing import BiSeNet, create_face_parser
+from uniface.constants import ParsingWeights, XSegWeights
+from uniface.parsing import BiSeNet, XSeg, create_face_parser
 
 
 def test_bisenet_initialization():
@@ -120,3 +119,151 @@ def test_bisenet_different_input_sizes():
 
         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

@@ -2,7 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Tests for face recognition models (ArcFace, MobileFace, SphereFace)."""
 
 from __future__ import annotations
 

tests/test_retinaface.py

@@ -2,7 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Tests for RetinaFace detector."""
 
 from __future__ import annotations
 

tests/test_scrfd.py

@@ -2,7 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Tests for SCRFD detector."""
 
 from __future__ import annotations
 

tests/test_types.py

@@ -2,7 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Tests for UniFace type definitions (dataclasses)."""
 
 from __future__ import annotations
 

tests/test_utils.py

@@ -2,7 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Tests for utility functions (compute_similarity, face_alignment, etc.)."""
 
 from __future__ import annotations
 

tools/README.md

@@ -6,26 +6,27 @@ CLI utilities for testing and running UniFace features.
 
 | Tool | Description |
 |------|-------------|
-| `detection.py` | Face detection on image, video, or webcam |
-| `face_anonymize.py` | Face anonymization/blurring for privacy |
-| `age_gender.py` | Age and gender prediction |
-| `face_emotion.py` | Emotion detection (7 or 8 emotions) |
-| `gaze_estimation.py` | Gaze direction estimation |
+| `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 |
-| `recognition.py` | Face embedding extraction and comparison |
-| `face_analyzer.py` | Complete face analysis (detection + recognition + attributes) |
-| `face_search.py` | Real-time face matching against reference |
+| `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 |
-| `face_parsing.py` | Face semantic segmentation |
-| `video_detection.py` | Face detection on video files with progress bar |
+| `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
 
-All tools use a unified `--source` argument that accepts:
+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)
@@ -34,26 +35,31 @@ All tools use a unified `--source` argument that accepts:
 
 ```bash
 # Face detection
-python tools/detection.py --source assets/test.jpg           # image
-python tools/detection.py --source video.mp4                 # video
-python tools/detection.py --source 0                         # webcam
+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/face_anonymize.py --source assets/test.jpg --method pixelate
-python tools/face_anonymize.py --source video.mp4 --method gaussian
-python tools/face_anonymize.py --source 0 --method pixelate
+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/age_gender.py --source assets/test.jpg
-python tools/age_gender.py --source 0
+python tools/attribute.py --source assets/test.jpg
+python tools/attribute.py --source 0
 
 # Emotion detection
-python tools/face_emotion.py --source assets/test.jpg
-python tools/face_emotion.py --source 0
+python tools/emotion.py --source assets/test.jpg
+python tools/emotion.py --source 0
 
 # Gaze estimation
-python tools/gaze_estimation.py --source assets/test.jpg
-python tools/gaze_estimation.py --source 0
+python tools/gaze.py --source assets/test.jpg
+python tools/gaze.py --source 0
 
 # Landmarks
 python tools/landmarks.py --source assets/test.jpg
@@ -63,31 +69,31 @@ python tools/landmarks.py --source 0
 python tools/fairface.py --source assets/test.jpg
 python tools/fairface.py --source 0
 
-# Face parsing
-python tools/face_parsing.py --source assets/test.jpg
-python tools/face_parsing.py --source 0
+# Face 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/face_analyzer.py --source assets/test.jpg
-python tools/face_analyzer.py --source 0
+python tools/analyze.py --source assets/test.jpg
+python tools/analyze.py --source 0
 
 # Face recognition (extract embedding)
-python tools/recognition.py --image assets/test.jpg
+python tools/recognize.py --image assets/test.jpg
 
 # Face comparison
-python tools/recognition.py --image1 face1.jpg --image2 face2.jpg
+python tools/recognize.py --image1 face1.jpg --image2 face2.jpg
 
 # Face search (match against reference)
-python tools/face_search.py --reference person.jpg --source 0
-python tools/face_search.py --reference person.jpg --source video.mp4
-
-# Video processing with progress bar
-python tools/video_detection.py --source video.mp4
-python tools/video_detection.py --source video.mp4 --output output.mp4
+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/
@@ -117,5 +123,5 @@ python tools/download_model.py  # downloads all
 ## Quick Test
 
 ```bash
-python tools/detection.py --source assets/test.jpg
+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

@@ -5,9 +5,9 @@
 """Face analysis using FaceAnalyzer.
 
 Usage:
-    python tools/face_analyzer.py --source path/to/image.jpg
-    python tools/face_analyzer.py --source path/to/video.mp4
-    python tools/face_analyzer.py --source 0  # webcam
+    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
@@ -16,28 +16,15 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 import numpy as np
 
-from uniface import AgeGender, ArcFace, FaceAnalyzer, RetinaFace
-from uniface.visualization import draw_detections
-
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
+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):
@@ -111,7 +98,7 @@ def process_image(analyzer, image_path: str, save_dir: str = 'outputs', show_sim
     bboxes = [f.bbox for f in faces]
     scores = [f.confidence for f in faces]
     landmarks = [f.landmarks for f in faces]
-    draw_detections(image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, fancy_bbox=True)
+    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)
@@ -153,7 +140,7 @@ def process_video(analyzer, video_path: str, save_dir: str = 'outputs'):
         bboxes = [f.bbox for f in faces]
         scores = [f.confidence for f in faces]
         landmarks = [f.landmarks for f in faces]
-        draw_detections(image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, fancy_bbox=True)
+        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)
@@ -189,7 +176,7 @@ def run_camera(analyzer, camera_id: int = 0):
         bboxes = [f.bbox for f in faces]
         scores = [f.confidence for f in faces]
         landmarks = [f.landmarks for f in faces]
-        draw_detections(image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, fancy_bbox=True)
+        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)

tools/anonymize.py

@@ -5,9 +5,9 @@
 """Face anonymization/blurring for privacy.
 
 Usage:
-    python tools/face_anonymize.py --source path/to/image.jpg --method pixelate
-    python tools/face_anonymize.py --source path/to/video.mp4 --method gaussian
-    python tools/face_anonymize.py --source 0 --method pixelate  # webcam
+    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
@@ -16,28 +16,12 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.privacy import BlurFace
 
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
-
 
 def process_image(
     detector,
@@ -56,7 +40,7 @@ def process_image(
     print(f'Detected {len(faces)} face(s)')
 
     if show_detections and faces:
-        from uniface.visualization import draw_detections
+        from uniface.draw import draw_detections
 
         preview = image.copy()
         bboxes = [face.bbox for face in faces]
@@ -171,19 +155,19 @@ def main():
         epilog="""
 Examples:
   # Anonymize image with pixelation (default)
-  python run_anonymization.py --source photo.jpg
+  python tools/anonymize.py --source photo.jpg
 
   # Use Gaussian blur with custom strength
-  python run_anonymization.py --source photo.jpg --method gaussian --blur-strength 5.0
+  python tools/anonymize.py --source photo.jpg --method gaussian --blur-strength 5.0
 
   # Real-time webcam anonymization
-  python run_anonymization.py --source 0 --method pixelate
+  python tools/anonymize.py --source 0 --method pixelate
 
   # Black boxes for maximum privacy
-  python run_anonymization.py --source photo.jpg --method blackout
+  python tools/anonymize.py --source photo.jpg --method blackout
 
   # Custom pixelation intensity
-  python run_anonymization.py --source photo.jpg --method pixelate --pixel-blocks 5
+  python tools/anonymize.py --source photo.jpg --method pixelate --pixel-blocks 5
         """,
     )
 

tools/attribute.py

@@ -5,9 +5,9 @@
 """Age and gender prediction on detected faces.
 
 Usage:
-    python tools/age_gender.py --source path/to/image.jpg
-    python tools/age_gender.py --source path/to/video.mp4
-    python tools/age_gender.py --source 0  # webcam
+    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
@@ -16,27 +16,12 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 
-from uniface import SCRFD, AgeGender, RetinaFace
-from uniface.visualization import draw_detections
-
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
+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):
@@ -71,7 +56,7 @@ def process_image(
     scores = [f.confidence for f in faces]
     landmarks = [f.landmarks for f in faces]
     draw_detections(
-        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, corner_bbox=True
     )
 
     for i, face in enumerate(faces):
@@ -123,7 +108,7 @@ def process_video(
         scores = [f.confidence for f in faces]
         landmarks = [f.landmarks for f in faces]
         draw_detections(
-            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, corner_bbox=True
         )
 
         for face in faces:
@@ -162,7 +147,7 @@ def run_camera(detector, age_gender, camera_id: int = 0, threshold: float = 0.6)
         scores = [f.confidence for f in faces]
         landmarks = [f.landmarks for f in faces]
         draw_detections(
-            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, corner_bbox=True
         )
 
         for face in faces:

tools/batch_process.py

@@ -14,8 +14,8 @@ from pathlib import Path
 import cv2
 from tqdm import tqdm
 
-from uniface import SCRFD, RetinaFace
-from uniface.visualization import draw_detections
+from uniface.detection import SCRFD, RetinaFace
+from uniface.draw import draw_detections
 
 
 def get_image_files(input_dir: Path, extensions: tuple) -> list:
@@ -39,7 +39,7 @@ def process_image(detector, image_path: Path, output_path: Path, threshold: floa
     scores = [f.confidence for f in faces]
     landmarks = [f.landmarks for f in faces]
     draw_detections(
-        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, corner_bbox=True
     )
 
     cv2.putText(

tools/detect.py

@@ -5,9 +5,9 @@
 """Face detection on image, video, or webcam.
 
 Usage:
-    python tools/detection.py --source path/to/image.jpg
-    python tools/detection.py --source path/to/video.mp4
-    python tools/detection.py --source 0  # webcam
+    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
@@ -16,27 +16,12 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
+from tqdm import tqdm
 
 from uniface.detection import SCRFD, RetinaFace, YOLOv5Face, YOLOv8Face
-from uniface.visualization import draw_detections
-
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
+from uniface.draw import draw_detections
 
 
 def process_image(detector, image_path: str, threshold: float = 0.6, save_dir: str = 'outputs'):
@@ -52,7 +37,7 @@ def process_image(detector, image_path: str, threshold: float = 0.6, save_dir: s
         bboxes = [face.bbox for face in faces]
         scores = [face.confidence for face in faces]
         landmarks = [face.landmarks for face in faces]
-        draw_detections(image, bboxes, scores, landmarks, vis_threshold=threshold)
+        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')
@@ -60,34 +45,47 @@ def process_image(detector, image_path: str, threshold: float = 0.6, save_dir: s
     print(f'Detected {len(faces)} face(s). Output saved: {output_path}')
 
 
-def process_video(detector, video_path: str, threshold: float = 0.6, save_dir: str = 'outputs'):
-    """Process a video file."""
-    cap = cv2.VideoCapture(video_path)
+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 '{video_path}'")
+        print(f"Error: Cannot open video file '{input_path}'")
         return
 
-    # Get video properties
+    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))
-    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
 
-    os.makedirs(save_dir, exist_ok=True)
-    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_out.mp4')
+    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))
 
-    print(f'Processing video: {video_path} ({total_frames} frames)')
-    frame_count = 0
+    if not out.isOpened():
+        print(f"Error: Cannot create output video '{output_path}'")
+        cap.release()
+        return
 
-    while True:
+    frame_count = 0
+    total_faces = 0
+
+    for _ in tqdm(range(total_frames), desc='Processing', unit='frames'):
         ret, frame = cap.read()
         if not ret:
             break
 
         frame_count += 1
         faces = detector.detect(frame)
+        total_faces += len(faces)
 
         bboxes = [f.bbox for f in faces]
         scores = [f.confidence for f in faces]
@@ -99,19 +97,26 @@ def process_video(detector, video_path: str, threshold: float = 0.6, save_dir: s
             landmarks=landmarks,
             vis_threshold=threshold,
             draw_score=True,
-            fancy_bbox=True,
+            corner_bbox=True,
         )
 
         cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
         out.write(frame)
 
-        # Show progress
-        if frame_count % 100 == 0:
-            print(f'  Processed {frame_count}/{total_frames} frames...')
+        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()
-    print(f'Done! Output saved: {output_path}')
+    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):
@@ -125,7 +130,7 @@ def run_camera(detector, camera_id: int = 0, threshold: float = 0.6):
 
     while True:
         ret, frame = cap.read()
-        frame = cv2.flip(frame, 1)  # mirror for natural interaction
+        frame = cv2.flip(frame, 1)
         if not ret:
             break
 
@@ -141,7 +146,7 @@ def run_camera(detector, camera_id: int = 0, threshold: float = 0.6):
             landmarks=landmarks,
             vis_threshold=threshold,
             draw_score=True,
-            fancy_bbox=True,
+            corner_bbox=True,
         )
 
         cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
@@ -158,18 +163,24 @@ def main():
     parser = argparse.ArgumentParser(description='Run face detection')
     parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
     parser.add_argument(
-        '--method', type=str, default='retinaface', choices=['retinaface', 'scrfd', 'yolov5face', 'yolov8face']
+        '--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.method == 'retinaface':
+    if args.detector == 'retinaface':
         detector = RetinaFace()
-    elif args.method == 'scrfd':
+    elif args.detector == 'scrfd':
         detector = SCRFD()
-    elif args.method == 'yolov5face':
+    elif args.detector == 'yolov5face':
         from uniface.constants import YOLOv5FaceWeights
 
         detector = YOLOv5Face(model_name=YOLOv5FaceWeights.YOLOV5M)
@@ -178,7 +189,6 @@ def main():
 
         detector = YOLOv8Face(model_name=YOLOv8FaceWeights.YOLOV8N)
 
-    # Determine source type and process
     source_type = get_source_type(args.source)
 
     if source_type == 'camera':
@@ -192,7 +202,12 @@ def main():
         if not os.path.exists(args.source):
             print(f'Error: Video not found: {args.source}')
             return
-        process_video(detector, args.source, args.threshold, args.save_dir)
+        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, ...)')

tools/emotion.py

@@ -5,9 +5,9 @@
 """Emotion detection on detected faces.
 
 Usage:
-    python tools/face_emotion.py --source path/to/image.jpg
-    python tools/face_emotion.py --source path/to/video.mp4
-    python tools/face_emotion.py --source 0  # webcam
+    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
@@ -16,27 +16,12 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 
-from uniface import SCRFD, Emotion, RetinaFace
-from uniface.visualization import draw_detections
-
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
+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):
@@ -71,7 +56,7 @@ def process_image(
     scores = [f.confidence for f in faces]
     landmarks = [f.landmarks for f in faces]
     draw_detections(
-        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, corner_bbox=True
     )
 
     for i, face in enumerate(faces):
@@ -123,7 +108,7 @@ def process_video(
         scores = [f.confidence for f in faces]
         landmarks = [f.landmarks for f in faces]
         draw_detections(
-            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, corner_bbox=True
         )
 
         for face in faces:
@@ -162,7 +147,7 @@ def run_camera(detector, emotion_predictor, camera_id: int = 0, threshold: float
         scores = [f.confidence for f in faces]
         landmarks = [f.landmarks for f in faces]
         draw_detections(
-            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, corner_bbox=True
         )
 
         for face in faces:

tools/fairface.py

@@ -16,28 +16,12 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 
-from uniface import SCRFD, RetinaFace
 from uniface.attribute import FairFace
-from uniface.visualization import draw_detections
-
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
+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):
@@ -72,7 +56,7 @@ def process_image(
     scores = [f.confidence for f in faces]
     landmarks = [f.landmarks for f in faces]
     draw_detections(
-        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+        image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, corner_bbox=True
     )
 
     for i, face in enumerate(faces):
@@ -124,7 +108,7 @@ def process_video(
         scores = [f.confidence for f in faces]
         landmarks = [f.landmarks for f in faces]
         draw_detections(
-            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, corner_bbox=True
         )
 
         for face in faces:
@@ -163,7 +147,7 @@ def run_camera(detector, fairface, camera_id: int = 0, threshold: float = 0.6):
         scores = [f.confidence for f in faces]
         landmarks = [f.landmarks for f in faces]
         draw_detections(
-            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
+            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, corner_bbox=True
         )
 
         for face in faces:

tools/gaze.py

@@ -5,9 +5,9 @@
 """Gaze estimation on detected faces.
 
 Usage:
-    python tools/gaze_estimation.py --source path/to/image.jpg
-    python tools/gaze_estimation.py --source path/to/video.mp4
-    python tools/gaze_estimation.py --source 0  # webcam
+    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
@@ -16,29 +16,13 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 import numpy as np
 
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
+from uniface.draw import draw_gaze
 from uniface.gaze import MobileGaze
-from uniface.visualization import draw_gaze
-
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
 
 
 def process_image(detector, gaze_estimator, image_path: str, save_dir: str = 'outputs'):

tools/landmarks.py

@@ -16,26 +16,11 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 
-from uniface import SCRFD, Landmark106, RetinaFace
-
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
+from uniface.detection import SCRFD, RetinaFace
+from uniface.landmark import Landmark106
 
 
 def process_image(detector, landmarker, image_path: str, save_dir: str = 'outputs'):

tools/parse.py

@@ -5,9 +5,9 @@
 """Face parsing on detected faces.
 
 Usage:
-    python tools/face_parsing.py --source path/to/image.jpg
-    python tools/face_parsing.py --source path/to/video.mp4
-    python tools/face_parsing.py --source 0  # webcam
+    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
@@ -16,30 +16,14 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 import numpy as np
 
-from uniface import RetinaFace
 from uniface.constants import ParsingWeights
+from uniface.detection import RetinaFace
+from uniface.draw import vis_parsing_maps
 from uniface.parsing import BiSeNet
-from uniface.visualization import vis_parsing_maps
-
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
 
 
 def expand_bbox(
@@ -225,7 +209,7 @@ def main():
     args = parser_arg.parse_args()
 
     detector = RetinaFace()
-    parser = BiSeNet(model_name=ParsingWeights.RESNET34)
+    parser = BiSeNet(model_name=args.model)
 
     source_type = get_source_type(args.source)
 

tools/recognize.py

@@ -5,8 +5,8 @@
 """Face recognition: extract embeddings or compare two faces.
 
 Usage:
-    python tools/recognition.py --image path/to/image.jpg
-    python tools/recognition.py --image1 face1.jpg --image2 face2.jpg
+    python tools/recognize.py --image path/to/image.jpg
+    python tools/recognize.py --image1 face1.jpg --image2 face2.jpg
 """
 
 import argparse
@@ -41,7 +41,7 @@ def run_inference(detector, recognizer, image_path: str):
 
     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)
+    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
 
@@ -65,8 +65,8 @@ def compare_faces(detector, recognizer, image1_path: str, image2_path: str, thre
         print('Error: No faces detected in one or both images')
         return
 
-    landmarks1 = faces1[0]['landmarks']
-    landmarks2 = faces2[0]['landmarks']
+    landmarks1 = faces1[0].landmarks
+    landmarks2 = faces2[0].landmarks
 
     embedding1 = recognizer.get_normalized_embedding(img1, landmarks1)
     embedding2 = recognizer.get_normalized_embedding(img2, landmarks2)

tools/search.py

@@ -5,8 +5,8 @@
 """Real-time face search: match faces against a reference image.
 
 Usage:
-    python tools/face_search.py --reference person.jpg --source 0  # webcam
-    python tools/face_search.py --reference person.jpg --source video.mp4
+    python tools/search.py --reference person.jpg --source 0  # webcam
+    python tools/search.py --reference person.jpg --source video.mp4
 """
 
 from __future__ import annotations
@@ -15,6 +15,7 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 import numpy as np
 
@@ -22,23 +23,6 @@ from uniface.detection import SCRFD, RetinaFace
 from uniface.face_utils import compute_similarity
 from uniface.recognition import ArcFace, MobileFace, SphereFace
 
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
-
 
 def get_recognizer(name: str):
     """Get recognizer by name."""

tools/spoofing.py

@@ -16,30 +16,14 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 import numpy as np
 
-from uniface import RetinaFace
 from uniface.constants import MiniFASNetWeights
+from uniface.detection import RetinaFace
 from uniface.spoofing import create_spoofer
 
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
-
 
 def draw_spoofing_result(
     image: np.ndarray,

tools/track.py

@@ -0,0 +1,199 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""Face tracking on video files using ByteTrack.
+
+Usage:
+    python tools/track.py --source video.mp4
+    python tools/track.py --source video.mp4 --output outputs/tracked.mp4
+    python tools/track.py --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+from _common import VIDEO_EXTENSIONS
+import cv2
+import numpy as np
+from tqdm import tqdm
+
+from uniface.common import xyxy_to_cxcywh
+from uniface.detection import SCRFD, RetinaFace
+from uniface.draw import draw_tracks
+from uniface.tracking import BYTETracker
+
+
+def _assign_track_ids(faces, tracks) -> list:
+    """Match tracker outputs back to Face objects by center distance."""
+    if len(tracks) == 0 or len(faces) == 0:
+        return []
+
+    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]  # (N, 2) -> [cx, cy]
+    track_centers = xyxy_to_cxcywh(tracks[:, :4])[:, :2]  # (M, 2) -> [cx, cy]
+
+    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]
+
+    return [f for f in faces if f.track_id is not None]
+
+
+def process_video(
+    detector,
+    tracker: BYTETracker,
+    input_path: str,
+    output_path: str,
+    threshold: float = 0.5,
+    show_preview: bool = False,
+):
+    """Process a video file with face tracking."""
+    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_tracks = 0
+
+    for _ in tqdm(range(total_frames), desc='Tracking', unit='frames'):
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+
+        # Detect faces
+        faces = detector.detect(frame)
+        dets = np.array([[*f.bbox, f.confidence] for f in faces if f.confidence >= threshold])
+        dets = dets if len(dets) > 0 else np.empty((0, 5))
+
+        # Update tracker
+        tracks = tracker.update(dets)
+        tracked_faces = _assign_track_ids(faces, tracks)
+        total_tracks += len(tracked_faces)
+
+        # Draw tracked faces
+        draw_tracks(image=frame, faces=tracked_faces)
+
+        cv2.putText(frame, f'Tracks: {len(tracked_faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(frame)
+
+        if show_preview:
+            cv2.imshow("Tracking - 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_tracks = total_tracks / frame_count if frame_count > 0 else 0
+    print(f'\nDone! {frame_count} frames, {total_tracks} tracks ({avg_tracks:.1f} avg/frame)')
+    print(f'Saved: {output_path}')
+
+
+def run_camera(
+    detector,
+    tracker: BYTETracker,
+    camera_id: int = 0,
+    threshold: float = 0.5,
+):
+    """Run real-time face tracking 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
+
+        # Detect faces
+        faces = detector.detect(frame)
+        dets = np.array([[*f.bbox, f.confidence] for f in faces if f.confidence >= threshold])
+        dets = dets if len(dets) > 0 else np.empty((0, 5))
+
+        # Update tracker
+        tracks = tracker.update(dets)
+        tracked_faces = _assign_track_ids(faces, tracks)
+
+        # Draw tracked faces
+        draw_tracks(image=frame, faces=tracked_faces)
+
+        cv2.putText(frame, f'Tracks: {len(tracked_faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('Face Tracking', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Face tracking on video using ByteTrack')
+    parser.add_argument('--source', type=str, required=True, help='Video path or camera ID (0, 1, ...)')
+    parser.add_argument('--output', type=str, default=None, help='Output video path')
+    parser.add_argument('--detector', type=str, default='scrfd', choices=['retinaface', 'scrfd'])
+    parser.add_argument('--threshold', type=float, default=0.5, help='Detection confidence threshold')
+    parser.add_argument('--track-buffer', type=int, default=30, help='Max frames to keep lost tracks')
+    parser.add_argument('--preview', action='store_true', help='Show live preview')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    args = parser.parse_args()
+
+    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
+    tracker = BYTETracker(track_thresh=args.threshold, track_buffer=args.track_buffer)
+
+    if args.source.isdigit():
+        run_camera(detector, tracker, int(args.source), args.threshold)
+    else:
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+
+        ext = Path(args.source).suffix.lower()
+        if ext not in VIDEO_EXTENSIONS:
+            print(f"Error: Unsupported format '{ext}'. Supported: {VIDEO_EXTENSIONS}")
+            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}_tracked.mp4')
+
+        process_video(detector, tracker, args.source, output_path, args.threshold, args.preview)
+
+
+if __name__ == '__main__':
+    main()

tools/video_detection.py

@@ -1,180 +0,0 @@
-# Copyright 2025-2026 Yakhyokhuja Valikhujaev
-# Author: Yakhyokhuja Valikhujaev
-# GitHub: https://github.com/yakhyo
-
-"""Face detection on video files with progress tracking.
-
-Usage:
-    python tools/video_detection.py --source video.mp4
-    python tools/video_detection.py --source video.mp4 --output output.mp4
-    python tools/video_detection.py --source 0  # webcam
-"""
-
-from __future__ import annotations
-
-import argparse
-import os
-from pathlib import Path
-
-import cv2
-from tqdm import tqdm
-
-from uniface import SCRFD, RetinaFace
-from uniface.visualization import draw_detections
-
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
-
-
-def process_video(
-    detector,
-    input_path: str,
-    output_path: str,
-    threshold: float = 0.6,
-    show_preview: bool = False,
-):
-    """Process a video file with progress bar."""
-    cap = cv2.VideoCapture(input_path)
-    if not cap.isOpened():
-        print(f"Error: Cannot open video file '{input_path}'")
-        return
-
-    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
-    fps = cap.get(cv2.CAP_PROP_FPS)
-    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-
-    print(f'Input: {input_path} ({width}x{height}, {fps:.1f} fps, {total_frames} frames)')
-    print(f'Output: {output_path}')
-
-    Path(output_path).parent.mkdir(parents=True, exist_ok=True)
-    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
-    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
-
-    if not out.isOpened():
-        print(f"Error: Cannot create output video '{output_path}'")
-        cap.release()
-        return
-
-    frame_count = 0
-    total_faces = 0
-
-    for _ in tqdm(range(total_frames), desc='Processing', unit='frames'):
-        ret, frame = cap.read()
-        if not ret:
-            break
-
-        frame_count += 1
-        faces = detector.detect(frame)
-        total_faces += len(faces)
-
-        bboxes = [f.bbox for f in faces]
-        scores = [f.confidence for f in faces]
-        landmarks = [f.landmarks for f in faces]
-        draw_detections(
-            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
-        )
-
-        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-        out.write(frame)
-
-        if show_preview:
-            cv2.imshow("Processing - Press 'q' to cancel", frame)
-            if cv2.waitKey(1) & 0xFF == ord('q'):
-                print('\nCancelled by user')
-                break
-
-    cap.release()
-    out.release()
-    if show_preview:
-        cv2.destroyAllWindows()
-
-    avg_faces = total_faces / frame_count if frame_count > 0 else 0
-    print(f'\nDone! {frame_count} frames, {total_faces} faces ({avg_faces:.1f} avg/frame)')
-    print(f'Saved: {output_path}')
-
-
-def run_camera(detector, camera_id: int = 0, threshold: float = 0.6):
-    """Run real-time detection on webcam."""
-    cap = cv2.VideoCapture(camera_id)
-    if not cap.isOpened():
-        print(f'Cannot open camera {camera_id}')
-        return
-
-    print("Press 'q' to quit")
-
-    while True:
-        ret, frame = cap.read()
-        frame = cv2.flip(frame, 1)
-        if not ret:
-            break
-
-        faces = detector.detect(frame)
-
-        bboxes = [f.bbox for f in faces]
-        scores = [f.confidence for f in faces]
-        landmarks = [f.landmarks for f in faces]
-        draw_detections(
-            image=frame, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=threshold, fancy_bbox=True
-        )
-
-        cv2.putText(frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
-        cv2.imshow('Face Detection', frame)
-
-        if cv2.waitKey(1) & 0xFF == ord('q'):
-            break
-
-    cap.release()
-    cv2.destroyAllWindows()
-
-
-def main():
-    parser = argparse.ArgumentParser(description='Process video with face detection')
-    parser.add_argument('--source', type=str, required=True, help='Video path or camera ID (0, 1, ...)')
-    parser.add_argument('--output', type=str, default=None, help='Output video path (auto-generated if not specified)')
-    parser.add_argument('--detector', type=str, default='retinaface', choices=['retinaface', 'scrfd'])
-    parser.add_argument('--threshold', type=float, default=0.6, help='Visualization threshold')
-    parser.add_argument('--preview', action='store_true', help='Show live preview')
-    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory (if --output not specified)')
-    args = parser.parse_args()
-
-    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
-
-    source_type = get_source_type(args.source)
-
-    if source_type == 'camera':
-        run_camera(detector, int(args.source), args.threshold)
-    elif source_type == 'video':
-        if not os.path.exists(args.source):
-            print(f'Error: Video not found: {args.source}')
-            return
-
-        # Determine output path
-        if args.output:
-            output_path = args.output
-        else:
-            os.makedirs(args.save_dir, exist_ok=True)
-            output_path = os.path.join(args.save_dir, f'{Path(args.source).stem}_detected.mp4')
-
-        process_video(detector, args.source, output_path, args.threshold, args.preview)
-    else:
-        print(f"Error: Unknown source type for '{args.source}'")
-        print('Supported formats: videos (.mp4, .avi, ...) or camera ID (0, 1, ...)')
-
-
-if __name__ == '__main__':
-    main()

tools/xseg.py

@@ -0,0 +1,235 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""XSeg face segmentation on detected faces.
+
+Usage:
+    python tools/xseg.py --source path/to/image.jpg
+    python tools/xseg.py --source path/to/video.mp4
+    python tools/xseg.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.parsing import XSeg
+
+
+def apply_mask_visualization(image: np.ndarray, mask: np.ndarray, alpha: float = 0.5) -> np.ndarray:
+    """Apply colored mask overlay for visualization."""
+    overlay = image.copy().astype(np.float32)
+    mask_3ch = np.stack([mask * 0.3, mask * 0.7, mask * 0.3], axis=-1)
+    overlay = overlay * (1 - mask[..., None] * alpha) + mask_3ch * 255 * alpha
+
+    return overlay.clip(0, 255).astype(np.uint8)
+
+
+def process_image(
+    detector: RetinaFace,
+    parser: XSeg,
+    image_path: str,
+    save_dir: str = 'outputs',
+) -> None:
+    """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 len(faces) == 0:
+        print('No faces detected.')
+        return
+
+    # Accumulate masks from all faces
+    full_mask = np.zeros((image.shape[0], image.shape[1]), dtype=np.float32)
+    for i, face in enumerate(faces):
+        if face.landmarks is None:
+            print(f'  Face {i + 1}: skipped (no landmarks)')
+            continue
+
+        mask = parser.parse(image, landmarks=face.landmarks)
+        full_mask = np.maximum(full_mask, mask)
+        print(f'  Face {i + 1}: done')
+
+    # Apply visualization
+    result_image = apply_mask_visualization(image, full_mask)
+
+    # Draw bounding boxes
+    for face in faces:
+        x1, y1, x2, y2 = map(int, face.bbox[:4])
+        cv2.rectangle(result_image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+    # Save results
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_xseg.jpg')
+    cv2.imwrite(output_path, result_image)
+    print(f'Output saved: {output_path}')
+
+    mask_path = os.path.join(save_dir, f'{Path(image_path).stem}_xseg_mask.png')
+    mask_uint8 = (full_mask * 255).astype(np.uint8)
+    cv2.imwrite(mask_path, mask_uint8)
+    print(f'Mask saved: {mask_path}')
+
+
+def process_video(
+    detector: RetinaFace,
+    parser: XSeg,
+    video_path: str,
+    save_dir: str = 'outputs',
+) -> None:
+    """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}_xseg.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)
+
+        # Accumulate masks from all faces
+        full_mask = np.zeros((frame.shape[0], frame.shape[1]), dtype=np.float32)
+        for face in faces:
+            if face.landmarks is None:
+                continue
+            mask = parser.parse(frame, landmarks=face.landmarks)
+            full_mask = np.maximum(full_mask, mask)
+
+        # Apply visualization
+        result_frame = apply_mask_visualization(frame, full_mask)
+
+        # Draw bounding boxes
+        for face in faces:
+            x1, y1, x2, y2 = map(int, face.bbox[:4])
+            cv2.rectangle(result_frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+        cv2.putText(result_frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        out.write(result_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: RetinaFace,
+    parser: XSeg,
+    camera_id: int = 0,
+) -> None:
+    """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)
+
+        # Accumulate masks from all faces
+        full_mask = np.zeros((frame.shape[0], frame.shape[1]), dtype=np.float32)
+        for face in faces:
+            if face.landmarks is None:
+                continue
+            mask = parser.parse(frame, landmarks=face.landmarks)
+            full_mask = np.maximum(full_mask, mask)
+
+        # Apply visualization
+        result_frame = apply_mask_visualization(frame, full_mask)
+
+        # Draw bounding boxes
+        for face in faces:
+            x1, y1, x2, y2 = map(int, face.bbox[:4])
+            cv2.rectangle(result_frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
+
+        cv2.putText(result_frame, f'Faces: {len(faces)}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.imshow('XSeg Face Segmentation', result_frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main() -> None:
+    arg_parser = argparse.ArgumentParser(description='XSeg face segmentation')
+    arg_parser.add_argument('--source', type=str, required=True, help='Image/video path or camera ID (0, 1, ...)')
+    arg_parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+    arg_parser.add_argument(
+        '--blur',
+        type=float,
+        default=0,
+        help='Gaussian blur sigma for mask smoothing (default: 0 = raw)',
+    )
+    arg_parser.add_argument(
+        '--align-size',
+        type=int,
+        default=256,
+        help='Face alignment size (default: 256)',
+    )
+    args = arg_parser.parse_args()
+
+    # Initialize models
+    detector = RetinaFace()
+    parser = XSeg(blur_sigma=args.blur, align_size=args.align_size)
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, parser, 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, parser, 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, parser, 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()

uniface/__init__.py

@@ -16,6 +16,7 @@
 This library provides unified APIs for:
 - Face detection (RetinaFace, SCRFD, YOLOv5Face, YOLOv8Face)
 - Face recognition (AdaFace, ArcFace, MobileFace, SphereFace)
+- Face tracking (ByteTrack with Kalman filtering)
 - Facial landmarks (106-point detection)
 - Face parsing (semantic segmentation)
 - Gaze estimation
@@ -28,39 +29,31 @@ from __future__ import annotations
 
 __license__ = 'MIT'
 __author__ = 'Yakhyokhuja Valikhujaev'
-__version__ = '2.2.0'
+__version__ = '3.0.0'
 
 from uniface.face_utils import compute_similarity, face_alignment
 from uniface.log import Logger, enable_logging
-from uniface.model_store import verify_model_weights
-from uniface.visualization import draw_detections, vis_parsing_maps
+from uniface.model_store import download_models, get_cache_dir, set_cache_dir, verify_model_weights
 
 from .analyzer import FaceAnalyzer
-from .attribute import AgeGender, FairFace
+from .attribute import AgeGender, Emotion, FairFace
 from .detection import (
     SCRFD,
     RetinaFace,
     YOLOv5Face,
     YOLOv8Face,
     create_detector,
-    detect_faces,
     list_available_detectors,
 )
 from .gaze import MobileGaze, create_gaze_estimator
 from .landmark import Landmark106, create_landmarker
-from .parsing import BiSeNet, create_face_parser
-from .privacy import BlurFace, anonymize_faces
+from .parsing import BiSeNet, XSeg, create_face_parser
+from .privacy import BlurFace
 from .recognition import AdaFace, ArcFace, MobileFace, SphereFace, create_recognizer
 from .spoofing import MiniFASNet, create_spoofer
+from .tracking import BYTETracker
 from .types import AttributeResult, EmotionResult, Face, GazeResult, SpoofingResult
 
-# Optional: Emotion requires PyTorch
-Emotion: type | None
-try:
-    from .attribute import Emotion
-except ImportError:
-    Emotion = None
-
 __all__ = [
     # Metadata
     '__author__',
@@ -76,7 +69,6 @@ __all__ = [
     'create_landmarker',
     'create_recognizer',
     'create_spoofer',
-    'detect_faces',
     'list_available_detectors',
     # Detection models
     'RetinaFace',
@@ -95,6 +87,7 @@ __all__ = [
     'MobileGaze',
     # Parsing models
     'BiSeNet',
+    'XSeg',
     # Attribute models
     'AgeGender',
     'AttributeResult',
@@ -104,15 +97,17 @@ __all__ = [
     # Spoofing models
     'MiniFASNet',
     'SpoofingResult',
+    # Tracking
+    'BYTETracker',
     # Privacy
     'BlurFace',
-    'anonymize_faces',
     # Utilities
     'Logger',
     'compute_similarity',
-    'draw_detections',
+    'download_models',
     'enable_logging',
     'face_alignment',
+    'get_cache_dir',
+    'set_cache_dir',
     'verify_model_weights',
-    'vis_parsing_maps',
 ]

uniface/attribute/__init__.py

@@ -12,18 +12,27 @@ from uniface.attribute.age_gender import AgeGender
 from uniface.attribute.base import Attribute
 from uniface.attribute.fairface import FairFace
 from uniface.constants import AgeGenderWeights, DDAMFNWeights, FairFaceWeights
-from uniface.types import AttributeResult, EmotionResult, Face
+from uniface.types import AttributeResult, EmotionResult
 
-# Emotion requires PyTorch - make it optional
 try:
     from uniface.attribute.emotion import Emotion
 
     _EMOTION_AVAILABLE = True
 except ImportError:
-    Emotion = None
     _EMOTION_AVAILABLE = False
 
-# Public API for the attribute module
+    class Emotion(Attribute):  # type: ignore[no-redef]
+        """Stub for Emotion when PyTorch is not installed."""
+
+        def __init__(self, *args: Any, **kwargs: Any) -> None:
+            raise ImportError("Emotion requires optional dependency 'torch'. Install with: pip install torch")
+
+        def _initialize_model(self) -> None: ...
+        def preprocess(self, image: np.ndarray, *args: Any) -> Any: ...
+        def postprocess(self, prediction: Any) -> Any: ...
+        def predict(self, image: np.ndarray, *args: Any) -> Any: ...
+
+
 __all__ = [
     'AgeGender',
     'AttributeResult',
@@ -31,16 +40,13 @@ __all__ = [
     'EmotionResult',
     'FairFace',
     'create_attribute_predictor',
-    'predict_attributes',
 ]
 
-# A mapping from model enums to their corresponding attribute classes
 _ATTRIBUTE_MODELS = {
     **dict.fromkeys(AgeGenderWeights, AgeGender),
     **dict.fromkeys(FairFaceWeights, FairFace),
 }
 
-# Add Emotion models only if PyTorch is available
 if _EMOTION_AVAILABLE:
     _ATTRIBUTE_MODELS.update(dict.fromkeys(DDAMFNWeights, Emotion))
 
@@ -48,21 +54,16 @@ if _EMOTION_AVAILABLE:
 def create_attribute_predictor(
     model_name: AgeGenderWeights | DDAMFNWeights | FairFaceWeights, **kwargs: Any
 ) -> Attribute:
-    """
-    Factory function to create an attribute predictor instance.
-
-    This high-level API simplifies the creation of attribute models by
-    dynamically selecting the correct class based on the provided model enum.
+    """Factory function to create an attribute predictor instance.
 
     Args:
         model_name: The enum corresponding to the desired attribute model
-                    (e.g., AgeGenderWeights.DEFAULT, DDAMFNWeights.AFFECNET7,
-                    or FairFaceWeights.DEFAULT).
-        **kwargs: Additional keyword arguments to pass to the model's constructor.
+            (e.g., AgeGenderWeights.DEFAULT, DDAMFNWeights.AFFECNET7,
+            or FairFaceWeights.DEFAULT).
+        **kwargs: Additional keyword arguments passed to the model constructor.
 
     Returns:
-        An initialized instance of an Attribute predictor class
-        (e.g., AgeGender, FairFace, or Emotion).
+        An initialized Attribute predictor (AgeGender, FairFace, or Emotion).
 
     Raises:
         ValueError: If the provided model_name is not a supported enum.
@@ -75,40 +76,4 @@ def create_attribute_predictor(
             f'Please choose from AgeGenderWeights, FairFaceWeights, or DDAMFNWeights.'
         )
 
-    # Pass model_name to the constructor, as some classes might need it
     return model_class(model_name=model_name, **kwargs)
-
-
-def predict_attributes(image: np.ndarray, faces: list[Face], predictor: Attribute) -> list[Face]:
-    """
-    High-level API to predict attributes for multiple detected faces.
-
-    This function iterates through a list of Face objects, runs the
-    specified attribute predictor on each one, and updates the Face
-    objects with the predicted attributes.
-
-    Args:
-        image (np.ndarray): The full input image in BGR format.
-        faces (List[Face]): A list of Face objects from face detection.
-        predictor (Attribute): An initialized attribute predictor instance,
-                               created by `create_attribute_predictor`.
-
-    Returns:
-        List[Face]: The list of Face objects with updated attribute fields.
-    """
-    for face in faces:
-        if isinstance(predictor, AgeGender):
-            result = predictor(image, face.bbox)
-            face.gender = result.gender
-            face.age = result.age
-        elif isinstance(predictor, FairFace):
-            result = predictor(image, face.bbox)
-            face.gender = result.gender
-            face.age_group = result.age_group
-            face.race = result.race
-        elif isinstance(predictor, Emotion):
-            result = predictor(image, face.landmarks)
-            face.emotion = result.emotion
-            face.emotion_confidence = result.confidence
-
-    return faces

uniface/attribute/age_gender.py

@@ -30,12 +30,15 @@ class AgeGender(Attribute):
             Defaults to `AgeGenderWeights.DEFAULT`.
         input_size (Optional[Tuple[int, int]]): Input size (height, width).
             If None, automatically detected from model metadata. Defaults to None.
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
     """
 
     def __init__(
         self,
         model_name: AgeGenderWeights = AgeGenderWeights.DEFAULT,
         input_size: tuple[int, int] | None = None,
+        providers: list[str] | None = None,
     ) -> None:
         """
         Initializes the AgeGender prediction model.
@@ -44,10 +47,13 @@ class AgeGender(Attribute):
             model_name (AgeGenderWeights): The enum specifying the model weights to load.
             input_size (Optional[Tuple[int, int]]): Input size (height, width).
                 If None, automatically detected from model metadata. Defaults to None.
+            providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+                the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
         """
         Logger.info(f'Initializing AgeGender with model={model_name.name}')
         self.model_path = verify_model_weights(model_name)
         self._user_input_size = input_size  # Store user preference
+        self.providers = providers
         self._initialize_model()
 
     def _initialize_model(self) -> None:
@@ -55,7 +61,7 @@ class AgeGender(Attribute):
         Initializes the ONNX model and creates an inference session.
         """
         try:
-            self.session = create_onnx_session(self.model_path)
+            self.session = create_onnx_session(self.model_path, providers=self.providers)
             # Get model input details from the loaded model
             input_meta = self.session.get_inputs()[0]
             self.input_name = input_meta.name

uniface/attribute/emotion.py

@@ -28,17 +28,17 @@ class Emotion(Attribute):
 
     def __init__(
         self,
-        model_weights: DDAMFNWeights = DDAMFNWeights.AFFECNET7,
+        model_name: DDAMFNWeights = DDAMFNWeights.AFFECNET7,
         input_size: tuple[int, int] = (112, 112),
     ) -> None:
         """
         Initializes the emotion recognition model.
 
         Args:
-            model_weights (DDAMFNWeights): The enum for the model weights to load.
+            model_name (DDAMFNWeights): The enum for the model weights to load.
             input_size (Tuple[int, int]): The expected input size for the model.
         """
-        Logger.info(f'Initializing Emotion with model={model_weights.name}')
+        Logger.info(f'Initializing Emotion with model={model_name.name}')
 
         if torch.backends.mps.is_available():
             self.device = torch.device('mps')
@@ -48,7 +48,7 @@ class Emotion(Attribute):
             self.device = torch.device('cpu')
 
         self.input_size = input_size
-        self.model_path = verify_model_weights(model_weights)
+        self.model_path = verify_model_weights(model_name)
 
         # Define emotion labels based on the selected model
         self.emotion_labels = [
@@ -60,7 +60,7 @@ class Emotion(Attribute):
             'Disgust',
             'Angry',
         ]
-        if model_weights == DDAMFNWeights.AFFECNET8:
+        if model_name == DDAMFNWeights.AFFECNET8:
             self.emotion_labels.append('Contempt')
 
         self._initialize_model()

uniface/attribute/fairface.py

@@ -44,12 +44,15 @@ class FairFace(Attribute):
             Defaults to `FairFaceWeights.DEFAULT`.
         input_size (Optional[Tuple[int, int]]): Input size (height, width).
             If None, defaults to (224, 224). Defaults to None.
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
     """
 
     def __init__(
         self,
         model_name: FairFaceWeights = FairFaceWeights.DEFAULT,
         input_size: tuple[int, int] | None = None,
+        providers: list[str] | None = None,
     ) -> None:
         """
         Initializes the FairFace prediction model.
@@ -58,10 +61,13 @@ class FairFace(Attribute):
             model_name (FairFaceWeights): The enum specifying the model weights to load.
             input_size (Optional[Tuple[int, int]]): Input size (height, width).
                 If None, defaults to (224, 224).
+            providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+                the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
         """
         Logger.info(f'Initializing FairFace with model={model_name.name}')
         self.model_path = verify_model_weights(model_name)
         self.input_size = input_size if input_size is not None else (224, 224)
+        self.providers = providers
         self._initialize_model()
 
     def _initialize_model(self) -> None:
@@ -69,7 +75,7 @@ class FairFace(Attribute):
         Initializes the ONNX model and creates an inference session.
         """
         try:
-            self.session = create_onnx_session(self.model_path)
+            self.session = create_onnx_session(self.model_path, providers=self.providers)
             # Get model input details from the loaded model
             input_meta = self.session.get_inputs()[0]
             self.input_name = input_meta.name

uniface/common.py

@@ -18,6 +18,7 @@ __all__ = [
     'generate_anchors',
     'non_max_suppression',
     'resize_image',
+    'xyxy_to_cxcywh',
 ]
 
 
@@ -61,6 +62,23 @@ def resize_image(
     return image, resize_factor
 
 
+def xyxy_to_cxcywh(bboxes: np.ndarray) -> np.ndarray:
+    """Convert bounding boxes from ``[x1, y1, x2, y2]`` to ``[cx, cy, w, h]``.
+
+    Args:
+        bboxes: Array of shape (N, 4) or (4,) with ``[x1, y1, x2, y2]`` coordinates.
+
+    Returns:
+        Array of the same shape with ``[cx, cy, w, h]`` coordinates.
+    """
+    out = np.empty_like(bboxes)
+    out[..., 0] = (bboxes[..., 0] + bboxes[..., 2]) / 2  # cx
+    out[..., 1] = (bboxes[..., 1] + bboxes[..., 3]) / 2  # cy
+    out[..., 2] = bboxes[..., 2] - bboxes[..., 0]  # w
+    out[..., 3] = bboxes[..., 3] - bboxes[..., 1]  # h
+    return out
+
+
 def generate_anchors(image_size: tuple[int, int] = (640, 640)) -> np.ndarray:
     """Generate anchor boxes for a given image size (RetinaFace specific).
 

uniface/constants.py

@@ -150,6 +150,15 @@ class ParsingWeights(str, Enum):
     RESNET34 = "parsing_resnet34"
 
 
+class XSegWeights(str, Enum):
+    """
+    XSeg face segmentation model from DeepFaceLab.
+    Outputs mask for face region.
+    https://github.com/iperov/DeepFaceLab
+    """
+    DEFAULT = "xseg"
+
+
 class MiniFASNetWeights(str, Enum):
     """
     MiniFASNet: Lightweight Face Anti-Spoofing models.
@@ -217,6 +226,8 @@ MODEL_URLS: dict[Enum, str] = {
     # Anti-Spoofing (MiniFASNet)
     MiniFASNetWeights.V1SE:          'https://github.com/yakhyo/face-anti-spoofing/releases/download/weights/MiniFASNetV1SE.onnx',
     MiniFASNetWeights.V2:            'https://github.com/yakhyo/face-anti-spoofing/releases/download/weights/MiniFASNetV2.onnx',
+    # XSeg
+    XSegWeights.DEFAULT:             'https://github.com/yakhyo/face-segmentation/releases/download/weights/xseg.onnx',
 }
 
 MODEL_SHA256: dict[Enum, str] = {
@@ -261,17 +272,19 @@ MODEL_SHA256: dict[Enum, str] = {
     # Landmark
     LandmarkWeights.DEFAULT:         'f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf',
     # MobileGaze (trained on Gaze360)
-    GazeWeights.RESNET18:            '23d5d7e4f6f40dce8c35274ce9d08b45b9e22cbaaf5af73182f473229d713d31',
-    GazeWeights.RESNET34:            '4457ee5f7acd1a5ab02da4b61f02fc3a0b17adbf3844dd0ba3cd4288f2b5e1de',
-    GazeWeights.RESNET50:            'e1eaf98f5ec7c89c6abe7cfe39f7be83e747163f98d1ff945c0603b3c521be22',
-    GazeWeights.MOBILENET_V2:        'fdcdb84e3e6421b5a79e8f95139f249fc258d7f387eed5ddac2b80a9a15ce076',
-    GazeWeights.MOBILEONE_S0:        'c0b5a4f4a0ffd24f76ab3c1452354bb2f60110899fd9a88b464c75bafec0fde8',
+    GazeWeights.RESNET18:            '404fec1efd07ff49f981e47f461c20c2627119e465ec441bbd1c067d3f16e657',
+    GazeWeights.RESNET34:            'c8e6b14f6095d2425241b9302aa663d9a23b7dfb9d43941352b718c91dc7f2cf',
+    GazeWeights.RESNET50:            'bb28d421565adc4dfb665742f8fc80bdef36dd8caa0c87e040e0937f9fdca9a6',
+    GazeWeights.MOBILENET_V2:        'b81312df85c7ac1c1b5f78c573620d22c2719cb839650e15f12dc7eecb7744a4',
+    GazeWeights.MOBILEONE_S0:        '8b4fdc4e3da44733c9a82e7776b411e4a39f94e8e285aee0fc85a548a55f7d9f',
     # Face Parsing
     ParsingWeights.RESNET18:         '0d9bd318e46987c3bdbfacae9e2c0f461cae1c6ac6ea6d43bbe541a91727e33f',
     ParsingWeights.RESNET34:         '5b805bba7b5660ab7070b5a381dcf75e5b3e04199f1e9387232a77a00095102e',
     # Anti-Spoofing (MiniFASNet)
     MiniFASNetWeights.V1SE:          'ebab7f90c7833fbccd46d3a555410e78d969db5438e169b6524be444862b3676',
     MiniFASNetWeights.V2:            'b32929adc2d9c34b9486f8c4c7bc97c1b69bc0ea9befefc380e4faae4e463907',
+    # XSeg
+    XSegWeights.DEFAULT:             '0b57328efcb839d85973164b617ceee9dfe6cfcb2c82e8a033bba9f4f09b27e5',
 }
 
 CHUNK_SIZE = 8192

uniface/detection/__init__.py

@@ -6,9 +6,12 @@ from __future__ import annotations
 
 from typing import Any
 
-import numpy as np
-
-from uniface.types import Face
+from uniface.constants import (
+    RetinaFaceWeights,
+    SCRFDWeights,
+    YOLOv5FaceWeights,
+    YOLOv8FaceWeights,
+)
 
 from .base import BaseDetector
 from .retinaface import RetinaFace
@@ -16,48 +19,6 @@ from .scrfd import SCRFD
 from .yolov5 import YOLOv5Face
 from .yolov8 import YOLOv8Face
 
-# Global cache for detector instances (keyed by method name + config hash)
-_detector_cache: dict[str, BaseDetector] = {}
-
-
-def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs: Any) -> list[Face]:
-    """High-level face detection function.
-
-    Detects faces in an image using the specified detection method.
-    Results are cached for repeated calls with the same configuration.
-
-    Args:
-        image: Input image as numpy array with shape (H, W, C) in BGR format.
-        method: Detection method to use. Options: 'retinaface', 'scrfd', 'yolov5face', 'yolov8face'.
-        **kwargs: Additional arguments passed to the detector.
-
-    Returns:
-        A list of Face objects, each containing:
-            - bbox: [x1, y1, x2, y2] bounding box coordinates.
-            - confidence: The confidence score of the detection.
-            - landmarks: 5-point facial landmarks with shape (5, 2).
-
-    Example:
-        >>> from uniface import detect_faces
-        >>> import cv2
-        >>> image = cv2.imread('your_image.jpg')
-        >>> faces = detect_faces(image, method='retinaface', confidence_threshold=0.8)
-        >>> for face in faces:
-        ...     print(f'Found face with confidence: {face.confidence}')
-        ...     print(f'BBox: {face.bbox}')
-    """
-    method_name = method.lower()
-
-    sorted_kwargs = sorted(kwargs.items())
-    cache_key = f'{method_name}_{sorted_kwargs!s}'
-
-    if cache_key not in _detector_cache:
-        # Pass kwargs to create the correctly configured detector
-        _detector_cache[cache_key] = create_detector(method, **kwargs)
-
-    detector = _detector_cache[cache_key]
-    return detector.detect(image)
-
 
 def create_detector(method: str = 'retinaface', **kwargs: Any) -> BaseDetector:
     """Factory function to create face detectors.
@@ -122,7 +83,7 @@ def list_available_detectors() -> dict[str, dict[str, Any]]:
             'supports_landmarks': True,
             'paper': 'https://arxiv.org/abs/1905.00641',
             'default_params': {
-                'model_name': 'mnet_v2',
+                'model_name': RetinaFaceWeights.MNET_V2.value,
                 'confidence_threshold': 0.5,
                 'nms_threshold': 0.4,
                 'input_size': (640, 640),
@@ -133,7 +94,7 @@ def list_available_detectors() -> dict[str, dict[str, Any]]:
             'supports_landmarks': True,
             'paper': 'https://arxiv.org/abs/2105.04714',
             'default_params': {
-                'model_name': 'scrfd_10g_kps',
+                'model_name': SCRFDWeights.SCRFD_10G_KPS.value,
                 'confidence_threshold': 0.5,
                 'nms_threshold': 0.4,
                 'input_size': (640, 640),
@@ -144,9 +105,9 @@ def list_available_detectors() -> dict[str, dict[str, Any]]:
             'supports_landmarks': True,
             'paper': 'https://arxiv.org/abs/2105.12931',
             'default_params': {
-                'model_name': 'yolov5s_face',
-                'confidence_threshold': 0.25,
-                'nms_threshold': 0.45,
+                'model_name': YOLOv5FaceWeights.YOLOV5S.value,
+                'confidence_threshold': 0.6,
+                'nms_threshold': 0.5,
                 'input_size': 640,
             },
         },
@@ -155,7 +116,7 @@ def list_available_detectors() -> dict[str, dict[str, Any]]:
             'supports_landmarks': True,
             'paper': 'https://github.com/derronqi/yolov8-face',
             'default_params': {
-                'model_name': 'yolov8n_face',
+                'model_name': YOLOv8FaceWeights.YOLOV8N.value,
                 'confidence_threshold': 0.5,
                 'nms_threshold': 0.45,
                 'input_size': 640,
@@ -171,6 +132,5 @@ __all__ = [
     'YOLOv5Face',
     'YOLOv8Face',
     'create_detector',
-    'detect_faces',
     'list_available_detectors',
 ]

uniface/detection/retinaface.py

@@ -39,6 +39,8 @@ class RetinaFace(BaseDetector):
         input_size (Tuple[int, int]): Fixed input size (width, height) if `dynamic_size=False`.
             Defaults to (640, 640).
             Note: Non-default sizes may cause slower inference and CoreML compatibility issues.
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
         **kwargs: Advanced options:
             pre_nms_topk (int): Number of top-scoring boxes considered before NMS. Defaults to 5000.
             post_nms_topk (int): Max number of detections kept after NMS. Defaults to 750.
@@ -68,6 +70,7 @@ class RetinaFace(BaseDetector):
         confidence_threshold: float = 0.5,
         nms_threshold: float = 0.4,
         input_size: tuple[int, int] = (640, 640),
+        providers: list[str] | None = None,
         **kwargs: Any,
     ) -> None:
         super().__init__(
@@ -75,6 +78,7 @@ class RetinaFace(BaseDetector):
             confidence_threshold=confidence_threshold,
             nms_threshold=nms_threshold,
             input_size=input_size,
+            providers=providers,
             **kwargs,
         )
         self._supports_landmarks = True  # RetinaFace supports landmarks
@@ -83,6 +87,7 @@ class RetinaFace(BaseDetector):
         self.confidence_threshold = confidence_threshold
         self.nms_threshold = nms_threshold
         self.input_size = input_size
+        self.providers = providers
 
         # Advanced options from kwargs
         self.pre_nms_topk = kwargs.get('pre_nms_topk', 5000)
@@ -116,7 +121,7 @@ class RetinaFace(BaseDetector):
             RuntimeError: If the model fails to load.
         """
         try:
-            self.session = create_onnx_session(model_path)
+            self.session = create_onnx_session(model_path, providers=self.providers)
             self.input_names = self.session.get_inputs()[0].name
             self.output_names = [x.name for x in self.session.get_outputs()]
             Logger.info(f'Successfully initialized the model from {model_path}')

uniface/detection/scrfd.py

@@ -36,6 +36,8 @@ class SCRFD(BaseDetector):
         input_size (Tuple[int, int]): Input image size (width, height).
             Defaults to (640, 640).
             Note: Non-default sizes may cause slower inference and CoreML compatibility issues.
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
         **kwargs: Reserved for future advanced options.
 
     Attributes:
@@ -61,6 +63,7 @@ class SCRFD(BaseDetector):
         confidence_threshold: float = 0.5,
         nms_threshold: float = 0.4,
         input_size: tuple[int, int] = (640, 640),
+        providers: list[str] | None = None,
         **kwargs: Any,
     ) -> None:
         super().__init__(
@@ -68,6 +71,7 @@ class SCRFD(BaseDetector):
             confidence_threshold=confidence_threshold,
             nms_threshold=nms_threshold,
             input_size=input_size,
+            providers=providers,
             **kwargs,
         )
         self._supports_landmarks = True  # SCRFD supports landmarks
@@ -76,6 +80,7 @@ class SCRFD(BaseDetector):
         self.confidence_threshold = confidence_threshold
         self.nms_threshold = nms_threshold
         self.input_size = input_size
+        self.providers = providers
 
         # ------- SCRFD model params ------
         self._num_feature_maps = 3
@@ -106,7 +111,7 @@ class SCRFD(BaseDetector):
             RuntimeError: If the model fails to load.
         """
         try:
-            self.session = create_onnx_session(model_path)
+            self.session = create_onnx_session(model_path, providers=self.providers)
             self.input_names = self.session.get_inputs()[0].name
             self.output_names = [x.name for x in self.session.get_outputs()]
             Logger.info(f'Successfully initialized the model from {model_path}')

uniface/detection/yolov5.py

@@ -44,7 +44,9 @@ class YOLOv5Face(BaseDetector):
         input_size (int): Input image size. Defaults to 640.
             Note: ONNX model is fixed at 640. Changing this will cause inference errors.
         nms_mode (str): NMS calculation method. Options: 'torchvision' (faster, requires torch)
-            or 'numpy' (no dependencies). Defaults to 'torchvision' if available.
+            or 'numpy' (no dependencies). Defaults to 'numpy'.
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
         **kwargs: Advanced options:
             max_det (int): Maximum number of detections to return. Defaults to 750.
 
@@ -70,6 +72,7 @@ class YOLOv5Face(BaseDetector):
         nms_threshold: float = 0.5,
         input_size: int = 640,
         nms_mode: Literal['torchvision', 'numpy'] = 'numpy',
+        providers: list[str] | None = None,
         **kwargs: Any,
     ) -> None:
         super().__init__(
@@ -78,6 +81,7 @@ class YOLOv5Face(BaseDetector):
             nms_threshold=nms_threshold,
             input_size=input_size,
             nms_mode=nms_mode,
+            providers=providers,
             **kwargs,
         )
         self._supports_landmarks = True  # YOLOv5-Face supports landmarks
@@ -92,6 +96,7 @@ class YOLOv5Face(BaseDetector):
         self.confidence_threshold = confidence_threshold
         self.nms_threshold = nms_threshold
         self.input_size = input_size
+        self.providers = providers
 
         # Set NMS mode with automatic fallback
         if nms_mode == 'torchvision' and not TORCHVISION_AVAILABLE:
@@ -126,7 +131,7 @@ class YOLOv5Face(BaseDetector):
             RuntimeError: If the model fails to load, logs an error and raises an exception.
         """
         try:
-            self.session = create_onnx_session(model_path)
+            self.session = create_onnx_session(model_path, providers=self.providers)
             self.input_names = self.session.get_inputs()[0].name
             self.output_names = [x.name for x in self.session.get_outputs()]
             Logger.info(f'Successfully initialized the model from {model_path}')

uniface/detection/yolov8.py

@@ -52,7 +52,9 @@ class YOLOv8Face(BaseDetector):
         input_size (int): Input image size. Defaults to 640.
             Note: ONNX model is fixed at 640. Changing this will cause inference errors.
         nms_mode (str): NMS calculation method. Options: 'torchvision' (faster, requires torch)
-            or 'numpy' (no dependencies). Defaults to 'torchvision' if available.
+            or 'numpy' (no dependencies). Defaults to 'numpy'.
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
         **kwargs: Advanced options:
             max_det (int): Maximum number of detections to return. Defaults to 750.
 
@@ -78,6 +80,7 @@ class YOLOv8Face(BaseDetector):
         nms_threshold: float = 0.45,
         input_size: int = 640,
         nms_mode: Literal['torchvision', 'numpy'] = 'numpy',
+        providers: list[str] | None = None,
         **kwargs: Any,
     ) -> None:
         super().__init__(
@@ -86,6 +89,7 @@ class YOLOv8Face(BaseDetector):
             nms_threshold=nms_threshold,
             input_size=input_size,
             nms_mode=nms_mode,
+            providers=providers,
             **kwargs,
         )
         self._supports_landmarks = True  # YOLOv8-Face supports landmarks
@@ -100,6 +104,7 @@ class YOLOv8Face(BaseDetector):
         self.confidence_threshold = confidence_threshold
         self.nms_threshold = nms_threshold
         self.input_size = input_size
+        self.providers = providers
 
         # Set NMS mode with automatic fallback
         if nms_mode == 'torchvision' and not TORCHVISION_AVAILABLE:
@@ -137,7 +142,7 @@ class YOLOv8Face(BaseDetector):
             RuntimeError: If the model fails to load, logs an error and raises an exception.
         """
         try:
-            self.session = create_onnx_session(model_path)
+            self.session = create_onnx_session(model_path, providers=self.providers)
             self.input_names = self.session.get_inputs()[0].name
             self.output_names = [x.name for x in self.session.get_outputs()]
             Logger.info(f'Successfully initialized the model from {model_path}')

uniface/draw.py

@@ -0,0 +1,475 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+import colorsys
+from typing import TYPE_CHECKING
+
+import cv2
+import numpy as np
+
+if TYPE_CHECKING:
+    from uniface.types import Face
+
+__all__ = [
+    'FACE_PARSING_COLORS',
+    'FACE_PARSING_LABELS',
+    'calculate_optimal_line_thickness',
+    'calculate_optimal_text_scale',
+    'draw_corner_bbox',
+    'draw_detections',
+    'draw_gaze',
+    'draw_text_label',
+    'draw_tracks',
+    'vis_parsing_maps',
+]
+
+# Face parsing component names (19 classes)
+FACE_PARSING_LABELS = [
+    'background',
+    'skin',
+    'l_brow',
+    'r_brow',
+    'l_eye',
+    'r_eye',
+    'eye_g',
+    'l_ear',
+    'r_ear',
+    'ear_r',
+    'nose',
+    'mouth',
+    'u_lip',
+    'l_lip',
+    'neck',
+    'neck_l',
+    'cloth',
+    'hair',
+    'hat',
+]
+
+# Color palette for face parsing visualization
+FACE_PARSING_COLORS = [
+    [0, 0, 0],
+    [255, 85, 0],
+    [255, 170, 0],
+    [255, 0, 85],
+    [255, 0, 170],
+    [0, 255, 0],
+    [85, 255, 0],
+    [170, 255, 0],
+    [0, 255, 85],
+    [0, 255, 170],
+    [0, 0, 255],
+    [85, 0, 255],
+    [170, 0, 255],
+    [0, 85, 255],
+    [0, 170, 255],
+    [255, 255, 0],
+    [255, 255, 85],
+    [255, 255, 170],
+    [255, 0, 255],
+]
+
+# Per-point colors for 5-point facial landmarks (BGR)
+_LANDMARK_COLORS = (
+    (0, 0, 255),
+    (0, 255, 255),
+    (255, 0, 255),
+    (0, 255, 0),
+    (255, 0, 0),
+)
+
+
+def _get_color(idx: int) -> tuple[int, int, int]:
+    """Get a visually distinct BGR color for a given index.
+
+    Uses golden-ratio hue stepping in HSV space to maximize perceptual
+    separation between consecutive indices. Works for any non-negative index.
+
+    Args:
+        idx: Non-negative integer index (e.g. track ID).
+
+    Returns:
+        BGR color tuple suitable for OpenCV drawing functions.
+    """
+    golden_ratio = 0.618033988749895
+    hue = (idx * golden_ratio) % 1.0
+    # HSV -> RGB with fixed saturation=0.85 and value=0.95 for vivid colors
+    r, g, b = colorsys.hsv_to_rgb(hue, 0.85, 0.95)
+    return int(b * 255), int(g * 255), int(r * 255)
+
+
+def calculate_optimal_line_thickness(resolution_wh: tuple[int, int]) -> int:
+    """Calculate adaptive line thickness based on image resolution.
+
+    Args:
+        resolution_wh: Image resolution as ``(width, height)``.
+
+    Returns:
+        Recommended line thickness in pixels.
+
+    Example:
+        >>> calculate_optimal_line_thickness((1920, 1080))
+        4
+        >>> calculate_optimal_line_thickness((640, 480))
+        2
+    """
+    return max(round(sum(resolution_wh) / 2 * 0.003), 2)
+
+
+def calculate_optimal_text_scale(resolution_wh: tuple[int, int]) -> float:
+    """Calculate adaptive font scale based on image resolution.
+
+    Args:
+        resolution_wh: Image resolution as ``(width, height)``.
+
+    Returns:
+        Recommended font scale factor.
+
+    Example:
+        >>> calculate_optimal_text_scale((1920, 1080))
+        1.08
+        >>> calculate_optimal_text_scale((640, 480))
+        0.48
+    """
+    return min(resolution_wh) * 1e-3
+
+
+def draw_corner_bbox(
+    image: np.ndarray,
+    bbox: np.ndarray,
+    color: tuple[int, int, int] = (0, 255, 0),
+    thickness: int = 3,
+    proportion: float = 0.2,
+) -> None:
+    """Draw a bounding box with corner brackets on an image.
+
+    Draws a thin full rectangle with thick corner accents, commonly used in
+    face-detection overlays for a clean look.
+
+    Args:
+        image: Input image to draw on (modified in-place).
+        bbox: Bounding box in xyxy format ``[x1, y1, x2, y2]``.
+        color: BGR color of the box. Defaults to green ``(0, 255, 0)``.
+        thickness: Thickness of corner bracket lines. Defaults to 3.
+        proportion: Corner length as a fraction of the shorter side.
+            Defaults to 0.2.
+    """
+    x1, y1, x2, y2 = map(int, bbox)
+    corner_length = int(proportion * min(x2 - x1, y2 - y1))
+
+    # Thin full rectangle
+    cv2.rectangle(image, (x1, y1), (x2, y2), color, 1)
+
+    # Top-left corner
+    cv2.line(image, (x1, y1), (x1 + corner_length, y1), color, thickness)
+    cv2.line(image, (x1, y1), (x1, y1 + corner_length), color, thickness)
+
+    # Top-right corner
+    cv2.line(image, (x2, y1), (x2 - corner_length, y1), color, thickness)
+    cv2.line(image, (x2, y1), (x2, y1 + corner_length), color, thickness)
+
+    # Bottom-left corner
+    cv2.line(image, (x1, y2), (x1, y2 - corner_length), color, thickness)
+    cv2.line(image, (x1, y2), (x1 + corner_length, y2), color, thickness)
+
+    # Bottom-right corner
+    cv2.line(image, (x2, y2), (x2, y2 - corner_length), color, thickness)
+    cv2.line(image, (x2, y2), (x2 - corner_length, y2), color, thickness)
+
+
+def draw_text_label(
+    image: np.ndarray,
+    text: str,
+    x: int,
+    y: int,
+    bg_color: tuple[int, int, int],
+    text_color: tuple[int, int, int] = (255, 255, 255),
+    font_scale: float = 0.5,
+    font_thickness: int = 2,
+    padding: int = 5,
+) -> None:
+    """Draw text with a filled background rectangle above a given position.
+
+    The label is placed so that its bottom edge sits at *y*, making it
+    suitable for positioning above a bounding box top-left corner.
+
+    Args:
+        image: Input image to draw on (modified in-place).
+        text: The text string to render.
+        x: Left x-coordinate for the label.
+        y: Bottom y-coordinate for the label (e.g. ``bbox[1]``).
+        bg_color: BGR background fill color.
+        text_color: BGR text color. Defaults to white.
+        font_scale: OpenCV font scale factor. Defaults to 0.5.
+        font_thickness: OpenCV font thickness. Defaults to 2.
+        padding: Pixel padding around the text. Defaults to 5.
+    """
+    (tw, th), baseline = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, font_scale, font_thickness)
+    cv2.rectangle(
+        image,
+        (x, y - th - baseline - padding * 2),
+        (x + tw + padding * 2, y),
+        bg_color,
+        -1,
+    )
+    cv2.putText(
+        image,
+        text,
+        (x + padding, y - padding),
+        cv2.FONT_HERSHEY_SIMPLEX,
+        font_scale,
+        text_color,
+        font_thickness,
+    )
+
+
+def draw_detections(
+    *,
+    image: np.ndarray,
+    bboxes: list[np.ndarray] | list[list[float]],
+    scores: np.ndarray | list[float],
+    landmarks: list[np.ndarray] | list[list[list[float]]],
+    vis_threshold: float = 0.6,
+    draw_score: bool = False,
+    corner_bbox: bool = True,
+) -> None:
+    """Draw bounding boxes, landmarks, and optional scores on an image.
+
+    Modifies the image in-place.
+
+    Args:
+        image: Input image to draw on (modified in-place).
+        bboxes: List of bounding boxes in xyxy format ``[x1, y1, x2, y2]``.
+        scores: List of confidence scores.
+        landmarks: List of landmark sets with shape ``(5, 2)``.
+        vis_threshold: Confidence threshold for filtering. Defaults to 0.6.
+        draw_score: Whether to draw confidence scores. Defaults to False.
+        corner_bbox: Use corner-style bounding boxes. Defaults to True.
+    """
+
+    # Adaptive line thickness
+    line_thickness = max(round(sum(image.shape[:2]) / 2 * 0.003), 2)
+
+    for i, score in enumerate(scores):
+        if score < vis_threshold:
+            continue
+
+        bbox = np.array(bboxes[i], dtype=np.int32)
+
+        # Draw bounding box
+        if corner_bbox:
+            draw_corner_bbox(image, bbox, color=(0, 255, 0), thickness=line_thickness, proportion=0.2)
+        else:
+            cv2.rectangle(image, tuple(bbox[:2]), tuple(bbox[2:]), (0, 255, 0), line_thickness)
+
+        # Draw confidence score label
+        if draw_score:
+            font_scale = max(0.4, min(0.7, (bbox[3] - bbox[1]) / 200))
+            draw_text_label(
+                image,
+                f'{score:.2f}',
+                bbox[0],
+                bbox[1],
+                bg_color=(0, 255, 0),
+                text_color=(0, 0, 0),
+                font_scale=font_scale,
+            )
+
+        # Draw landmarks
+        landmark_set = np.array(landmarks[i], dtype=np.int32)
+        for j, point in enumerate(landmark_set):
+            cv2.circle(image, tuple(point), line_thickness + 1, _LANDMARK_COLORS[j % len(_LANDMARK_COLORS)], -1)
+
+
+def draw_gaze(
+    image: np.ndarray,
+    bbox: np.ndarray,
+    pitch: np.ndarray | float,
+    yaw: np.ndarray | float,
+    *,
+    draw_bbox: bool = True,
+    corner_bbox: bool = True,
+    draw_angles: bool = True,
+) -> None:
+    """Draw gaze direction with optional bounding box on an image.
+
+    Modifies the image in-place.
+
+    Args:
+        image: Input image to draw on (modified in-place).
+        bbox: Face bounding box in xyxy format ``[x1, y1, x2, y2]``.
+        pitch: Vertical gaze angle in radians.
+        yaw: Horizontal gaze angle in radians.
+        draw_bbox: Whether to draw the bounding box. Defaults to True.
+        corner_bbox: Use corner-style bounding box. Defaults to True.
+        draw_angles: Whether to display pitch/yaw values as text. Defaults to True.
+    """
+
+    x_min, y_min, x_max, y_max = map(int, bbox[:4])
+
+    # Adaptive line thickness
+    line_thickness = max(round(sum(image.shape[:2]) / 2 * 0.003), 2)
+
+    # Draw bounding box if requested
+    if draw_bbox:
+        if corner_bbox:
+            draw_corner_bbox(image, bbox, color=(0, 255, 0), thickness=line_thickness)
+        else:
+            cv2.rectangle(image, (x_min, y_min), (x_max, y_max), (0, 255, 0), line_thickness)
+
+    # Calculate center of the bounding box
+    x_center = (x_min + x_max) // 2
+    y_center = (y_min + y_max) // 2
+
+    # Calculate the direction of the gaze
+    length = x_max - x_min
+    dx = int(-length * np.sin(yaw) * np.cos(pitch))
+    dy = int(-length * np.sin(pitch))
+
+    # Draw gaze arrow
+    center_radius = max(line_thickness + 1, 4)
+    cv2.circle(image, (x_center, y_center), radius=center_radius, color=(0, 0, 255), thickness=-1)
+    cv2.arrowedLine(
+        image,
+        (x_center, y_center),
+        (x_center + dx, y_center + dy),
+        color=(0, 0, 255),
+        thickness=line_thickness,
+        line_type=cv2.LINE_AA,
+        tipLength=0.25,
+    )
+
+    # Draw angle values
+    if draw_angles:
+        font_scale = max(0.4, min(0.7, (y_max - y_min) / 200))
+        draw_text_label(
+            image,
+            f'P:{np.degrees(pitch):.0f}deg Y:{np.degrees(yaw):.0f}deg',
+            x_min,
+            y_min,
+            bg_color=(0, 0, 255),
+            text_color=(255, 255, 255),
+            font_scale=font_scale,
+        )
+
+
+def draw_tracks(
+    *,
+    image: np.ndarray,
+    faces: list[Face],
+    draw_landmarks: bool = True,
+    draw_id: bool = True,
+    corner_bbox: bool = True,
+) -> None:
+    """Draw tracked faces with color-coded track IDs on an image.
+
+    Each track ID is assigned a deterministic color for consistent visualization
+    across frames. Faces without a ``track_id`` are drawn in gray.
+
+    Modifies the image in-place.
+
+    Args:
+        image: Input image to draw on (modified in-place).
+        faces: List of Face objects (with ``track_id`` assigned by BYTETracker).
+        draw_landmarks: Whether to draw facial landmarks. Defaults to True.
+        draw_id: Whether to draw track ID labels. Defaults to True.
+        corner_bbox: Use corner-style bounding boxes. Defaults to True.
+
+    Example:
+        >>> from uniface import BYTETracker, RetinaFace
+        >>> from uniface.draw import draw_tracks
+        >>> detector = RetinaFace()
+        >>> tracker = BYTETracker()
+        >>> draw_tracks(image=frame, faces=faces)
+    """
+    untracked_color = (128, 128, 128)
+
+    # Adaptive line thickness
+    line_thickness = max(round(sum(image.shape[:2]) / 2 * 0.003), 2)
+
+    for face in faces:
+        bbox = np.array(face.bbox, dtype=np.int32)
+        track_id = face.track_id
+
+        # Pick color based on track ID
+        color = _get_color(track_id) if track_id is not None else untracked_color
+
+        # Draw bounding box
+        if corner_bbox:
+            draw_corner_bbox(image, bbox, color=color, thickness=line_thickness, proportion=0.2)
+        else:
+            cv2.rectangle(image, tuple(bbox[:2]), tuple(bbox[2:]), color, line_thickness)
+
+        # Draw track ID label
+        if draw_id and track_id is not None:
+            font_scale = max(0.4, min(0.7, (bbox[3] - bbox[1]) / 200))
+            draw_text_label(
+                image,
+                f'ID:{track_id}',
+                bbox[0],
+                bbox[1],
+                bg_color=color,
+                font_scale=font_scale,
+            )
+
+        # Draw landmarks
+        if draw_landmarks and face.landmarks is not None:
+            landmark_set = np.array(face.landmarks, dtype=np.int32)
+            for j, point in enumerate(landmark_set):
+                cv2.circle(image, tuple(point), line_thickness + 1, _LANDMARK_COLORS[j % len(_LANDMARK_COLORS)], -1)
+
+
+def vis_parsing_maps(
+    image: np.ndarray,
+    segmentation_mask: np.ndarray,
+    *,
+    save_image: bool = False,
+    save_path: str = 'result.png',
+) -> np.ndarray:
+    """Visualize face parsing segmentation mask by overlaying colored regions.
+
+    Args:
+        image: Input face image in RGB format with shape ``(H, W, 3)``.
+        segmentation_mask: Segmentation mask with shape ``(H, W)`` where each
+            pixel value represents a facial component class (0-18).
+        save_image: Whether to save the visualization to disk. Defaults to False.
+        save_path: Path to save the visualization if *save_image* is True.
+
+    Returns:
+        Blended image with segmentation overlay in BGR format.
+
+    Example:
+        >>> import cv2
+        >>> from uniface.parsing import BiSeNet
+        >>> from uniface.draw import vis_parsing_maps
+        >>> parser = BiSeNet()
+        >>> face_image = cv2.imread('face.jpg')
+        >>> mask = parser.parse(face_image)
+        >>> face_rgb = cv2.cvtColor(face_image, cv2.COLOR_BGR2RGB)
+        >>> result = vis_parsing_maps(face_rgb, mask)
+        >>> cv2.imwrite('parsed_face.jpg', result)
+    """
+    image = np.array(image).copy().astype(np.uint8)
+    segmentation_mask = segmentation_mask.copy().astype(np.uint8)
+
+    # Create a color mask
+    segmentation_mask_color = np.zeros((segmentation_mask.shape[0], segmentation_mask.shape[1], 3))
+
+    num_classes = np.max(segmentation_mask)
+    for class_index in range(1, num_classes + 1):
+        class_pixels = np.where(segmentation_mask == class_index)
+        segmentation_mask_color[class_pixels[0], class_pixels[1], :] = FACE_PARSING_COLORS[class_index]
+
+    segmentation_mask_color = segmentation_mask_color.astype(np.uint8)
+
+    # Convert image to BGR format for blending
+    bgr_image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
+    blended_image = cv2.addWeighted(bgr_image, 0.6, segmentation_mask_color, 0.4, 0)
+
+    if save_image:
+        cv2.imwrite(save_path, blended_image, [int(cv2.IMWRITE_JPEG_QUALITY), 100])
+
+    return blended_image

uniface/gaze/__init__.py

@@ -31,7 +31,7 @@ def create_gaze_estimator(method: str = 'mobilegaze', **kwargs) -> BaseGazeEstim
         ValueError: If the specified `method` is not supported.
 
     Examples:
-        >>> # Create the default MobileGaze estimator (ResNet18 backbone)
+        >>> # Create the default MobileGaze estimator (ResNet34 backbone)
         >>> estimator = create_gaze_estimator()
 
         >>> # Create with MobileNetV2 backbone

uniface/gaze/models.py

@@ -38,6 +38,8 @@ class MobileGaze(BaseGazeEstimator):
             Defaults to `GazeWeights.RESNET18`.
         input_size (Tuple[int, int]): The resolution (width, height) for the model's
             input. Defaults to (448, 448).
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
 
     Attributes:
         input_size (Tuple[int, int]): Model input dimensions.
@@ -65,12 +67,14 @@ class MobileGaze(BaseGazeEstimator):
         self,
         model_name: GazeWeights = GazeWeights.RESNET34,
         input_size: tuple[int, int] = (448, 448),
+        providers: list[str] | None = None,
     ) -> None:
         Logger.info(f'Initializing MobileGaze with model={model_name}, input_size={input_size}')
 
         self.input_size = input_size
         self.input_mean = [0.485, 0.456, 0.406]
         self.input_std = [0.229, 0.224, 0.225]
+        self.providers = providers
 
         # Model specific parameters for bin-based classification (Gaze360 config)
         self._bins = 90
@@ -89,7 +93,7 @@ class MobileGaze(BaseGazeEstimator):
             RuntimeError: If the model fails to load or initialize.
         """
         try:
-            self.session = create_onnx_session(self.model_path)
+            self.session = create_onnx_session(self.model_path, providers=self.providers)
 
             # Get input configuration
             input_cfg = self.session.get_inputs()[0]
@@ -102,7 +106,7 @@ class MobileGaze(BaseGazeEstimator):
             self.output_names = [output.name for output in outputs]
 
             if len(self.output_names) != 2:
-                raise ValueError(f'Expected 2 output nodes (pitch, yaw), got {len(self.output_names)}')
+                raise ValueError(f'Expected 2 output nodes (yaw, pitch), got {len(self.output_names)}')
 
             Logger.info(f'MobileGaze initialized with input size {self.input_size}')
 
@@ -157,19 +161,19 @@ class MobileGaze(BaseGazeEstimator):
         Returns:
             GazeResult: Result containing pitch and yaw angles in radians.
         """
-        pitch_logits, yaw_logits = outputs
+        yaw_logits, pitch_logits = outputs
 
         # Convert logits to probabilities
-        pitch_probs = self._softmax(pitch_logits)
         yaw_probs = self._softmax(yaw_logits)
+        pitch_probs = self._softmax(pitch_logits)
 
         # Compute expected bin index (soft-argmax)
-        pitch_deg = np.sum(pitch_probs * self._idx_tensor, axis=1) * self._binwidth - self._angle_offset
         yaw_deg = np.sum(yaw_probs * self._idx_tensor, axis=1) * self._binwidth - self._angle_offset
+        pitch_deg = np.sum(pitch_probs * self._idx_tensor, axis=1) * self._binwidth - self._angle_offset
 
         # Convert degrees to radians
-        pitch = float(np.radians(pitch_deg[0]))
         yaw = float(np.radians(yaw_deg[0]))
+        pitch = float(np.radians(pitch_deg[0]))
 
         return GazeResult(pitch=pitch, yaw=yaw)
 

uniface/landmark/__init__.py

@@ -11,17 +11,18 @@ def create_landmarker(method: str = '2d106det', **kwargs) -> BaseLandmarker:
     Factory function to create facial landmark predictors.
 
     Args:
-        method (str): Landmark prediction method. Options: '106'.
+        method (str): Landmark prediction method.
+            Options: '2d106det' (default), 'landmark106', '106'.
         **kwargs: Model-specific parameters.
 
     Returns:
         Initialized landmarker instance.
     """
     method = method.lower()
-    if method == '2d106det':
+    if method in ('2d106det', 'landmark106', '106'):
         return Landmark106(**kwargs)
     else:
-        available = ['2d106det']
+        available = ['2d106det', 'landmark106', '106']
         raise ValueError(f"Unsupported method: '{method}'. Available: {available}")
 
 

uniface/landmark/models.py

@@ -31,6 +31,8 @@ class Landmark106(BaseLandmarker):
             Defaults to `LandmarkWeights.DEFAULT`.
         input_size (Tuple[int, int]): The resolution (width, height) for the model's
             input. Defaults to (192, 192).
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
 
     Example:
         >>> # Assume 'image' is a loaded image and 'bbox' is a face bounding box
@@ -46,11 +48,13 @@ class Landmark106(BaseLandmarker):
         self,
         model_name: LandmarkWeights = LandmarkWeights.DEFAULT,
         input_size: tuple[int, int] = (192, 192),
+        providers: list[str] | None = None,
     ) -> None:
         Logger.info(f'Initializing Facial Landmark with model={model_name}, input_size={input_size}')
         self.input_size = input_size
         self.input_std = 1.0
         self.input_mean = 0.0
+        self.providers = providers
         self.model_path = verify_model_weights(model_name)
         self._initialize_model()
 
@@ -62,7 +66,7 @@ class Landmark106(BaseLandmarker):
             RuntimeError: If the model fails to load or initialize.
         """
         try:
-            self.session = create_onnx_session(self.model_path)
+            self.session = create_onnx_session(self.model_path, providers=self.providers)
 
             # Get input configuration
             input_metadata = self.session.get_inputs()[0]

uniface/model_store.py

@@ -10,6 +10,7 @@ using SHA-256 checksums for integrity validation.
 
 from __future__ import annotations
 
+from concurrent.futures import ThreadPoolExecutor, as_completed
 from enum import Enum
 import hashlib
 import os
@@ -20,10 +21,50 @@ from tqdm import tqdm
 import uniface.constants as const
 from uniface.log import Logger
 
-__all__ = ['verify_model_weights']
+__all__ = ['download_models', 'get_cache_dir', 'set_cache_dir', 'verify_model_weights']
+
+_DEFAULT_CACHE_DIR = '~/.uniface/models'
+_ENV_KEY = 'UNIFACE_CACHE_DIR'
 
 
-def verify_model_weights(model_name: Enum, root: str = '~/.uniface/models') -> str:
+def get_cache_dir() -> str:
+    """Get the current model cache directory path.
+
+    Resolution order:
+        1. ``UNIFACE_CACHE_DIR`` environment variable (set via :func:`set_cache_dir` or directly).
+        2. Default: ``~/.uniface/models``.
+
+    Returns:
+        Absolute, expanded path to the cache directory.
+
+    Example:
+        >>> from uniface import get_cache_dir
+        >>> print(get_cache_dir())
+        '/home/user/.uniface/models'
+    """
+    return os.path.expanduser(os.environ.get(_ENV_KEY, _DEFAULT_CACHE_DIR))
+
+
+def set_cache_dir(path: str) -> None:
+    """Set the model cache directory.
+
+    This sets the ``UNIFACE_CACHE_DIR`` environment variable so that all
+    subsequent model downloads and lookups use the new path.
+
+    Args:
+        path: Directory path for storing model weights.
+
+    Example:
+        >>> from uniface import set_cache_dir, get_cache_dir
+        >>> set_cache_dir('/data/models')
+        >>> print(get_cache_dir())
+        '/data/models'
+    """
+    os.environ[_ENV_KEY] = path
+    Logger.info(f'Cache directory set to: {path}')
+
+
+def verify_model_weights(model_name: Enum, root: str | None = None) -> str:
     """Ensure model weights are present, downloading and verifying them if necessary.
 
     Given a model identifier from an Enum class (e.g., `RetinaFaceWeights.MNET_V2`),
@@ -34,7 +75,7 @@ def verify_model_weights(model_name: Enum, root: str = '~/.uniface/models') -> s
     Args:
         model_name: Model weight identifier enum (e.g., `RetinaFaceWeights.MNET_V2`).
         root: Directory to store or locate the model weights.
-            Defaults to '~/.uniface/models'.
+            If None, uses the cache directory from :func:`get_cache_dir`.
 
     Returns:
         Absolute path to the verified model weights file.
@@ -51,7 +92,7 @@ def verify_model_weights(model_name: Enum, root: str = '~/.uniface/models') -> s
         '/home/user/.uniface/models/retinaface_mnet_v2.onnx'
     """
 
-    root = os.path.expanduser(root)
+    root = os.path.expanduser(root) if root is not None else get_cache_dir()
     os.makedirs(root, exist_ok=True)
 
     # Keep model_name as enum for dictionary lookup
@@ -121,9 +162,50 @@ def verify_file_hash(file_path: str, expected_hash: str) -> bool:
     return actual_hash == expected_hash
 
 
-if __name__ == '__main__':
-    model_names = [model.value for model in const.RetinaFaceWeights]
+def download_models(model_names: list[Enum], max_workers: int = 4) -> dict[Enum, str]:
+    """Download and verify multiple models concurrently.
 
-    # Download each model in the list
-    for model_name in model_names:
-        model_path = verify_model_weights(model_name)
+    Uses a thread pool to download models in parallel, which is significantly
+    faster when initializing several models at once.
+
+    Args:
+        model_names: List of model weight enum identifiers to download.
+        max_workers: Maximum number of concurrent download threads. Defaults to 4.
+
+    Returns:
+        Mapping of each model enum to its local file path.
+
+    Raises:
+        RuntimeError: If any model download or verification fails.
+
+    Example:
+        >>> from uniface import download_models
+        >>> from uniface.constants import RetinaFaceWeights, ArcFaceWeights
+        >>> paths = download_models([RetinaFaceWeights.MNET_V2, ArcFaceWeights.RESNET])
+    """
+    results: dict[Enum, str] = {}
+    errors: list[str] = []
+
+    with ThreadPoolExecutor(max_workers=max_workers) as executor:
+        future_to_model = {executor.submit(verify_model_weights, name): name for name in model_names}
+
+        for future in as_completed(future_to_model):
+            model = future_to_model[future]
+            try:
+                path = future.result()
+                results[model] = path
+                Logger.info(f'Ready: {model.value} -> {path}')
+            except Exception as e:
+                errors.append(f'{model.value}: {e}')
+                Logger.error(f'Failed to download {model.value}: {e}')
+
+    if errors:
+        raise RuntimeError(f'Failed to download {len(errors)} model(s):\n' + '\n'.join(errors))
+
+    Logger.info(f'All {len(results)} model(s) downloaded and verified')
+    return results
+
+
+if __name__ == '__main__':
+    for model in const.RetinaFaceWeights:
+        model_path = verify_model_weights(model)

uniface/parsing/__init__.py

@@ -4,27 +4,25 @@
 
 from __future__ import annotations
 
-from uniface.constants import ParsingWeights
+from uniface.constants import ParsingWeights, XSegWeights
 
 from .base import BaseFaceParser
 from .bisenet import BiSeNet
+from .xseg import XSeg
 
-__all__ = ['BaseFaceParser', 'BiSeNet', 'create_face_parser']
+__all__ = ['BaseFaceParser', 'BiSeNet', 'XSeg', 'create_face_parser']
 
 
 def create_face_parser(
-    model_name: str | ParsingWeights = ParsingWeights.RESNET18,
+    model_name: str | ParsingWeights | XSegWeights = ParsingWeights.RESNET18,
+    **kwargs,
 ) -> BaseFaceParser:
-    """Factory function to create a face parsing model instance.
-
-    This function provides a convenient way to instantiate face parsing models
-    without directly importing the specific model classes.
+    """Factory function to create a face parsing model.
 
     Args:
-        model_name: The face parsing model to create. Can be either a string
-            or a ParsingWeights enum value. Available options:
-            - 'parsing_resnet18' or ParsingWeights.RESNET18 (default)
-            - 'parsing_resnet34' or ParsingWeights.RESNET34
+        model_name: Model to create. Options: ParsingWeights.RESNET18/RESNET34 (BiSeNet),
+            XSegWeights.DEFAULT (XSeg, requires landmarks).
+        **kwargs: Additional arguments passed to the model constructor.
 
     Returns:
         An instance of the requested face parsing model.
@@ -33,20 +31,32 @@ def create_face_parser(
         ValueError: If the model_name is not recognized.
 
     Example:
-        >>> from uniface.parsing import create_face_parser
-        >>> from uniface.constants import ParsingWeights
         >>> parser = create_face_parser(ParsingWeights.RESNET18)
         >>> mask = parser.parse(face_crop)
     """
+    # Handle XSegWeights
+    if isinstance(model_name, XSegWeights):
+        return XSeg(model_name=model_name, **kwargs)
+
     # Convert string to enum if necessary
     if isinstance(model_name, str):
+        # Try XSegWeights first
+        try:
+            xseg_model = XSegWeights(model_name)
+            return XSeg(model_name=xseg_model, **kwargs)
+        except ValueError:
+            pass
+
+        # Try ParsingWeights
         try:
             model_name = ParsingWeights(model_name)
         except ValueError as e:
-            valid_models = [e.value for e in ParsingWeights]
+            valid_parsing = [m.value for m in ParsingWeights]
+            valid_xseg = [m.value for m in XSegWeights]
+            valid_models = valid_parsing + valid_xseg
             raise ValueError(
                 f"Unknown face parsing model: '{model_name}'. Valid options are: {', '.join(valid_models)}"
             ) from e
 
-    # All parsing models use the same BiSeNet class
-    return BiSeNet(model_name=model_name)
+    # BiSeNet models
+    return BiSeNet(model_name=model_name, **kwargs)

uniface/parsing/base.py

@@ -2,6 +2,8 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from __future__ import annotations
+
 from abc import ABC, abstractmethod
 
 import numpy as np
@@ -69,7 +71,7 @@ class BaseFaceParser(ABC):
         raise NotImplementedError('Subclasses must implement the postprocess method.')
 
     @abstractmethod
-    def parse(self, face_image: np.ndarray) -> np.ndarray:
+    def parse(self, image: np.ndarray, *, landmarks: np.ndarray | None = None) -> np.ndarray:
         """
         Perform end-to-end face parsing on a face image.
 
@@ -77,9 +79,11 @@ class BaseFaceParser(ABC):
         running inference, and postprocessing to return the segmentation mask.
 
         Args:
-            face_image (np.ndarray): A face image in BGR format.
-                                     The face should be roughly centered and
-                                     well-framed within the image.
+            image (np.ndarray): A face image in BGR format.
+                The face should be roughly centered and well-framed within the image.
+            landmarks (np.ndarray | None): Optional 5-point facial landmarks with
+                shape (5, 2). Required by some parsers (e.g., XSeg) for face alignment.
+                Ignored by parsers that do not need landmarks (e.g., BiSeNet).
 
         Returns:
             np.ndarray: Segmentation mask with the same size as input image,
@@ -92,14 +96,15 @@ class BaseFaceParser(ABC):
         """
         raise NotImplementedError('Subclasses must implement the parse method.')
 
-    def __call__(self, face_image: np.ndarray) -> np.ndarray:
+    def __call__(self, image: np.ndarray, *, landmarks: np.ndarray | None = None) -> np.ndarray:
         """
         Provides a convenient, callable shortcut for the `parse` method.
 
         Args:
-            face_image (np.ndarray): A face image in BGR format.
+            image (np.ndarray): A face image in BGR format.
+            landmarks (np.ndarray | None): Optional 5-point facial landmarks.
 
         Returns:
             np.ndarray: Segmentation mask with the same size as input image.
         """
-        return self.parse(face_image)
+        return self.parse(image, landmarks=landmarks)

uniface/parsing/bisenet.py

@@ -2,6 +2,7 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
+from __future__ import annotations
 
 import cv2
 import numpy as np
@@ -37,6 +38,8 @@ class BiSeNet(BaseFaceParser):
             Defaults to `ParsingWeights.RESNET18`.
         input_size (Tuple[int, int]): The resolution (width, height) for the model's
             input. Defaults to (512, 512).
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
 
     Attributes:
         input_size (Tuple[int, int]): Model input dimensions.
@@ -64,12 +67,14 @@ class BiSeNet(BaseFaceParser):
         self,
         model_name: ParsingWeights = ParsingWeights.RESNET18,
         input_size: tuple[int, int] = (512, 512),
+        providers: list[str] | None = None,
     ) -> None:
         Logger.info(f'Initializing BiSeNet with model={model_name}, input_size={input_size}')
 
         self.input_size = input_size
         self.input_mean = np.array([0.485, 0.456, 0.406], dtype=np.float32)
         self.input_std = np.array([0.229, 0.224, 0.225], dtype=np.float32)
+        self.providers = providers
 
         self.model_path = verify_model_weights(model_name)
         self._initialize_model()
@@ -82,7 +87,7 @@ class BiSeNet(BaseFaceParser):
             RuntimeError: If the model fails to load or initialize.
         """
         try:
-            self.session = create_onnx_session(self.model_path)
+            self.session = create_onnx_session(self.model_path, providers=self.providers)
 
             # Get input configuration
             input_cfg = self.session.get_inputs()[0]
@@ -145,21 +150,26 @@ class BiSeNet(BaseFaceParser):
 
         return restored_mask
 
-    def parse(self, face_image: np.ndarray) -> np.ndarray:
+    def parse(self, image: np.ndarray, *, landmarks: np.ndarray | None = None) -> np.ndarray:
         """
         Perform end-to-end face parsing on a face image.
 
         This method orchestrates the full pipeline: preprocessing the input,
         running inference, and postprocessing to return the segmentation mask.
 
+        BiSeNet operates on face crops and does not require landmarks.
+        The ``landmarks`` parameter is accepted for API compatibility but ignored.
+
         Args:
-            face_image (np.ndarray): A face image in BGR format.
+            image (np.ndarray): A face image in BGR format.
+            landmarks (np.ndarray | None): Ignored. Accepted for interface
+                compatibility with :class:`BaseFaceParser`.
 
         Returns:
             np.ndarray: Segmentation mask with the same size as input image.
         """
-        original_size = (face_image.shape[1], face_image.shape[0])  # (width, height)
-        input_tensor = self.preprocess(face_image)
+        original_size = (image.shape[1], image.shape[0])  # (width, height)
+        input_tensor = self.preprocess(image)
         outputs = self.session.run(self.output_names, {self.input_name: input_tensor})
 
         return self.postprocess(outputs[0], original_size)

uniface/parsing/xseg.py

@@ -0,0 +1,250 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from __future__ import annotations
+
+import cv2
+import numpy as np
+
+from uniface.constants import XSegWeights
+from uniface.face_utils import face_alignment
+from uniface.log import Logger
+from uniface.model_store import verify_model_weights
+from uniface.onnx_utils import create_onnx_session
+
+from .base import BaseFaceParser
+
+__all__ = ['XSeg']
+
+
+class XSeg(BaseFaceParser):
+    """
+    XSeg: Face Segmentation Model from DeepFaceLab with ONNX Runtime.
+
+    XSeg outputs a mask for face regions. Unlike BiSeNet which works
+    on bbox crops, XSeg requires 5-point landmarks for face alignment. The model
+    uses NHWC input format and outputs values in [0, 1] range.
+
+    Reference:
+        https://github.com/iperov/DeepFaceLab
+
+    Args:
+        model_name (XSegWeights): The enum specifying the XSeg model to load.
+            Defaults to `XSegWeights.DEFAULT`.
+        align_size (int): Face alignment output size. Must be multiple of 112 or 128.
+            Defaults to 256.
+        blur_sigma (float): Gaussian blur sigma for mask smoothing.
+            0 = raw output (no blur). Defaults to 0.
+        providers (list[str] | None): ONNX Runtime execution providers. If None,
+            auto-detects the best available provider.
+
+    Attributes:
+        align_size (int): Face alignment output size.
+        blur_sigma (float): Blur sigma for post-processing.
+        input_size (tuple[int, int]): Model input dimensions (width, height).
+
+    Example:
+        >>> from uniface.parsing import XSeg
+        >>> from uniface import RetinaFace
+        >>>
+        >>> detector = RetinaFace()
+        >>> parser = XSeg()
+        >>>
+        >>> 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}')
+    """
+
+    def __init__(
+        self,
+        model_name: XSegWeights = XSegWeights.DEFAULT,
+        align_size: int = 256,
+        blur_sigma: float = 0,
+        providers: list[str] | None = None,
+    ) -> None:
+        Logger.info(f'Initializing XSeg with model={model_name}, align_size={align_size}, blur_sigma={blur_sigma}')
+
+        self.align_size = align_size
+        self.blur_sigma = blur_sigma
+        self.providers = providers
+
+        self.model_path = verify_model_weights(model_name)
+        self._initialize_model()
+
+    def _initialize_model(self) -> None:
+        """
+        Initialize the ONNX model from the stored model path.
+
+        Raises:
+            RuntimeError: If the model fails to load or initialize.
+        """
+        try:
+            self.session = create_onnx_session(self.model_path, providers=self.providers)
+
+            # Get input configuration
+            input_cfg = self.session.get_inputs()[0]
+            input_shape = input_cfg.shape
+            self.input_name = input_cfg.name
+
+            # NHWC format: (N, H, W, C)
+            if isinstance(input_shape[1], int) and isinstance(input_shape[2], int):
+                self.input_size = (input_shape[2], input_shape[1])
+            else:
+                self.input_size = (256, 256)
+                Logger.info(f'Dynamic input shape detected, using default: {self.input_size}')
+
+            # Get output configuration
+            outputs = self.session.get_outputs()
+            self.output_names = [output.name for output in outputs]
+
+            Logger.info(f'XSeg initialized with input size {self.input_size}')
+
+        except Exception as e:
+            Logger.error(f"Failed to load XSeg model from '{self.model_path}'", exc_info=True)
+            raise RuntimeError(f'Failed to initialize XSeg model: {e}') from e
+
+    def preprocess(self, face_crop: np.ndarray) -> np.ndarray:
+        """
+        Preprocess an aligned face crop for inference.
+
+        Args:
+            face_crop (np.ndarray): An aligned face crop in BGR format.
+
+        Returns:
+            np.ndarray: Preprocessed image tensor with shape (1, H, W, 3).
+        """
+        # Resize to model input size
+        image = cv2.resize(face_crop, self.input_size, interpolation=cv2.INTER_LINEAR)
+
+        # Normalize to [0, 1]
+        image = image.astype(np.float32) / 255.0
+
+        # Add batch dimension (NHWC format)
+        image = np.expand_dims(image, axis=0)
+
+        return image
+
+    def postprocess(self, outputs: np.ndarray, crop_size: tuple[int, int]) -> np.ndarray:
+        """
+        Postprocess model output to segmentation mask.
+
+        Args:
+            outputs (np.ndarray): Raw model output.
+            crop_size (tuple[int, int]): Size to resize mask to (width, height).
+
+        Returns:
+            np.ndarray: Segmentation mask as float32 in range [0, 1].
+        """
+        # Squeeze and clip to valid range
+        mask = outputs.squeeze().clip(0, 1).astype(np.float32)
+
+        # Resize back to crop size
+        mask = cv2.resize(mask, crop_size, interpolation=cv2.INTER_LINEAR)
+
+        # Apply optional blur and threshold
+        if self.blur_sigma > 0:
+            mask = cv2.GaussianBlur(mask, (0, 0), self.blur_sigma)
+            mask = (mask.clip(0.5, 1) - 0.5) * 2
+
+        return mask
+
+    def parse(self, image: np.ndarray, *, landmarks: np.ndarray | None = None) -> np.ndarray:
+        """
+        Perform face segmentation using 5-point landmarks.
+
+        XSeg requires landmarks for face alignment. Unlike BiSeNet, calling
+        this method without landmarks will raise a :class:`ValueError`.
+
+        Args:
+            image (np.ndarray): Input image in BGR format.
+            landmarks (np.ndarray | None): 5-point facial landmarks with shape (5, 2).
+                Required for XSeg face alignment.
+
+        Returns:
+            np.ndarray: Segmentation mask in original image space, values in [0, 1].
+
+        Raises:
+            ValueError: If landmarks is None or has incorrect shape.
+        """
+        if landmarks is None:
+            raise ValueError(
+                'XSeg requires 5-point facial landmarks for face alignment. Pass landmarks=... with shape (5, 2).'
+            )
+        if landmarks.shape != (5, 2):
+            raise ValueError(f'Landmarks must have shape (5, 2), got {landmarks.shape}')
+
+        # Align face using landmarks
+        face_crop, inverse_matrix = face_alignment(image, landmarks, image_size=self.align_size)
+
+        # Run inference
+        crop_size = (face_crop.shape[1], face_crop.shape[0])
+        input_tensor = self.preprocess(face_crop)
+        outputs = self.session.run(self.output_names, {self.input_name: input_tensor})
+
+        # Postprocess mask
+        mask = self.postprocess(outputs[0], crop_size)
+
+        # Warp mask back to original image space
+        h, w = image.shape[:2]
+        warped_mask = cv2.warpAffine(
+            mask,
+            inverse_matrix,
+            (w, h),
+            flags=cv2.INTER_LINEAR,
+            borderMode=cv2.BORDER_CONSTANT,
+            borderValue=0,
+        )
+
+        return warped_mask
+
+    def parse_aligned(self, face_crop: np.ndarray) -> np.ndarray:
+        """
+        Perform segmentation on an already aligned face crop.
+
+        Args:
+            face_crop (np.ndarray): An aligned face crop in BGR format.
+
+        Returns:
+            np.ndarray: Segmentation mask with same size as input, values in [0, 1].
+        """
+        crop_size = (face_crop.shape[1], face_crop.shape[0])
+
+        # Run inference
+        input_tensor = self.preprocess(face_crop)
+        outputs = self.session.run(self.output_names, {self.input_name: input_tensor})
+
+        return self.postprocess(outputs[0], crop_size)
+
+    def parse_with_inverse(
+        self,
+        image: np.ndarray,
+        landmarks: np.ndarray,
+    ) -> tuple[np.ndarray, np.ndarray, np.ndarray]:
+        """
+        Parse face and return mask with inverse matrix for custom warping.
+
+        Args:
+            image (np.ndarray): Input image in BGR format.
+            landmarks (np.ndarray): 5-point facial landmarks with shape (5, 2).
+
+        Returns:
+            Tuple of (mask, face_crop, inverse_matrix).
+        """
+        if landmarks.shape != (5, 2):
+            raise ValueError(f'Landmarks must have shape (5, 2), got {landmarks.shape}')
+
+        # Align face using landmarks
+        face_crop, inverse_matrix = face_alignment(image, landmarks, image_size=self.align_size)
+
+        # Run inference
+        crop_size = (face_crop.shape[1], face_crop.shape[0])
+        input_tensor = self.preprocess(face_crop)
+        outputs = self.session.run(self.output_names, {self.input_name: input_tensor})
+
+        # Postprocess mask (in crop space)
+        mask = self.postprocess(outputs[0], crop_size)
+
+        return mask, face_crop, inverse_matrix

uniface/privacy/__init__.py

@@ -2,51 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-from __future__ import annotations
+from .blur import BlurFace, EllipticalBlur
 
-import numpy as np
-
-from .blur import BlurFace
-
-
-def anonymize_faces(
-    image: np.ndarray,
-    detector: object | None = None,
-    method: str = 'pixelate',
-    blur_strength: float = 3.0,
-    pixel_blocks: int = 10,
-    confidence_threshold: float = 0.5,
-    **kwargs,
-) -> np.ndarray:
-    """One-line face anonymization with automatic detection.
-
-    Args:
-        image (np.ndarray): Input image (BGR format).
-        detector: Face detector instance. Creates RetinaFace if None.
-        method (str): Blur method name. Defaults to 'pixelate'.
-        blur_strength (float): Blur intensity. Defaults to 3.0.
-        pixel_blocks (int): Block count for pixelate. Defaults to 10.
-        confidence_threshold (float): Detection confidence threshold. Defaults to 0.5.
-        **kwargs: Additional detector arguments.
-
-    Returns:
-        np.ndarray: Anonymized image.
-
-    Example:
-        >>> from uniface.privacy import anonymize_faces
-        >>> anonymized = anonymize_faces(image, method='pixelate')
-    """
-    if detector is None:
-        try:
-            from uniface import RetinaFace
-
-            detector = RetinaFace(confidence_threshold=confidence_threshold, **kwargs)
-        except ImportError as err:
-            raise ImportError('Could not import RetinaFace. Please ensure UniFace is properly installed.') from err
-
-    faces = detector.detect(image)
-    blurrer = BlurFace(method=method, blur_strength=blur_strength, pixel_blocks=pixel_blocks)
-    return blurrer.anonymize(image, faces)
-
-
-__all__ = ['BlurFace', 'anonymize_faces']
+__all__ = ['BlurFace', 'EllipticalBlur']

uniface/recognition/adaface.py

@@ -31,6 +31,8 @@ class AdaFace(BaseRecognizer):
             Defaults to `AdaFaceWeights.IR_18`.
         preprocessing (Optional[PreprocessConfig]): An optional custom preprocessing
             configuration. If None, a default config for AdaFace is used.
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
 
     Example:
         >>> from uniface.recognition import AdaFace
@@ -46,11 +48,12 @@ class AdaFace(BaseRecognizer):
         self,
         model_name: AdaFaceWeights = AdaFaceWeights.IR_18,
         preprocessing: PreprocessConfig | None = None,
+        providers: list[str] | None = None,
     ) -> None:
         if preprocessing is None:
             preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
         model_path = verify_model_weights(model_name)
-        super().__init__(model_path=model_path, preprocessing=preprocessing)
+        super().__init__(model_path=model_path, preprocessing=preprocessing, providers=providers)
 
     def preprocess(self, face_img: np.ndarray) -> np.ndarray:
         """Preprocess the image: resize, normalize, and convert to blob.

uniface/recognition/base.py

@@ -39,19 +39,27 @@ class BaseRecognizer(ABC):
     """
 
     @abstractmethod
-    def __init__(self, model_path: str, preprocessing: PreprocessConfig) -> None:
+    def __init__(
+        self,
+        model_path: str,
+        preprocessing: PreprocessConfig,
+        providers: list[str] | None = None,
+    ) -> None:
         """
         Initializes the model. Subclasses must call this.
 
         Args:
             model_path (str): The direct path to the verified ONNX model.
             preprocessing (PreprocessConfig): The configuration for preprocessing.
+            providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+                the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
         """
         self.input_mean = preprocessing.input_mean
         self.input_std = preprocessing.input_std
         self.input_size = preprocessing.input_size
 
         self.model_path = model_path
+        self.providers = providers
         self._initialize_model()
 
     def _initialize_model(self) -> None:
@@ -63,7 +71,7 @@ class BaseRecognizer(ABC):
         """
         try:
             # Initialize model session with available providers
-            self.session = create_onnx_session(self.model_path)
+            self.session = create_onnx_session(self.model_path, providers=self.providers)
 
             # Extract input configuration
             input_cfg = self.session.get_inputs()[0]

uniface/recognition/models.py

@@ -24,6 +24,8 @@ class ArcFace(BaseRecognizer):
             Defaults to `ArcFaceWeights.MNET`.
         preprocessing (Optional[PreprocessConfig]): An optional custom preprocessing
             configuration. If None, a default config for ArcFace is used.
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
 
     Example:
         >>> from uniface.recognition import ArcFace
@@ -35,11 +37,12 @@ class ArcFace(BaseRecognizer):
         self,
         model_name: ArcFaceWeights = ArcFaceWeights.MNET,
         preprocessing: PreprocessConfig | None = None,
+        providers: list[str] | None = None,
     ) -> None:
         if preprocessing is None:
             preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
         model_path = verify_model_weights(model_name)
-        super().__init__(model_path=model_path, preprocessing=preprocessing)
+        super().__init__(model_path=model_path, preprocessing=preprocessing, providers=providers)
 
 
 class MobileFace(BaseRecognizer):
@@ -54,6 +57,8 @@ class MobileFace(BaseRecognizer):
             Defaults to `MobileFaceWeights.MNET_V2`.
         preprocessing (Optional[PreprocessConfig]): An optional custom preprocessing
             configuration. If None, a default config for MobileFaceNet is used.
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
 
     Example:
         >>> from uniface.recognition import MobileFace
@@ -65,11 +70,12 @@ class MobileFace(BaseRecognizer):
         self,
         model_name: MobileFaceWeights = MobileFaceWeights.MNET_V2,
         preprocessing: PreprocessConfig | None = None,
+        providers: list[str] | None = None,
     ) -> None:
         if preprocessing is None:
             preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
         model_path = verify_model_weights(model_name)
-        super().__init__(model_path=model_path, preprocessing=preprocessing)
+        super().__init__(model_path=model_path, preprocessing=preprocessing, providers=providers)
 
 
 class SphereFace(BaseRecognizer):
@@ -84,6 +90,8 @@ class SphereFace(BaseRecognizer):
             Defaults to `SphereFaceWeights.SPHERE20`.
         preprocessing (Optional[PreprocessConfig]): An optional custom preprocessing
             configuration. If None, a default config for SphereFace is used.
+        providers (list[str] | None): ONNX Runtime execution providers. If None, auto-detects
+            the best available provider. Example: ['CPUExecutionProvider'] to force CPU.
 
     Example:
         >>> from uniface.recognition import SphereFace
@@ -95,9 +103,10 @@ class SphereFace(BaseRecognizer):
         self,
         model_name: SphereFaceWeights = SphereFaceWeights.SPHERE20,
         preprocessing: PreprocessConfig | None = None,
+        providers: list[str] | None = None,
     ) -> None:
         if preprocessing is None:
             preprocessing = PreprocessConfig(input_mean=127.5, input_std=127.5, input_size=(112, 112))
 
         model_path = verify_model_weights(model_name)
-        super().__init__(model_path=model_path, preprocessing=preprocessing)
+        super().__init__(model_path=model_path, preprocessing=preprocessing, providers=providers)