fix: Cleaning up excessive comments

* release: Release UniFace version v3.1.0

* docs: Change classifiers to stable from beta

.gitignore

@@ -1,5 +1,6 @@
 tmp_*
 .vscode/
+*.onnx
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

CONTRIBUTING.md

@@ -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

@@ -9,11 +9,12 @@
 [![PyPI Downloads](https://static.pepy.tech/personalized-badge/uniface?period=total&units=INTERNATIONAL_SYSTEM&left_color=GRAY&right_color=BLUE&left_text=Downloads)](https://pepy.tech/projects/uniface)
 [![UniFace Documentation](https://img.shields.io/badge/Docs-UniFace-blue.svg)](https://yakhyo.github.io/uniface/)
 [![Kaggle Badge](https://img.shields.io/badge/Notebooks-Kaggle?label=Kaggle&color=blue)](https://www.kaggle.com/yakhyokhuja/code)
+[![Discord](https://img.shields.io/badge/Discord-Join%20Server-5865F2?logo=discord&logoColor=white)](https://discord.gg/wdzrjr7R5j)
 
 </div>
 
 <div align="center">
-    <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">
+    <img src="https://raw.githubusercontent.com/yakhyo/uniface/main/.github/logos/uniface_rounded_q80.webp" width="90%" alt="UniFace - All-in-One Open-Source Face Analysis Library">
 </div>
 
 ---
@@ -26,10 +27,12 @@
 
 - **Face Detection** — RetinaFace, SCRFD, YOLOv5-Face, and YOLOv8-Face with 5-point landmarks
 - **Face Recognition** — ArcFace, MobileFace, and SphereFace embeddings
+- **Face Tracking** — Multi-object tracking with [BYTETracker](https://github.com/yakhyo/bytetrack-tracker) for persistent IDs across video frames
 - **Facial Landmarks** — 106-point landmark localization module (separate from 5-point detector landmarks)
 - **Face Parsing** — BiSeNet semantic segmentation (19 classes), XSeg face masking
 - **Gaze Estimation** — Real-time gaze direction with MobileGaze
 - **Attribute Analysis** — Age, gender, race (FairFace), and emotion
+- **Vector Indexing** — FAISS-backed embedding store for fast multi-identity search
 - **Anti-Spoofing** — Face liveness detection with MiniFASNet
 - **Face Anonymization** — 5 blur methods for privacy protection
 - **Hardware Acceleration** — ARM64 (Apple Silicon), CUDA (NVIDIA), CPU
@@ -57,6 +60,12 @@ git clone https://github.com/yakhyo/uniface.git
 cd uniface && pip install -e .
 ```
 
+**FAISS vector indexing**
+
+```bash
+pip install faiss-cpu   # or faiss-gpu for CUDA
+```
+
 **Optional dependencies**
 - Emotion model uses TorchScript and requires `torch`:
   `pip install torch` (choose the correct build for your OS/CUDA)
@@ -71,7 +80,18 @@ Models are downloaded automatically on first use and verified via SHA-256.
 
 Default cache location: `~/.uniface/models`
 
-You can override it with `UNIFACE_CACHE_DIR=/your/cache/path`
+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
+```
 
 ---
 
@@ -79,7 +99,7 @@ You can override it with `UNIFACE_CACHE_DIR=/your/cache/path`
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 detector = RetinaFace()
 
@@ -106,7 +126,9 @@ for face in faces:
 
 ```python
 import cv2
-from uniface import RetinaFace, ArcFace, FaceAnalyzer
+from uniface.analyzer import FaceAnalyzer
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
 
 detector = RetinaFace()
 recognizer = ArcFace()
@@ -128,7 +150,7 @@ for face in faces:
 ## Execution Providers (ONNX Runtime)
 
 ```python
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 
 # Force CPU-only inference
 detector = RetinaFace(providers=["CPUExecutionProvider"])
@@ -150,6 +172,23 @@ Full documentation: https://yakhyo.github.io/uniface/
 | [API Reference](https://yakhyo.github.io/uniface/modules/detection/) | Detailed module documentation |
 | [Tutorials](https://yakhyo.github.io/uniface/recipes/image-pipeline/) | Step-by-step workflow examples |
 | [Guides](https://yakhyo.github.io/uniface/concepts/overview/) | Architecture and design principles |
+| [Datasets](https://yakhyo.github.io/uniface/datasets/) | Training data and evaluation benchmarks |
+
+---
+
+## Datasets
+
+| Task | Training Dataset | Models |
+|------|-----------------|--------|
+| Detection | WIDER FACE | RetinaFace, SCRFD, YOLOv5-Face, YOLOv8-Face |
+| Recognition | MS1MV2 | MobileFace, SphereFace |
+| Recognition | WebFace600K | ArcFace |
+| Recognition | WebFace4M / 12M | AdaFace |
+| Gaze | Gaze360 | MobileGaze |
+| Parsing | CelebAMask-HQ | BiSeNet |
+| Attributes | CelebA, FairFace, AffectNet | AgeGender, FairFace, Emotion |
+
+> See [Datasets documentation](https://yakhyo.github.io/uniface/datasets/) for download links, benchmarks, and details.
 
 ---
 
@@ -166,6 +205,7 @@ Full documentation: https://yakhyo.github.io/uniface/
 | [07_face_anonymization.ipynb](examples/07_face_anonymization.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/07_face_anonymization.ipynb) | Privacy-preserving blur |
 | [08_gaze_estimation.ipynb](examples/08_gaze_estimation.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/08_gaze_estimation.ipynb) | Gaze direction estimation |
 | [09_face_segmentation.ipynb](examples/09_face_segmentation.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/09_face_segmentation.ipynb) | Face segmentation with XSeg |
+| [10_face_vector_store.ipynb](examples/10_face_vector_store.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/10_face_vector_store.ipynb) | FAISS-backed face database |
 
 ---
 
@@ -189,6 +229,7 @@ If you plan commercial use, verify model license compatibility.
 | 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 |
@@ -209,6 +250,7 @@ Contributions are welcome. Please see [CONTRIBUTING.md](CONTRIBUTING.md).
 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
 

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()
@@ -28,7 +28,8 @@ detector = RetinaFace()
 You can specify which execution provider to use by passing the `providers` parameter:
 
 ```python
-from uniface import RetinaFace, ArcFace
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
 
 # Force CPU execution (even if GPU is available)
 detector = RetinaFace(providers=['CPUExecutionProvider'])
@@ -174,7 +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)

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
@@ -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 +28,14 @@ graph TB
         PRIV[Privacy]
     end
 
+    subgraph Tracking
+        TRK[BYTETracker]
+    end
+
+    subgraph Indexing
+        IDX[FAISS Vector Store]
+    end
+
     subgraph Output
         FACE[Face Objects]
     end
@@ -40,9 +48,12 @@ graph TB
     DET --> PARSE
     DET --> SPOOF
     DET --> PRIV
+    DET --> TRK
+    REC --> IDX
     REC --> FACE
     LMK --> FACE
     ATTR --> FACE
+    TRK --> FACE
 ```
 
 ---
@@ -51,12 +62,14 @@ graph TB
 
 ### 1. ONNX-First
 
-All models use ONNX Runtime for inference:
+UniFace runs inference primarily via ONNX Runtime for core components:
 
 - **Cross-platform**: Same models work on macOS, Linux, Windows
 - **Hardware acceleration**: Automatic selection of optimal provider
 - **Production-ready**: No Python-only dependencies for inference
 
+Some optional components (e.g., emotion TorchScript, torchvision NMS) require PyTorch.
+
 ### 2. Minimal Dependencies
 
 Core dependencies are kept minimal:
@@ -74,12 +87,14 @@ 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
@@ -99,17 +114,19 @@ 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
 ├── gaze/           # Gaze estimation
 ├── spoofing/       # Anti-spoofing
 ├── privacy/        # Face anonymization
+├── indexing/       # Vector indexing (FAISS)
 ├── types.py        # Dataclasses (Face, GazeResult, etc.)
 ├── constants.py    # Model weights and URLs
 ├── model_store.py  # Model download and caching
 ├── onnx_utils.py   # ONNX Runtime utilities
-└── visualization.py # Drawing utilities
+└── draw.py         # Drawing utilities
 ```
 
 ---
@@ -120,7 +137,9 @@ 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()
@@ -151,7 +170,10 @@ for face in faces:
 For convenience, `FaceAnalyzer` combines multiple modules:
 
 ```python
-from uniface import FaceAnalyzer, RetinaFace, ArcFace, AgeGender, FairFace
+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()
@@ -176,7 +198,7 @@ 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
@@ -185,6 +207,11 @@ 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/datasets.md

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

docs/index.md

@@ -18,8 +18,9 @@ template: home.html
 [![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: 90%; margin: 1rem 0;">
+<!-- <img src="https://raw.githubusercontent.com/yakhyo/uniface/main/.github/logos/uniface_rounded_q80.webp" alt="UniFace - All-in-One Open-Source Face Analysis Library" style="max-width: 70%; margin: 1rem 0;"> -->
 
 [Get Started](quickstart.md){ .md-button .md-button--primary }
 [View on GitHub](https://github.com/yakhyo/uniface){ .md-button }
@@ -58,6 +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.
@@ -68,31 +74,35 @@ Face liveness detection with MiniFASNet to prevent fraud.
 Face anonymization with 5 blur methods for privacy protection.
 </div>
 
+<div class="feature-card" markdown>
+### :material-database-search: Vector Indexing
+FAISS-backed embedding store for fast multi-identity face search.
+</div>
+
 </div>
 
 ---
 
 ## Installation
 
-=== "Standard"
+UniFace runs inference primarily via **ONNX Runtime**; some optional components (e.g., emotion TorchScript, torchvision NMS) require **PyTorch**.
 
-    ```bash
-    pip install uniface
-    ```
+**Standard**
+```bash
+pip install uniface
+```
 
-=== "GPU (CUDA)"
+**GPU (CUDA)**
+```bash
+pip install uniface[gpu]
+```
 
-    ```bash
-    pip install uniface[gpu]
-    ```
-
-=== "From Source"
-
-    ```bash
-    git clone https://github.com/yakhyo/uniface.git
-    cd uniface
-    pip install -e .
-    ```
+**From Source**
+```bash
+git clone https://github.com/yakhyo/uniface.git
+cd uniface
+pip install -e .
+```
 
 ---
 

docs/installation.md

@@ -55,11 +55,10 @@ pip install uniface[gpu]
 
 **Requirements:**
 
-- CUDA 11.x or 12.x
-- cuDNN 8.x
+- `uniface[gpu]` automatically installs `onnxruntime-gpu`. Requirements depend on the ORT version and execution provider.
 
 !!! info "CUDA Compatibility"
-    See [ONNX Runtime GPU requirements](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html) for detailed compatibility matrix.
+    See the [ONNX Runtime GPU compatibility matrix](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html) for matching CUDA and cuDNN versions.
 
 Verify GPU installation:
 
@@ -71,6 +70,19 @@ print("Available providers:", ort.get_available_providers())
 
 ---
 
+### FAISS Vector Indexing
+
+For fast multi-identity face search using a FAISS index:
+
+```bash
+pip install faiss-cpu   # CPU
+pip install faiss-gpu   # NVIDIA GPU (CUDA)
+```
+
+See the [Indexing module](modules/indexing.md) for usage.
+
+---
+
 ### CPU-Only (All Platforms)
 
 ```bash
@@ -107,12 +119,20 @@ 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 |
 
+**Optional:**
+
+| Package | Install extra | Purpose |
+|---------|---------------|---------|
+| `faiss-cpu` / `faiss-gpu` | `pip install faiss-cpu` | FAISS vector indexing |
+| `onnxruntime-gpu` | `uniface[gpu]` | CUDA acceleration |
+| `torch` | `pip install torch` | Emotion model uses TorchScript |
+| `torchvision` | `pip install torchvision` | Faster NMS for YOLO detectors |
+
 ---
 
 ## Verify Installation
@@ -128,7 +148,7 @@ 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!")
 ```

docs/models.md

@@ -8,7 +8,7 @@ Complete guide to all available models and their performance characteristics.
 
 ### RetinaFace Family
 
-RetinaFace models are trained on the WIDER FACE dataset.
+RetinaFace models are trained on the [WIDER FACE](datasets.md#wider-face) dataset.
 
 | Model Name     | Params | Size  | Easy   | Medium | Hard   |
 | -------------- | ------ | ----- | ------ | ------ | ------ |
@@ -22,13 +22,13 @@ 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>`
+    **Speed**: Benchmark on your own hardware using `python tools/detect.py --source <image>`
 
 ---
 
 ### SCRFD Family
 
-SCRFD (Sample and Computation Redistribution for Efficient Face Detection) models trained on WIDER FACE dataset.
+SCRFD (Sample and Computation Redistribution for Efficient Face Detection) models trained on [WIDER FACE](datasets.md#wider-face) dataset.
 
 | Model Name       | Params | Size  | Easy   | Medium | Hard   |
 | ---------------- | ------ | ----- | ------ | ------ | ------ |
@@ -38,13 +38,13 @@ SCRFD (Sample and Computation Redistribution for Efficient Face Detection) model
 !!! 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>`
+    **Speed**: Benchmark on your own hardware using `python tools/detect.py --source <image>`
 
 ---
 
 ### YOLOv5-Face Family
 
-YOLOv5-Face models provide detection with 5-point facial landmarks, trained on WIDER FACE dataset.
+YOLOv5-Face models provide detection with 5-point facial landmarks, trained on [WIDER FACE](datasets.md#wider-face) dataset.
 
 | Model Name     | Size | Easy   | Medium | Hard   |
 | -------------- | ---- | ------ | ------ | ------ |
@@ -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>`
+    **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.
@@ -93,7 +93,7 @@ Face recognition using adaptive margin based on image quality.
 | `IR_101`  | IR-101   | WebFace12M  | 249 MB | -         | 97.66%    |
 
 !!! info "Training Data & Accuracy"
-    **Dataset**: WebFace4M (4M images) / WebFace12M (12M images)
+    **Dataset**: [WebFace4M / WebFace12M](datasets.md#webface4m--webface12m) (4M / 12M images)
 
     **Accuracy**: IJB-B and IJB-C benchmarks, TAR@FAR=0.01%
 
@@ -113,7 +113,7 @@ Face recognition using additive angular margin loss.
 | `RESNET`  | ResNet50  | 43.6M  | 166MB | 99.83% | 99.33% | 98.23%   | 97.25% |
 
 !!! info "Training Data"
-    **Dataset**: Trained on WebFace600K (600K images)
+    **Dataset**: Trained on [WebFace600K](datasets.md#webface600k) (600K images)
 
     **Accuracy**: IJB-C accuracy reported as TAR@FAR=1e-4
 
@@ -131,7 +131,7 @@ Lightweight face recognition models with MobileNet backbones.
 | `MNET_V3_LARGE` | MobileNetV3-L    | 3.52M  | 10MB | 99.53% | 94.56% | 86.79% | 95.13%   |
 
 !!! info "Training Data"
-    **Dataset**: Trained on MS1M-V2 (5.8M images, 85K identities)
+    **Dataset**: Trained on [MS1MV2](datasets.md#ms1mv2) (5.8M images, 85K identities)
 
     **Accuracy**: Evaluated on LFW, CALFW, CPLFW, and AgeDB-30 benchmarks
 
@@ -147,7 +147,7 @@ Face recognition using angular softmax loss.
 | `SPHERE36` | Sphere36 | 34.6M  | 92MB | 99.72% | 95.64% | 89.92% | 96.83%   |
 
 !!! info "Training Data"
-    **Dataset**: Trained on MS1M-V2 (5.8M images, 85K identities)
+    **Dataset**: Trained on [MS1MV2](datasets.md#ms1mv2) (5.8M images, 85K identities)
 
     **Accuracy**: Evaluated on LFW, CALFW, CPLFW, and AgeDB-30 benchmarks
 
@@ -187,7 +187,7 @@ Facial landmark localization model.
 | `AgeGender` | Age, Gender | 2.1M   | 8MB  |
 
 !!! info "Training Data"
-    **Dataset**: Trained on CelebA
+    **Dataset**: Trained on [CelebA](datasets.md#celeba)
 
 !!! warning "Accuracy Note"
     Accuracy varies by demographic and image quality. Test on your specific use case.
@@ -201,7 +201,7 @@ Facial landmark localization model.
 | `FairFace` | Race, Gender, Age Group | -      | 44MB  |
 
 !!! info "Training Data"
-    **Dataset**: Trained on FairFace dataset with balanced demographics
+    **Dataset**: Trained on [FairFace](datasets.md#fairface) dataset with balanced demographics
 
 !!! tip "Equitable Predictions"
     FairFace provides more equitable predictions across different racial and gender groups.
@@ -219,12 +219,12 @@ 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
 
 !!! info "Training Data"
-    **Dataset**: Trained on AffectNet
+    **Dataset**: Trained on [AffectNet](datasets.md#affectnet)
 
 !!! note "Accuracy Note"
     Emotion detection accuracy depends heavily on facial expression clarity and cultural context.
@@ -235,7 +235,7 @@ Facial landmark localization model.
 
 ### MobileGaze Family
 
-Gaze direction prediction models trained on Gaze360 dataset. Returns pitch (vertical) and yaw (horizontal) angles in radians.
+Gaze direction prediction models trained on [Gaze360](datasets.md#gaze360) dataset. Returns pitch (vertical) and yaw (horizontal) angles in radians.
 
 | Model Name     | Params | Size    | MAE*  |
 | -------------- | ------ | ------- | ----- |
@@ -248,7 +248,7 @@ Gaze direction prediction models trained on Gaze360 dataset. Returns pitch (vert
 *MAE (Mean Absolute Error) in degrees on Gaze360 test set - lower is better
 
 !!! info "Training Data"
-    **Dataset**: Trained on Gaze360 (indoor/outdoor scenes with diverse head poses)
+    **Dataset**: Trained on [Gaze360](datasets.md#gaze360) (indoor/outdoor scenes with diverse head poses)
 
     **Training**: 200 epochs with classification-based approach (binned angles)
 
@@ -269,7 +269,7 @@ BiSeNet (Bilateral Segmentation Network) models for semantic face parsing. Segme
 | `RESNET34`   | 24.1M  | 89.2 MB | 19      |
 
 !!! info "Training Data"
-    **Dataset**: Trained on CelebAMask-HQ
+    **Dataset**: Trained on [CelebAMask-HQ](datasets.md#celebamask-hq)
 
     **Architecture**: BiSeNet with ResNet backbone
 
@@ -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:**
 
@@ -349,10 +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

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()
@@ -120,12 +122,12 @@ 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
 
 detector = RetinaFace()
-emotion = Emotion(model_weights=DDAMFNWeights.AFFECNET7)
+emotion = Emotion(model_name=DDAMFNWeights.AFFECNET7)
 
 faces = detector.detect(image)
 
@@ -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
@@ -169,10 +171,10 @@ from uniface.attribute import Emotion
 from uniface.constants import DDAMFNWeights
 
 # 7-class emotion
-emotion = Emotion(model_weights=DDAMFNWeights.AFFECNET7)
+emotion = Emotion(model_name=DDAMFNWeights.AFFECNET7)
 
 # 8-class emotion
-emotion = Emotion(model_weights=DDAMFNWeights.AFFECNET8)
+emotion = Emotion(model_name=DDAMFNWeights.AFFECNET8)
 ```
 
 ---
@@ -182,7 +184,8 @@ emotion = Emotion(model_weights=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()
@@ -206,7 +209,9 @@ for face in faces:
 ### Using FaceAnalyzer
 
 ```python
-from uniface import FaceAnalyzer, RetinaFace, AgeGender
+from uniface.analyzer import FaceAnalyzer
+from uniface.attribute import AgeGender
+from uniface.detection import RetinaFace
 
 analyzer = FaceAnalyzer(
     RetinaFace(),

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)
@@ -82,7 +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)
@@ -91,7 +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)
@@ -127,7 +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)
@@ -136,7 +136,7 @@ faces = detector.detect(image)
 ### Model Variants
 
 ```python
-from uniface import YOLOv5Face
+from uniface.detection import YOLOv5Face
 from uniface.constants import YOLOv5FaceWeights
 
 # Lightweight
@@ -179,7 +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)
@@ -188,7 +188,7 @@ faces = detector.detect(image)
 ### Model Variants
 
 ```python
-from uniface import YOLOv8Face
+from uniface.detection import YOLOv8Face
 from uniface.constants import YOLOv8FaceWeights
 
 # Lightweight
@@ -225,7 +225,7 @@ detector = YOLOv8Face(
 Create detectors dynamically:
 
 ```python
-from uniface import create_detector
+from uniface.detection import create_detector
 
 detector = create_detector('retinaface')
 # or
@@ -238,22 +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]`:
@@ -276,7 +260,7 @@ for face in faces:
 ## Visualization
 
 ```python
-from uniface.visualization import draw_detections
+from uniface.draw import draw_detections
 
 draw_detections(
     image=image,
@@ -296,7 +280,7 @@ cv2.imwrite("result.jpg", image)
 Benchmark on your hardware:
 
 ```bash
-python tools/detection.py --source image.jpg
+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/indexing.md

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

docs/modules/landmarks.md

@@ -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

@@ -19,7 +19,7 @@ Face parsing segments faces into semantic components or face regions.
 ```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()
@@ -85,9 +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()
@@ -177,23 +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
@@ -234,7 +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)
@@ -257,7 +253,7 @@ XSeg outputs a mask for face regions. Unlike BiSeNet which works on bbox crops,
 
 ```python
 import cv2
-from uniface import RetinaFace
+from uniface.detection import RetinaFace
 from uniface.parsing import XSeg
 
 detector = RetinaFace()
@@ -268,7 +264,7 @@ faces = detector.detect(image)
 
 for face in faces:
     if face.landmarks is not None:
-        mask = parser.parse(image, face.landmarks)
+        mask = parser.parse(image, landmarks=face.landmarks)
         print(f"Mask shape: {mask.shape}")  # (H, W), values in [0, 1]
 ```
 
@@ -296,7 +292,7 @@ parser = XSeg(
 
 ```python
 # Full pipeline: align -> segment -> warp back to original space
-mask = parser.parse(image, landmarks)
+mask = parser.parse(image, landmarks=landmarks)
 
 # For pre-aligned face crops
 mask = parser.parse_aligned(face_crop)
@@ -318,7 +314,7 @@ mask, face_crop, inverse_matrix = parser.parse_with_inverse(image, landmarks)
 ## Factory Function
 
 ```python
-from uniface import create_face_parser
+from uniface.parsing import create_face_parser
 from uniface.constants import ParsingWeights, XSegWeights
 
 # BiSeNet (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
 
@@ -59,7 +42,7 @@ 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 |
@@ -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)
@@ -69,7 +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()
@@ -86,7 +88,7 @@ if faces:
 ### Model Variants
 
 ```python
-from uniface import ArcFace
+from uniface.recognition import ArcFace
 from uniface.constants import ArcFaceWeights
 
 # Lightweight (default)
@@ -118,7 +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)
@@ -127,7 +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
@@ -156,7 +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)
@@ -175,7 +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
@@ -211,7 +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
@@ -223,7 +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()
@@ -282,7 +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()
@@ -128,7 +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()
@@ -253,7 +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

@@ -17,6 +17,7 @@ Run UniFace examples directly in your browser with Google Colab, or download and
 | [Face Anonymization](https://github.com/yakhyo/uniface/blob/main/examples/07_face_anonymization.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/07_face_anonymization.ipynb) | Privacy-preserving blur |
 | [Gaze Estimation](https://github.com/yakhyo/uniface/blob/main/examples/08_gaze_estimation.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/08_gaze_estimation.ipynb) | Gaze direction estimation |
 | [Face Segmentation](https://github.com/yakhyo/uniface/blob/main/examples/09_face_segmentation.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/09_face_segmentation.ipynb) | Face segmentation with XSeg |
+| [Face Vector Store](https://github.com/yakhyo/uniface/blob/main/examples/10_face_vector_store.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yakhyo/uniface/blob/main/examples/10_face_vector_store.ipynb) | FAISS-backed face database |
 
 ---
 

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 +465,18 @@ 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.indexing import FAISS  # pip install faiss-cpu
+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/face-search.md

@@ -1,178 +1,166 @@
 # Face Search
 
-Build a face search system for finding people in images.
+Find and identify people in images and video streams.
 
-!!! note "Work in Progress"
-    This page contains example code patterns. Test thoroughly before using in production.
+UniFace supports two search approaches:
+
+| Approach             | Use case                                         | Tool                    |
+| -------------------- | ------------------------------------------------ | ----------------------- |
+| **Reference search** | "Is this specific person in the video?"          | `tools/search.py`       |
+| **Vector search**    | "Who is this?" against a database of known faces | `tools/faiss_search.py` |
 
 ---
 
-## Basic Face Database
+## Reference Search (single image)
+
+Compare every detected face against a single reference photo:
 
 ```python
+import cv2
 import numpy as np
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+from uniface.face_utils import compute_similarity
+
+detector = RetinaFace()
+recognizer = ArcFace()
+
+ref_image = cv2.imread("reference.jpg")
+ref_faces = detector.detect(ref_image)
+ref_embedding = recognizer.get_normalized_embedding(ref_image, ref_faces[0].landmarks)
+
+query_image = cv2.imread("group_photo.jpg")
+faces = detector.detect(query_image)
+
+for face in faces:
+    embedding = recognizer.get_normalized_embedding(query_image, face.landmarks)
+    sim = compute_similarity(ref_embedding, embedding)
+
+    label = f"Match ({sim:.2f})" if sim > 0.4 else f"Unknown ({sim:.2f})"
+    print(label)
+```
+
+**CLI tool:**
+
+```bash
+python tools/search.py --reference ref.jpg --source video.mp4
+python tools/search.py --reference ref.jpg --source 0  # webcam
+```
+
+---
+
+## Vector Search (FAISS index)
+
+For identifying faces against a database of many known people, use the
+[`FAISS`](../modules/indexing.md) vector store.
+
+!!! info "Install extra"
+`bash
+    pip install faiss-cpu
+    `
+
+### Build an index
+
+Organise face images in person sub-folders:
+
+```
+dataset/
+├── alice/
+│   ├── 001.jpg
+│   └── 002.jpg
+├── bob/
+│   └── 001.jpg
+└── charlie/
+    ├── 001.jpg
+    └── 002.jpg
+```
+
+```python
 import cv2
 from pathlib import Path
-from uniface import RetinaFace, ArcFace
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+from uniface.indexing import FAISS
 
-class FaceDatabase:
-    def __init__(self):
-        self.detector = RetinaFace()
-        self.recognizer = ArcFace()
-        self.embeddings = {}
+detector = RetinaFace()
+recognizer = ArcFace()
+store = FAISS(db_path="./my_index")
 
-    def add_face(self, person_id, image):
-        """Add a face to the database."""
-        faces = self.detector.detect(image)
-        if not faces:
-            raise ValueError(f"No face found for {person_id}")
+for person_dir in sorted(Path("dataset").iterdir()):
+    if not person_dir.is_dir():
+        continue
+    for img_path in person_dir.glob("*.jpg"):
+        image = cv2.imread(str(img_path))
+        faces = detector.detect(image)
+        if faces:
+            emb = recognizer.get_normalized_embedding(image, faces[0].landmarks)
+            store.add(emb, {"person_id": person_dir.name, "source": str(img_path)})
 
-        face = max(faces, key=lambda f: f.confidence)
-        embedding = self.recognizer.get_normalized_embedding(image, face.landmarks)
-        self.embeddings[person_id] = embedding
-        return True
-
-    def search(self, image, threshold=0.6):
-        """Search for faces in an image."""
-        faces = self.detector.detect(image)
-        results = []
-
-        for face in faces:
-            embedding = self.recognizer.get_normalized_embedding(image, face.landmarks)
-
-            best_match = None
-            best_similarity = -1
-
-            for person_id, db_embedding in self.embeddings.items():
-                similarity = np.dot(embedding, db_embedding.T)[0][0]
-                if similarity > best_similarity:
-                    best_similarity = similarity
-                    best_match = person_id
-
-            results.append({
-                'bbox': face.bbox,
-                'match': best_match if best_similarity >= threshold else None,
-                'similarity': best_similarity
-            })
-
-        return results
-
-    def save(self, path):
-        """Save database to file."""
-        np.savez(path, embeddings=dict(self.embeddings))
-
-    def load(self, path):
-        """Load database from file."""
-        data = np.load(path, allow_pickle=True)
-        self.embeddings = data['embeddings'].item()
-
-# Usage
-db = FaceDatabase()
-
-# Add faces
-for image_path in Path("known_faces/").glob("*.jpg"):
-    person_id = image_path.stem
-    image = cv2.imread(str(image_path))
-    try:
-        db.add_face(person_id, image)
-        print(f"Added: {person_id}")
-    except ValueError as e:
-        print(f"Skipped: {e}")
-
-# Save database
-db.save("face_database.npz")
-
-# Search
-query_image = cv2.imread("group_photo.jpg")
-results = db.search(query_image)
-
-for r in results:
-    if r['match']:
-        print(f"Found: {r['match']} (similarity: {r['similarity']:.3f})")
+store.save()
+print(f"Index saved: {store}")
 ```
 
----
+**CLI tool:**
 
-## Visualization
+```bash
+python tools/faiss_search.py build --faces-dir dataset/ --db-path ./my_index
+```
+
+### Search against the index
 
 ```python
 import cv2
+from uniface.detection import RetinaFace
+from uniface.recognition import ArcFace
+from uniface.indexing import FAISS
 
-def visualize_search_results(image, results):
-    """Draw search results on image."""
-    for r in results:
-        x1, y1, x2, y2 = map(int, r['bbox'])
+detector = RetinaFace()
+recognizer = ArcFace()
 
-        if r['match']:
-            color = (0, 255, 0)  # Green for match
-            label = f"{r['match']} ({r['similarity']:.2f})"
-        else:
-            color = (0, 0, 255)  # Red for unknown
-            label = f"Unknown ({r['similarity']:.2f})"
+store = FAISS(db_path="./my_index")
+store.load()
 
-        cv2.rectangle(image, (x1, y1), (x2, y2), color, 2)
-        cv2.putText(image, label, (x1, y1 - 10),
-                    cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
+image = cv2.imread("query.jpg")
+faces = detector.detect(image)
 
-    return image
+for face in faces:
+    embedding = recognizer.get_normalized_embedding(image, face.landmarks)
+    result, similarity = store.search(embedding, threshold=0.4)
 
-# Usage
-results = db.search(image)
-annotated = visualize_search_results(image.copy(), results)
-cv2.imwrite("search_result.jpg", annotated)
+    if result:
+        print(f"Matched: {result['person_id']} ({similarity:.2f})")
+    else:
+        print(f"Unknown ({similarity:.2f})")
 ```
 
----
+**CLI tool:**
 
-## Real-Time Search
+```bash
+python tools/faiss_search.py run --db-path ./my_index --source video.mp4
+python tools/faiss_search.py run --db-path ./my_index --source 0  # webcam
+```
+
+### Manage the index
 
 ```python
-import cv2
+from uniface.indexing import FAISS
 
-def realtime_search(db):
-    """Real-time face search from webcam."""
-    cap = cv2.VideoCapture(0)
+store = FAISS(db_path="./my_index")
+store.load()
 
-    while True:
-        ret, frame = cap.read()
-        if not ret:
-            break
+print(f"Total vectors: {len(store)}")
 
-        results = db.search(frame, threshold=0.5)
+removed = store.remove("person_id", "bob")
+print(f"Removed {removed} entries")
 
-        for r in results:
-            x1, y1, x2, y2 = map(int, r['bbox'])
-
-            if r['match']:
-                color = (0, 255, 0)
-                label = r['match']
-            else:
-                color = (0, 0, 255)
-                label = "Unknown"
-
-            cv2.rectangle(frame, (x1, y1), (x2, y2), color, 2)
-            cv2.putText(frame, label, (x1, y1 - 10),
-                        cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
-
-        cv2.imshow("Face Search", frame)
-
-        if cv2.waitKey(1) & 0xFF == ord('q'):
-            break
-
-    cap.release()
-    cv2.destroyAllWindows()
-
-# Usage
-db = FaceDatabase()
-db.load("face_database.npz")
-realtime_search(db)
+store.save()
 ```
 
 ---
 
 ## See Also
 
+- [Indexing Module](../modules/indexing.md) - Full `FAISS` API reference
 - [Recognition Module](../modules/recognition.md) - Face recognition details
-- [Batch Processing](batch-processing.md) - Process multiple files
 - [Video & Webcam](video-webcam.md) - Real-time processing
 - [Concepts: Thresholds](../concepts/thresholds-calibration.md) - Tuning similarity thresholds

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()
@@ -67,7 +69,10 @@ cv2.imwrite("result.jpg", result_image)
 For convenience, use the built-in `FaceAnalyzer`:
 
 ```python
-from uniface import FaceAnalyzer, RetinaFace, ArcFace, AgeGender
+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
@@ -101,13 +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):
@@ -193,8 +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/01_face_detection.ipynb

@@ -51,7 +51,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.0.0\n"
+      "3.0.0\n"
      ]
     }
    ],
@@ -62,7 +62,7 @@
     "\n",
     "import uniface\n",
     "from uniface.detection import RetinaFace\n",
-    "from uniface.visualization import draw_detections\n",
+    "from uniface.draw import draw_detections\n",
     "\n",
     "print(uniface.__version__)"
    ]
@@ -162,7 +162,7 @@
     "landmarks = [f.landmarks for f in faces]\n",
     "\n",
     "# Draw detections\n",
-    "draw_detections(image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=0.6, fancy_bbox=True)\n",
+    "draw_detections(image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=0.6, corner_bbox=True)\n",
     "\n",
     "# Display result\n",
     "output_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n",
@@ -214,7 +214,7 @@
     "scores = [f.confidence for f in faces]\n",
     "landmarks = [f.landmarks for f in faces]\n",
     "\n",
-    "draw_detections(image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=0.6, fancy_bbox=True)\n",
+    "draw_detections(image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=0.6, corner_bbox=True)\n",
     "\n",
     "output_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n",
     "display.display(Image.fromarray(output_image))"
@@ -261,7 +261,7 @@
     "scores = [f.confidence for f in faces]\n",
     "landmarks = [f.landmarks for f in faces]\n",
     "\n",
-    "draw_detections(image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=0.6, fancy_bbox=True)\n",
+    "draw_detections(image=image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=0.6, corner_bbox=True)\n",
     "\n",
     "output_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n",
     "display.display(Image.fromarray(output_image))"

examples/02_face_alignment.ipynb

@@ -55,7 +55,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.0.0\n"
+      "3.0.0\n"
      ]
     }
    ],
@@ -67,7 +67,7 @@
     "import uniface\n",
     "from uniface.detection import RetinaFace\n",
     "from uniface.face_utils import face_alignment\n",
-    "from uniface.visualization import draw_detections\n",
+    "from uniface.draw import draw_detections\n",
     "\n",
     "print(uniface.__version__)"
    ]
@@ -142,7 +142,7 @@
     "    bboxes = [f.bbox for f in faces]\n",
     "    scores = [f.confidence for f in faces]\n",
     "    landmarks = [f.landmarks for f in faces]\n",
-    "    draw_detections(image=bbox_image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=0.6, fancy_bbox=True)\n",
+    "    draw_detections(image=bbox_image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=0.6, corner_bbox=True)\n",
     "\n",
     "    # Align first detected face (returns aligned image and inverse transform matrix)\n",
     "    first_landmarks = faces[0].landmarks\n",

examples/03_face_verification.ipynb

@@ -44,7 +44,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.0.0\n"
+      "3.0.0\n"
      ]
     }
    ],
@@ -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

@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -49,7 +49,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.0.0\n"
+      "3.0.0\n"
      ]
     }
    ],
@@ -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",
@@ -69,16 +69,7 @@
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "✓ Model loaded (CoreML (Apple Silicon))\n",
-      "✓ Model loaded (CoreML (Apple Silicon))\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "analyzer = FaceAnalyzer(\n",
     "    detector=RetinaFace(confidence_threshold=0.5),\n",

examples/05_face_analyzer.ipynb

@@ -51,7 +51,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2.0.0\n"
+      "3.0.0\n"
      ]
     }
    ],
@@ -60,11 +60,11 @@
     "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",
-    "from uniface.visualization import draw_detections\n",
+    "from uniface.draw import draw_detections\n",
     "\n",
     "print(uniface.__version__)"
    ]
@@ -148,7 +148,7 @@
     "    bboxes = [f.bbox for f in faces]\n",
     "    scores = [f.confidence for f in faces]\n",
     "    landmarks = [f.landmarks for f in faces]\n",
-    "    draw_detections(image=vis_image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=0.5, fancy_bbox=True)\n",
+    "    draw_detections(image=vis_image, bboxes=bboxes, scores=scores, landmarks=landmarks, vis_threshold=0.5, corner_bbox=True)\n",
     "\n",
     "    results.append((image_path, cv2.cvtColor(vis_image, cv2.COLOR_BGR2RGB), faces))"
    ]

examples/06_face_parsing.ipynb

@@ -15,7 +15,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -53,7 +53,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "UniFace version: 2.0.0\n"
+      "UniFace version: 3.0.0\n"
      ]
     }
    ],
@@ -66,7 +66,7 @@
     "import uniface\n",
     "from uniface.parsing import BiSeNet\n",
     "from uniface.constants import ParsingWeights\n",
-    "from uniface.visualization import vis_parsing_maps\n",
+    "from uniface.draw import vis_parsing_maps\n",
     "\n",
     "print(f\"UniFace version: {uniface.__version__}\")"
    ]
@@ -82,15 +82,7 @@
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "✓ Model loaded (CoreML (Apple Silicon))\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# Initialize face parser (uses ResNet18 by default)\n",
     "parser = BiSeNet(model_name=ParsingWeights.RESNET34) # use resnet34 for better accuracy"

examples/08_gaze_estimation.ipynb

@@ -51,7 +51,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "UniFace version: 2.0.0\n"
+      "UniFace version: 3.0.0\n"
      ]
     }
    ],
@@ -65,7 +65,7 @@
     "import uniface\n",
     "from uniface.detection import RetinaFace\n",
     "from uniface.gaze import MobileGaze\n",
-    "from uniface.visualization import draw_gaze\n",
+    "from uniface.draw import draw_gaze\n",
     "\n",
     "print(f\"UniFace version: {uniface.__version__}\")"
    ]
@@ -110,19 +110,19 @@
      "text": [
       "Processing: image0.jpg\n",
       "  Detected 1 face(s)\n",
-      "    Face 1: pitch=-0.0°, yaw=7.1°\n",
+      "    Face 1: pitch=7.1°, yaw=-0.0°\n",
       "Processing: image1.jpg\n",
       "  Detected 1 face(s)\n",
-      "    Face 1: pitch=-3.3°, yaw=-5.6°\n",
+      "    Face 1: pitch=-5.6°, yaw=-3.3°\n",
       "Processing: image2.jpg\n",
       "  Detected 1 face(s)\n",
-      "    Face 1: pitch=-3.9°, yaw=-0.3°\n",
+      "    Face 1: pitch=-0.3°, yaw=-3.9°\n",
       "Processing: image3.jpg\n",
       "  Detected 1 face(s)\n",
-      "    Face 1: pitch=-22.1°, yaw=1.0°\n",
+      "    Face 1: pitch=1.0°, yaw=-22.1°\n",
       "Processing: image4.jpg\n",
       "  Detected 1 face(s)\n",
-      "    Face 1: pitch=2.1°, yaw=5.0°\n",
+      "    Face 1: pitch=5.0°, yaw=2.1°\n",
       "\n",
       "Processed 5 images\n"
      ]

mkdocs.yml

@@ -48,6 +48,7 @@ theme:
     - content.action.edit
     - content.action.view
     - content.tabs.link
+    - announce.dismiss
     - toc.follow
 
   icon:
@@ -134,6 +135,7 @@ nav:
       - Quickstart: quickstart.md
       - Notebooks: notebooks.md
       - Model Zoo: models.md
+      - Datasets: datasets.md
   - Tutorials:
       - Image Pipeline: recipes/image-pipeline.md
       - Video & Webcam: recipes/video-webcam.md
@@ -144,12 +146,14 @@ 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
       - Gaze: modules/gaze.md
       - Anti-Spoofing: modules/spoofing.md
       - Privacy: modules/privacy.md
+      - Indexing: modules/indexing.md
   - Guides:
       - Overview: concepts/overview.md
       - Inputs & Outputs: concepts/inputs-outputs.md

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "uniface"
-version = "2.3.0"
-description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Face Parsing, Gaze Estimation, Age, and Gender Detection"
+version = "3.1.0"
+description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Tracking, Landmark Analysis, Face Parsing, Gaze Estimation, Age, and Gender Detection"
 readme = "README.md"
 license = "MIT"
 authors = [{ name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" }]
@@ -13,6 +13,7 @@ requires-python = ">=3.10,<3.14"
 keywords = [
     "face-detection",
     "face-recognition",
+    "face-tracking",
     "facial-landmarks",
     "face-parsing",
     "face-segmentation",
@@ -28,7 +29,7 @@ keywords = [
 ]
 
 classifiers = [
-    "Development Status :: 4 - Beta",
+    "Development Status :: 5 - Production/Stable",
     "Intended Audience :: Developers",
     "Intended Audience :: Science/Research",
     "Operating System :: OS Independent",
@@ -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

@@ -2,7 +2,6 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Tests for face parsing models (BiSeNet and XSeg)."""
 
 from __future__ import annotations
 
@@ -209,7 +208,7 @@ def test_xseg_parse_with_landmarks():
     )
 
     # Parse
-    mask = parser.parse(image, landmarks)
+    mask = parser.parse(image, landmarks=landmarks)
 
     assert mask.shape == (480, 640)
     assert mask.dtype == np.float32
@@ -226,7 +225,7 @@ def test_xseg_parse_invalid_landmarks():
     invalid_landmarks = np.array([[0, 0], [1, 1], [2, 2]])
 
     with pytest.raises(ValueError, match='Landmarks must have shape'):
-        parser.parse(image, invalid_landmarks)
+        parser.parse(image, landmarks=invalid_landmarks)
 
 
 def test_xseg_parse_with_inverse():

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

@@ -6,27 +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 (BiSeNet) |
+| `parse.py` | Face semantic segmentation (BiSeNet) |
 | `xseg.py` | Face segmentation (XSeg) |
-| `video_detection.py` | Face detection on video files with progress bar |
 | `batch_process.py` | Batch process folder of images |
 | `download_model.py` | Download model weights |
 | `sha256_generate.py` | Generate SHA256 hash for model files |
 
 ## Unified `--source` Pattern
 
-All tools use a unified `--source` argument that accepts:
+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)
@@ -35,26 +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
@@ -65,8 +70,8 @@ python tools/fairface.py --source assets/test.jpg
 python tools/fairface.py --source 0
 
 # Face parsing (BiSeNet)
-python tools/face_parsing.py --source assets/test.jpg
-python tools/face_parsing.py --source 0
+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
@@ -77,22 +82,18 @@ 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/
@@ -122,5 +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
@@ -15,28 +15,14 @@ from __future__ import annotations
 import argparse
 import os
 from pathlib import Path
+import time
 
+from _common import get_source_type
 import cv2
+from tqdm import tqdm
 
 from uniface.detection import SCRFD, RetinaFace, YOLOv5Face, YOLOv8Face
-from uniface.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 +38,7 @@ 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 +46,48 @@ 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
 
+        t0 = time.perf_counter()
         frame_count += 1
         faces = detector.detect(frame)
+        total_faces += len(faces)
 
         bboxes = [f.bbox for f in faces]
         scores = [f.confidence for f in faces]
@@ -99,19 +99,28 @@ 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)
+        inference_fps = 1.0 / max(time.perf_counter() - t0, 1e-9)
+        cv2.putText(frame, f'FPS: {inference_fps:.1f}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 65), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
         out.write(frame)
 
-        # 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):
@@ -123,9 +132,10 @@ def run_camera(detector, camera_id: int = 0, threshold: float = 0.6):
 
     print("Press 'q' to quit")
 
+    prev_time = time.perf_counter()
     while True:
         ret, frame = cap.read()
-        frame = cv2.flip(frame, 1)  # mirror for natural interaction
+        frame = cv2.flip(frame, 1)
         if not ret:
             break
 
@@ -141,10 +151,14 @@ 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)
+        curr_time = time.perf_counter()
+        fps = 1.0 / max(curr_time - prev_time, 1e-9)
+        prev_time = curr_time
+        cv2.putText(frame, f'FPS: {fps:.1f}', (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
+        cv2.putText(frame, f'Faces: {len(faces)}', (10, 65), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
         cv2.imshow('Face Detection', frame)
 
         if cv2.waitKey(1) & 0xFF == ord('q'):
@@ -158,18 +172,24 @@ 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 +198,6 @@ 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 +211,12 @@ 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/faiss_search.py

@@ -0,0 +1,208 @@
+# Copyright 2025-2026 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+"""FAISS index build and multi-identity face search.
+
+Build a vector index from a directory of person sub-folders, then search
+against it in a video or webcam stream.
+
+Usage:
+    python tools/faiss_search.py build --faces-dir dataset/ --db-path ./vector_index
+    python tools/faiss_search.py run   --db-path ./vector_index --source video.mp4
+    python tools/faiss_search.py run   --db-path ./vector_index --source 0  # webcam
+"""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+
+from _common import IMAGE_EXTENSIONS, get_source_type
+import cv2
+
+from uniface import create_detector, create_recognizer
+from uniface.draw import draw_corner_bbox, draw_text_label
+from uniface.indexing import FAISS
+
+
+def _draw_face(image, bbox, text: str, color: tuple[int, int, int]) -> None:
+    x1, y1, x2, y2 = map(int, bbox[:4])
+    thickness = max(round(sum(image.shape[:2]) / 2 * 0.003), 2)
+    font_scale = max(0.4, min(0.7, (y2 - y1) / 200))
+    draw_corner_bbox(image, (x1, y1, x2, y2), color=color, thickness=thickness)
+    draw_text_label(image, text, x1, y1, bg_color=color, font_scale=font_scale)
+
+
+def process_frame(frame, detector, recognizer, store: FAISS, threshold: float = 0.4):
+    faces = detector.detect(frame)
+    if not faces:
+        return frame
+
+    for face in faces:
+        embedding = recognizer.get_normalized_embedding(frame, face.landmarks)
+        result, sim = store.search(embedding, threshold=threshold)
+
+        text = f'{result["person_id"]} ({sim:.2f})' if result else f'Unknown ({sim:.2f})'
+        color = (0, 255, 0) if result else (0, 0, 255)
+        _draw_face(frame, face.bbox, text, color)
+
+    return frame
+
+
+def process_video(detector, recognizer, store: FAISS, video_path: str, save_dir: str, threshold: float = 0.4):
+    cap = cv2.VideoCapture(video_path)
+    if not cap.isOpened():
+        print(f"Error: Cannot open video file '{video_path}'")
+        return
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(video_path).stem}_faiss_search.mp4')
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print(f'Processing video: {video_path} ({total_frames} frames)')
+    frame_count = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        frame_count += 1
+        frame = process_frame(frame, detector, recognizer, store, threshold)
+        out.write(frame)
+
+        if frame_count % 100 == 0:
+            print(f'  Processed {frame_count}/{total_frames} frames...')
+
+    cap.release()
+    out.release()
+    print(f'Done! Output saved: {output_path}')
+
+
+def run_camera(detector, recognizer, store: FAISS, camera_id: int = 0, threshold: float = 0.4):
+    cap = cv2.VideoCapture(camera_id)
+    if not cap.isOpened():
+        print(f'Cannot open camera {camera_id}')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)
+        if not ret:
+            break
+
+        frame = process_frame(frame, detector, recognizer, store, threshold)
+
+        cv2.imshow('Vector Search', frame)
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def build(args: argparse.Namespace) -> None:
+    faces_dir = Path(args.faces_dir)
+    if not faces_dir.is_dir():
+        print(f"Error: '{faces_dir}' is not a directory")
+        return
+
+    detector = create_detector()
+    recognizer = create_recognizer()
+    store = FAISS(db_path=args.db_path)
+
+    persons = sorted(p.name for p in faces_dir.iterdir() if p.is_dir())
+    if not persons:
+        print(f"Error: No sub-folders found in '{faces_dir}'")
+        return
+
+    print(f'Found {len(persons)} persons: {", ".join(persons)}')
+
+    total_added = 0
+    for person_id in persons:
+        person_dir = faces_dir / person_id
+        images = [f for f in person_dir.iterdir() if f.suffix.lower() in IMAGE_EXTENSIONS]
+
+        added = 0
+        for img_path in images:
+            image = cv2.imread(str(img_path))
+            if image is None:
+                print(f'  Warning: Failed to read {img_path}, skipping')
+                continue
+
+            faces = detector.detect(image)
+            if not faces:
+                print(f'  Warning: No face detected in {img_path}, skipping')
+                continue
+
+            embedding = recognizer.get_normalized_embedding(image, faces[0].landmarks)
+            store.add(embedding, {'person_id': person_id, 'source': str(img_path)})
+            added += 1
+
+        total_added += added
+        if added:
+            print(f'  {person_id}: {added} embeddings added')
+        else:
+            print(f'  {person_id}: no valid faces found')
+
+    store.save()
+    print(f'\nIndex saved to {args.db_path} ({total_added} vectors, {len(persons)} persons)')
+
+
+def run(args: argparse.Namespace) -> None:
+    detector = create_detector()
+    recognizer = create_recognizer()
+
+    store = FAISS(db_path=args.db_path)
+    if not store.load():
+        print(f"Error: No index found at '{args.db_path}'")
+        return
+    print(f'Loaded FAISS index: {store}')
+
+    source_type = get_source_type(args.source)
+
+    if source_type == 'camera':
+        run_camera(detector, recognizer, store, int(args.source), args.threshold)
+    elif source_type == 'video':
+        if not os.path.exists(args.source):
+            print(f'Error: Video not found: {args.source}')
+            return
+        process_video(detector, recognizer, store, args.source, args.save_dir, args.threshold)
+    else:
+        print(f"Error: Source must be a video file or camera ID, not '{args.source}'")
+
+
+def main():
+    parser = argparse.ArgumentParser(description='FAISS vector search')
+    sub = parser.add_subparsers(dest='command', required=True)
+
+    build_p = sub.add_parser('build', help='Build a FAISS index from person sub-folders')
+    build_p.add_argument('--faces-dir', type=str, required=True, help='Directory with person sub-folders')
+    build_p.add_argument('--db-path', type=str, default='./vector_index', help='Where to save the index')
+
+    run_p = sub.add_parser('run', help='Search faces against a FAISS index')
+    run_p.add_argument('--db-path', type=str, required=True, help='Path to saved FAISS index')
+    run_p.add_argument('--source', type=str, required=True, help='Video path or camera ID')
+    run_p.add_argument('--threshold', type=float, default=0.4, help='Similarity threshold')
+    run_p.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
+
+    args = parser.parse_args()
+
+    if args.command == 'build':
+        build(args)
+    elif args.command == 'run':
+        run(args)
+
+
+if __name__ == '__main__':
+    main()

tools/gaze.py

@@ -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

@@ -2,11 +2,14 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo
 
-"""Real-time face search: match faces against a reference image.
+"""Single-reference face search on video or webcam.
+
+Given a reference face image, detects faces in the source and shows
+whether each face matches the reference.
 
 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 ref.jpg --source video.mp4
+    python tools/search.py --reference ref.jpg --source 0  # webcam
 """
 
 from __future__ import annotations
@@ -15,43 +18,16 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 import numpy as np
 
-from uniface.detection import SCRFD, RetinaFace
+from uniface import create_detector, create_recognizer
+from uniface.draw import draw_corner_bbox, draw_text_label
 from uniface.face_utils import compute_similarity
-from uniface.recognition import ArcFace, MobileFace, SphereFace
-
-IMAGE_EXTENSIONS = {'.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff'}
-VIDEO_EXTENSIONS = {'.mp4', '.avi', '.mov', '.mkv', '.webm', '.flv'}
-
-
-def get_source_type(source: str) -> str:
-    """Determine if source is image, video, or camera."""
-    if source.isdigit():
-        return 'camera'
-    path = Path(source)
-    suffix = path.suffix.lower()
-    if suffix in IMAGE_EXTENSIONS:
-        return 'image'
-    elif suffix in VIDEO_EXTENSIONS:
-        return 'video'
-    else:
-        return 'unknown'
-
-
-def get_recognizer(name: str):
-    """Get recognizer by name."""
-    if name == 'arcface':
-        return ArcFace()
-    elif name == 'mobileface':
-        return MobileFace()
-    else:
-        return SphereFace()
 
 
 def extract_reference_embedding(detector, recognizer, image_path: str) -> np.ndarray:
-    """Extract embedding from reference image."""
     image = cv2.imread(image_path)
     if image is None:
         raise RuntimeError(f'Failed to load image: {image_path}')
@@ -60,33 +36,34 @@ def extract_reference_embedding(detector, recognizer, image_path: str) -> np.nda
     if not faces:
         raise RuntimeError('No faces found in reference image.')
 
-    landmarks = faces[0].landmarks
-    return recognizer.get_normalized_embedding(image, landmarks)
+    return recognizer.get_normalized_embedding(image, faces[0].landmarks)
+
+
+def _draw_face(image, bbox, text: str, color: tuple[int, int, int]) -> None:
+    x1, y1, x2, y2 = map(int, bbox[:4])
+    thickness = max(round(sum(image.shape[:2]) / 2 * 0.003), 2)
+    font_scale = max(0.4, min(0.7, (y2 - y1) / 200))
+    draw_corner_bbox(image, (x1, y1, x2, y2), color=color, thickness=thickness)
+    draw_text_label(image, text, x1, y1, bg_color=color, font_scale=font_scale)
 
 
 def process_frame(frame, detector, recognizer, ref_embedding: np.ndarray, threshold: float = 0.4):
-    """Process a single frame and return annotated frame."""
     faces = detector.detect(frame)
 
     for face in faces:
-        bbox = face.bbox
-        landmarks = face.landmarks
-        x1, y1, x2, y2 = map(int, bbox)
-
-        embedding = recognizer.get_normalized_embedding(frame, landmarks)
+        embedding = recognizer.get_normalized_embedding(frame, face.landmarks)
         sim = compute_similarity(ref_embedding, embedding)
 
-        label = f'Match ({sim:.2f})' if sim > threshold else f'Unknown ({sim:.2f})'
+        text = f'Match ({sim:.2f})' if sim > threshold else f'Unknown ({sim:.2f})'
         color = (0, 255, 0) if sim > threshold else (0, 0, 255)
-
-        cv2.rectangle(frame, (x1, y1), (x2, y2), color, 2)
-        cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
+        _draw_face(frame, face.bbox, text, color)
 
     return frame
 
 
-def process_video(detector, recognizer, ref_embedding: np.ndarray, video_path: str, save_dir: str, threshold: float):
-    """Process a video file."""
+def process_video(
+    detector, recognizer, video_path: str, save_dir: str, ref_embedding: np.ndarray, threshold: float = 0.4
+):
     cap = cv2.VideoCapture(video_path)
     if not cap.isOpened():
         print(f"Error: Cannot open video file '{video_path}'")
@@ -123,7 +100,6 @@ def process_video(detector, recognizer, ref_embedding: np.ndarray, video_path: s
 
 
 def run_camera(detector, recognizer, ref_embedding: np.ndarray, camera_id: int = 0, threshold: float = 0.4):
-    """Run real-time face search on webcam."""
     cap = cv2.VideoCapture(camera_id)
     if not cap.isOpened():
         print(f'Cannot open camera {camera_id}')
@@ -139,7 +115,7 @@ def run_camera(detector, recognizer, ref_embedding: np.ndarray, camera_id: int =
 
         frame = process_frame(frame, detector, recognizer, ref_embedding, threshold)
 
-        cv2.imshow('Face Recognition', frame)
+        cv2.imshow('Face Search', frame)
         if cv2.waitKey(1) & 0xFF == ord('q'):
             break
 
@@ -148,17 +124,10 @@ def run_camera(detector, recognizer, ref_embedding: np.ndarray, camera_id: int =
 
 
 def main():
-    parser = argparse.ArgumentParser(description='Face search using a reference image')
+    parser = argparse.ArgumentParser(description='Single-reference face search')
     parser.add_argument('--reference', type=str, required=True, help='Reference face image')
-    parser.add_argument('--source', type=str, required=True, help='Video path or camera ID (0, 1, ...)')
-    parser.add_argument('--threshold', type=float, default=0.4, help='Match threshold')
-    parser.add_argument('--detector', type=str, default='scrfd', choices=['retinaface', 'scrfd'])
-    parser.add_argument(
-        '--recognizer',
-        type=str,
-        default='arcface',
-        choices=['arcface', 'mobileface', 'sphereface'],
-    )
+    parser.add_argument('--source', type=str, required=True, help='Video path or camera ID')
+    parser.add_argument('--threshold', type=float, default=0.4, help='Similarity threshold')
     parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory')
     args = parser.parse_args()
 
@@ -166,8 +135,8 @@ def main():
         print(f'Error: Reference image not found: {args.reference}')
         return
 
-    detector = RetinaFace() if args.detector == 'retinaface' else SCRFD()
-    recognizer = get_recognizer(args.recognizer)
+    detector = create_detector()
+    recognizer = create_recognizer()
 
     print(f'Loading reference: {args.reference}')
     ref_embedding = extract_reference_embedding(detector, recognizer, args.reference)
@@ -180,10 +149,9 @@ def main():
         if not os.path.exists(args.source):
             print(f'Error: Video not found: {args.source}')
             return
-        process_video(detector, recognizer, ref_embedding, args.source, args.save_dir, args.threshold)
+        process_video(detector, recognizer, args.source, args.save_dir, ref_embedding, args.threshold)
     else:
         print(f"Error: Source must be a video file or camera ID, not '{args.source}'")
-        print('Supported formats: videos (.mp4, .avi, ...) or camera ID (0, 1, ...)')
 
 
 if __name__ == '__main__':

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

@@ -16,27 +16,12 @@ import argparse
 import os
 from pathlib import Path
 
+from _common import get_source_type
 import cv2
 import numpy as np
 
-from uniface import RetinaFace, XSeg
-
-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 RetinaFace
+from uniface.parsing import XSeg
 
 
 def apply_mask_visualization(image: np.ndarray, mask: np.ndarray, alpha: float = 0.5) -> np.ndarray:
@@ -74,7 +59,7 @@ def process_image(
             print(f'  Face {i + 1}: skipped (no landmarks)')
             continue
 
-        mask = parser.parse(image, face.landmarks)
+        mask = parser.parse(image, landmarks=face.landmarks)
         full_mask = np.maximum(full_mask, mask)
         print(f'  Face {i + 1}: done')
 
@@ -136,7 +121,7 @@ def process_video(
         for face in faces:
             if face.landmarks is None:
                 continue
-            mask = parser.parse(frame, face.landmarks)
+            mask = parser.parse(frame, landmarks=face.landmarks)
             full_mask = np.maximum(full_mask, mask)
 
         # Apply visualization
@@ -184,7 +169,7 @@ def run_camera(
         for face in faces:
             if face.landmarks is None:
                 continue
-            mask = parser.parse(frame, face.landmarks)
+            mask = parser.parse(frame, landmarks=face.landmarks)
             full_mask = np.maximum(full_mask, mask)
 
         # Apply visualization

uniface-cpp/.clang-format

@@ -0,0 +1,180 @@
+---
+# Modern C++ style based on Google with enhancements
+Language: Cpp
+Standard: c++17
+
+BasedOnStyle: Google
+ColumnLimit: 100
+IndentWidth: 4
+TabWidth: 4
+UseTab: Never
+
+# Access modifiers
+AccessModifierOffset: -4
+IndentAccessModifiers: false
+
+# Alignment
+AlignAfterOpenBracket: BlockIndent
+AlignArrayOfStructures: Right
+AlignConsecutiveAssignments:
+  Enabled: false
+AlignConsecutiveBitFields:
+  Enabled: true
+AlignConsecutiveDeclarations:
+  Enabled: false
+AlignConsecutiveMacros:
+  Enabled: true
+AlignEscapedNewlines: Left
+AlignOperands: AlignAfterOperator
+AlignTrailingComments:
+  Kind: Always
+  OverEmptyLines: 1
+
+# Arguments and parameters
+AllowAllArgumentsOnNextLine: true
+AllowAllParametersOfDeclarationOnNextLine: true
+BinPackArguments: false
+BinPackParameters: false
+
+# Short forms
+AllowShortBlocksOnASingleLine: Empty
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortEnumsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: Inline
+AllowShortIfStatementsOnASingleLine: Never
+AllowShortLambdasOnASingleLine: Inline
+AllowShortLoopsOnASingleLine: false
+
+# Break behavior
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: true
+AlwaysBreakTemplateDeclarations: Yes
+BreakAfterAttributes: Leave
+BreakBeforeBinaryOperators: None
+BreakBeforeBraces: Attach
+BreakBeforeConceptDeclarations: Always
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializers: BeforeComma
+BreakInheritanceList: BeforeComma
+BreakStringLiterals: true
+
+# Braces
+InsertBraces: false
+RemoveBracesLLVM: false
+
+# Constructors
+PackConstructorInitializers: CurrentLine
+ConstructorInitializerIndentWidth: 4
+
+# Empty lines
+EmptyLineAfterAccessModifier: Never
+EmptyLineBeforeAccessModifier: LogicalBlock
+KeepEmptyLinesAtTheStartOfBlocks: false
+MaxEmptyLinesToKeep: 1
+SeparateDefinitionBlocks: Always
+
+# Includes
+IncludeBlocks: Regroup
+IncludeCategories:
+  # Main header (same name as source file)
+  - Regex: '^"([a-zA-Z0-9_]+)\.(h|hpp)"$'
+    Priority: 1
+    SortPriority: 1
+    CaseSensitive: true
+  # Project headers
+  - Regex: '^".*"$'
+    Priority: 2
+    SortPriority: 2
+  # C system headers
+  - Regex: '^<(assert|complex|ctype|errno|fenv|float|inttypes|iso646|limits|locale|math|setjmp|signal|stdalign|stdarg|stdatomic|stdbool|stddef|stdint|stdio|stdlib|stdnoreturn|string|tgmath|threads|time|uchar|wchar|wctype)\.h>$'
+    Priority: 3
+    SortPriority: 3
+  # C++ standard library
+  - Regex: '^<[a-z_]+>$'
+    Priority: 4
+    SortPriority: 4
+  # External libraries
+  - Regex: '^<.*>$'
+    Priority: 5
+    SortPriority: 5
+SortIncludes: CaseSensitive
+
+# Indentation
+IndentCaseBlocks: false
+IndentCaseLabels: true
+IndentExternBlock: NoIndent
+IndentGotoLabels: false
+IndentPPDirectives: AfterHash
+IndentRequiresClause: true
+IndentWrappedFunctionNames: false
+
+# Lambdas
+LambdaBodyIndentation: Signature
+
+# Namespaces
+CompactNamespaces: false
+FixNamespaceComments: true
+NamespaceIndentation: None
+ShortNamespaceLines: 0
+
+# Penalties (guide formatting decisions)
+PenaltyBreakAssignment: 25
+PenaltyBreakBeforeFirstCallParameter: 19
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakOpenParenthesis: 0
+PenaltyBreakString: 1000
+PenaltyBreakTemplateDeclaration: 10
+PenaltyExcessCharacter: 1000000
+PenaltyIndentedWhitespace: 0
+PenaltyReturnTypeOnItsOwnLine: 200
+
+# Pointers and references
+DerivePointerAlignment: false
+PointerAlignment: Left
+ReferenceAlignment: Pointer
+QualifierAlignment: Leave
+
+# Requires clause (C++20 concepts)
+RequiresClausePosition: OwnLine
+RequiresExpressionIndentation: OuterScope
+
+# Spacing
+BitFieldColonSpacing: Both
+SpaceAfterCStyleCast: false
+SpaceAfterLogicalNot: false
+SpaceAfterTemplateKeyword: true
+SpaceAroundPointerQualifiers: Default
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCaseColon: false
+SpaceBeforeCpp11BracedList: false
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeParens: ControlStatements
+SpaceBeforeRangeBasedForLoopColon: true
+SpaceBeforeSquareBrackets: false
+SpaceInEmptyBlock: false
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 2
+SpacesInAngles: Never
+SpacesInCStyleCastParentheses: false
+SpacesInConditionalStatement: false
+SpacesInContainerLiterals: false
+SpacesInLineCommentPrefix:
+  Minimum: 1
+  Maximum: -1
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+
+# Other
+Cpp11BracedListStyle: true
+InsertNewlineAtEOF: true
+InsertTrailingCommas: None
+IntegerLiteralSeparator:
+  Binary: 4
+  Decimal: 3
+  Hex: 4
+ReflowComments: true
+RemoveSemicolon: false
+SortUsingDeclarations: LexicographicNumeric
+...

uniface-cpp/CMakeLists.txt

@@ -0,0 +1,51 @@
+cmake_minimum_required(VERSION 3.14)
+
+project(uniface
+    VERSION 1.0.0
+    DESCRIPTION "Uniface C++ face analysis library"
+    LANGUAGES CXX
+)
+
+# Options
+option(UNIFACE_BUILD_EXAMPLES "Build example programs" ON)
+
+# C++ standard
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+set(CMAKE_CXX_EXTENSIONS OFF)
+set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
+
+# Compiler warnings
+if(CMAKE_CXX_COMPILER_ID MATCHES "GNU|Clang")
+    add_compile_options(-Wall -Wextra -Wpedantic)
+elseif(MSVC)
+    add_compile_options(/W4)
+endif()
+
+# Find dependencies
+find_package(OpenCV REQUIRED COMPONENTS core imgproc dnn calib3d)
+
+# Library
+add_library(uniface
+    src/utils.cpp
+    src/detector.cpp
+    src/recognizer.cpp
+    src/landmarker.cpp
+    src/analyzer.cpp
+)
+
+target_include_directories(uniface
+    PUBLIC
+        $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
+        $<INSTALL_INTERFACE:include>
+)
+
+target_link_libraries(uniface
+    PUBLIC
+        ${OpenCV_LIBS}
+)
+
+# Examples
+if(UNIFACE_BUILD_EXAMPLES)
+    add_subdirectory(examples)
+endif()

uniface-cpp/README.md

@@ -0,0 +1,69 @@
+# Uniface C++
+
+C++ implementation of the Uniface face analysis library.
+
+## Features
+
+- **Face Detection** - RetinaFace detector with 5-point landmarks
+
+## Requirements
+
+- C++17 compiler
+- CMake 3.14+
+- OpenCV 4.x
+
+## Build
+
+```bash
+mkdir build && cd build
+cmake ..
+make -j$(nproc)
+```
+
+## Usage
+
+### Image Detection
+
+```bash
+./examples/detect <model_path> <image_path>
+```
+
+### Webcam Demo
+
+```bash
+./examples/webcam <model_path> [camera_id]
+```
+
+### Code Example
+
+```cpp
+#include <uniface/uniface.hpp>
+#include <opencv2/highgui.hpp>
+
+int main() {
+    uniface::RetinaFace detector("retinaface.onnx");
+
+    cv::Mat image = cv::imread("photo.jpg");
+    auto faces = detector.detect(image);
+
+    for (const auto& face : faces) {
+        cv::rectangle(image, face.bbox, cv::Scalar(0, 255, 0), 2);
+    }
+
+    cv::imwrite("result.jpg", image);
+    return 0;
+}
+```
+
+## Models
+
+Download models from the main uniface repository or use:
+
+```bash
+# RetinaFace MobileNet V2
+wget https://github.com/your-repo/uniface/releases/download/v1.0/retinaface_mv2.onnx -P models/
+```
+
+## License
+
+Same license as the main uniface project.

uniface-cpp/examples/CMakeLists.txt

@@ -0,0 +1,23 @@
+# Examples
+
+find_package(OpenCV REQUIRED COMPONENTS highgui imgcodecs videoio)
+
+# Image detection example
+add_executable(detect detect.cpp)
+target_link_libraries(detect PRIVATE uniface ${OpenCV_LIBS})
+
+# Face recognition example
+add_executable(recognize recognize.cpp)
+target_link_libraries(recognize PRIVATE uniface ${OpenCV_LIBS})
+
+# Facial landmarks example
+add_executable(landmarks landmarks.cpp)
+target_link_libraries(landmarks PRIVATE uniface ${OpenCV_LIBS})
+
+# Face analyzer example
+add_executable(analyzer analyzer.cpp)
+target_link_libraries(analyzer PRIVATE uniface ${OpenCV_LIBS})
+
+# Webcam example
+add_executable(webcam webcam.cpp)
+target_link_libraries(webcam PRIVATE uniface ${OpenCV_LIBS})

uniface-cpp/examples/analyzer.cpp

@@ -0,0 +1,113 @@
+#include <iomanip>
+#include <iostream>
+
+#include <opencv2/highgui.hpp>
+#include <opencv2/imgproc.hpp>
+#include <uniface/uniface.hpp>
+
+int main(int argc, char** argv) {
+    if (argc < 3) {
+        std::cout << "Usage: " << argv[0]
+                  << " <detector_model> <image_path> [recognizer_model] [landmark_model]"
+                  << std::endl;
+        std::cout << "\nAnalyzes faces in an image using available models." << std::endl;
+        std::cout << "  - detector_model: Required. Path to face detector ONNX model." << std::endl;
+        std::cout << "  - recognizer_model: Optional. Path to face recognizer ONNX model."
+                  << std::endl;
+        std::cout << "  - landmark_model: Optional. Path to 106-point landmark ONNX model."
+                  << std::endl;
+        return 1;
+    }
+
+    const std::string detector_path = argv[1];
+    const std::string image_path = argv[2];
+    const std::string recognizer_path = (argc > 3) ? argv[3] : "";
+    const std::string landmark_path = (argc > 4) ? argv[4] : "";
+
+    try {
+        // Create analyzer and load components
+        uniface::FaceAnalyzer analyzer;
+
+        std::cout << "Loading detector: " << detector_path << std::endl;
+        analyzer.loadDetector(detector_path);
+
+        if (!recognizer_path.empty()) {
+            std::cout << "Loading recognizer: " << recognizer_path << std::endl;
+            analyzer.loadRecognizer(recognizer_path);
+        }
+
+        if (!landmark_path.empty()) {
+            std::cout << "Loading landmarker: " << landmark_path << std::endl;
+            analyzer.loadLandmarker(landmark_path);
+        }
+
+        // Load image
+        cv::Mat image = cv::imread(image_path);
+        if (image.empty()) {
+            std::cerr << "Failed to load image: " << image_path << std::endl;
+            return 1;
+        }
+
+        std::cout << "\nAnalyzing image..." << std::endl;
+
+        // Analyze faces
+        auto results = analyzer.analyze(image);
+
+        std::cout << "Found " << results.size() << " face(s)\n" << std::endl;
+
+        // Process each face
+        for (size_t i = 0; i < results.size(); ++i) {
+            const auto& result = results[i];
+
+            std::cout << "Face " << (i + 1) << ":" << std::endl;
+            std::cout << "  BBox: [" << result.face.bbox.x << ", " << result.face.bbox.y << ", "
+                      << result.face.bbox.width << ", " << result.face.bbox.height << "]"
+                      << std::endl;
+            std::cout << std::fixed << std::setprecision(3);
+            std::cout << "  Confidence: " << result.face.confidence << std::endl;
+
+            // Draw bounding box
+            cv::rectangle(image, result.face.bbox, cv::Scalar(0, 255, 0), 2);
+
+            // Draw 5-point landmarks from detector
+            for (const auto& pt : result.face.landmarks) {
+                cv::circle(image, pt, 3, cv::Scalar(0, 0, 255), -1);
+            }
+
+            // If 106-point landmarks available
+            if (result.landmarks) {
+                std::cout << "  Landmarks: 106 points detected" << std::endl;
+                for (const auto& pt : result.landmarks->points) {
+                    cv::circle(image, pt, 1, cv::Scalar(0, 255, 255), -1);
+                }
+            }
+
+            // If embedding available
+            if (result.embedding) {
+                // Show first few values of embedding
+                std::cout << "  Embedding: [";
+                for (size_t j = 0; j < 5; ++j) {
+                    std::cout << (*result.embedding)[j];
+                    if (j < 4)
+                        std::cout << ", ";
+                }
+                std::cout << ", ... ] (512-dim)" << std::endl;
+            }
+
+            std::cout << std::endl;
+        }
+
+        // Save result
+        cv::imwrite("analyzer_result.jpg", image);
+        std::cout << "Saved result to analyzer_result.jpg" << std::endl;
+
+    } catch (const cv::Exception& e) {
+        std::cerr << "OpenCV Error: " << e.what() << std::endl;
+        return 1;
+    } catch (const std::exception& e) {
+        std::cerr << "Error: " << e.what() << std::endl;
+        return 1;
+    }
+
+    return 0;
+}

uniface-cpp/examples/detect.cpp

@@ -0,0 +1,48 @@
+#include <iostream>
+
+#include <opencv2/highgui.hpp>
+#include <opencv2/imgproc.hpp>
+#include <uniface/uniface.hpp>
+
+int main(int argc, char** argv) {
+    if (argc < 3) {
+        std::cout << "Usage: " << argv[0] << " <model_path> <image_path>" << std::endl;
+        return 1;
+    }
+
+    const std::string model_path = argv[1];
+    const std::string image_path = argv[2];
+
+    try {
+        uniface::RetinaFace detector(model_path);
+
+        cv::Mat image = cv::imread(image_path);
+        if (image.empty()) {
+            std::cerr << "Failed to load image: " << image_path << std::endl;
+            return 1;
+        }
+
+        const auto faces = detector.detect(image);
+        std::cout << "Detected " << faces.size() << " faces." << std::endl;
+
+        // Draw results
+        for (const auto& face : faces) {
+            cv::rectangle(image, face.bbox, cv::Scalar(0, 255, 0), 2);
+            for (const auto& pt : face.landmarks) {
+                cv::circle(image, pt, 2, cv::Scalar(0, 0, 255), -1);
+            }
+        }
+
+        cv::imwrite("result.jpg", image);
+        std::cout << "Saved result to result.jpg" << std::endl;
+
+    } catch (const cv::Exception& e) {
+        std::cerr << "OpenCV Error: " << e.what() << std::endl;
+        return 1;
+    } catch (const std::exception& e) {
+        std::cerr << "Error: " << e.what() << std::endl;
+        return 1;
+    }
+
+    return 0;
+}

uniface-cpp/examples/landmarks.cpp

@@ -0,0 +1,66 @@
+#include <iostream>
+
+#include <opencv2/highgui.hpp>
+#include <opencv2/imgproc.hpp>
+#include <uniface/uniface.hpp>
+
+int main(int argc, char** argv) {
+    if (argc < 4) {
+        std::cout << "Usage: " << argv[0] << " <detector_model> <landmark_model> <image_path>"
+                  << std::endl;
+        std::cout << "\nDetects 106-point facial landmarks and saves visualization." << std::endl;
+        return 1;
+    }
+
+    const std::string detector_path = argv[1];
+    const std::string landmark_path = argv[2];
+    const std::string image_path = argv[3];
+
+    try {
+        // Load models
+        uniface::RetinaFace detector(detector_path);
+        uniface::Landmark106 landmarker(landmark_path);
+
+        // Load image
+        cv::Mat image = cv::imread(image_path);
+        if (image.empty()) {
+            std::cerr << "Failed to load image: " << image_path << std::endl;
+            return 1;
+        }
+
+        // Detect faces
+        auto faces = detector.detect(image);
+        std::cout << "Detected " << faces.size() << " face(s)" << std::endl;
+
+        // Process each face
+        for (size_t i = 0; i < faces.size(); ++i) {
+            const auto& face = faces[i];
+
+            // Draw bounding box
+            cv::rectangle(image, face.bbox, cv::Scalar(0, 255, 0), 2);
+
+            // Get 106-point landmarks
+            auto landmarks = landmarker.getLandmarks(image, face.bbox);
+
+            // Draw all 106 points
+            for (const auto& pt : landmarks.points) {
+                cv::circle(image, pt, 1, cv::Scalar(0, 255, 255), -1);
+            }
+
+            std::cout << "Face " << (i + 1) << ": 106 landmarks detected" << std::endl;
+        }
+
+        // Save result
+        cv::imwrite("landmarks_result.jpg", image);
+        std::cout << "Saved result to landmarks_result.jpg" << std::endl;
+
+    } catch (const cv::Exception& e) {
+        std::cerr << "OpenCV Error: " << e.what() << std::endl;
+        return 1;
+    } catch (const std::exception& e) {
+        std::cerr << "Error: " << e.what() << std::endl;
+        return 1;
+    }
+
+    return 0;
+}

uniface-cpp/examples/recognize.cpp

@@ -0,0 +1,81 @@
+#include <iomanip>
+#include <iostream>
+
+#include <opencv2/highgui.hpp>
+#include <opencv2/imgproc.hpp>
+#include <uniface/uniface.hpp>
+
+int main(int argc, char** argv) {
+    if (argc < 5) {
+        std::cout << "Usage: " << argv[0]
+                  << " <detector_model> <recognizer_model> <image1> <image2>" << std::endl;
+        std::cout << "\nCompares faces from two images and outputs similarity score." << std::endl;
+        return 1;
+    }
+
+    const std::string detector_path = argv[1];
+    const std::string recognizer_path = argv[2];
+    const std::string image1_path = argv[3];
+    const std::string image2_path = argv[4];
+
+    try {
+        // Load models
+        uniface::RetinaFace detector(detector_path);
+        uniface::ArcFace recognizer(recognizer_path);
+
+        // Load images
+        cv::Mat image1 = cv::imread(image1_path);
+        cv::Mat image2 = cv::imread(image2_path);
+
+        if (image1.empty()) {
+            std::cerr << "Failed to load image: " << image1_path << std::endl;
+            return 1;
+        }
+        if (image2.empty()) {
+            std::cerr << "Failed to load image: " << image2_path << std::endl;
+            return 1;
+        }
+
+        // Detect faces
+        auto faces1 = detector.detect(image1);
+        auto faces2 = detector.detect(image2);
+
+        if (faces1.empty()) {
+            std::cerr << "No face detected in image1" << std::endl;
+            return 1;
+        }
+        if (faces2.empty()) {
+            std::cerr << "No face detected in image2" << std::endl;
+            return 1;
+        }
+
+        std::cout << "Detected " << faces1.size() << " face(s) in image1" << std::endl;
+        std::cout << "Detected " << faces2.size() << " face(s) in image2" << std::endl;
+
+        // Get embeddings for first face in each image
+        auto embedding1 = recognizer.getNormalizedEmbedding(image1, faces1[0].landmarks);
+        auto embedding2 = recognizer.getNormalizedEmbedding(image2, faces2[0].landmarks);
+
+        // Compute similarity
+        float similarity = uniface::cosineSimilarity(embedding1, embedding2);
+
+        std::cout << std::fixed << std::setprecision(4);
+        std::cout << "\nCosine Similarity: " << similarity << std::endl;
+
+        // Interpretation
+        if (similarity > 0.4f) {
+            std::cout << "Result: Same person (similarity > 0.4)" << std::endl;
+        } else {
+            std::cout << "Result: Different persons (similarity <= 0.4)" << std::endl;
+        }
+
+    } catch (const cv::Exception& e) {
+        std::cerr << "OpenCV Error: " << e.what() << std::endl;
+        return 1;
+    } catch (const std::exception& e) {
+        std::cerr << "Error: " << e.what() << std::endl;
+        return 1;
+    }
+
+    return 0;
+}

uniface-cpp/examples/webcam.cpp

@@ -0,0 +1,209 @@
+#include <chrono>
+#include <iostream>
+#include <memory>
+
+#include <opencv2/highgui.hpp>
+#include <opencv2/imgproc.hpp>
+#include <opencv2/videoio.hpp>
+#include <uniface/uniface.hpp>
+
+int main(int argc, char** argv) {
+    if (argc < 2) {
+        std::cout << "Usage: " << argv[0] << " <detector_model> [landmark_model] [camera_id]"
+                  << std::endl;
+        std::cout << "\nArguments:" << std::endl;
+        std::cout << "  detector_model : Path to face detector ONNX model (required)" << std::endl;
+        std::cout << "  landmark_model : Path to 106-point landmark ONNX model (optional)"
+                  << std::endl;
+        std::cout << "  camera_id      : Camera device ID, default 0 (optional)" << std::endl;
+        std::cout << "\nExamples:" << std::endl;
+        std::cout << "  " << argv[0] << " detector.onnx" << std::endl;
+        std::cout << "  " << argv[0] << " detector.onnx landmark.onnx" << std::endl;
+        std::cout << "  " << argv[0] << " detector.onnx landmark.onnx 1" << std::endl;
+        return 1;
+    }
+
+    const std::string detector_path = argv[1];
+    std::string landmark_path;
+    int camera_id = 0;
+
+    // Parse arguments - landmark_model is optional
+    if (argc >= 3) {
+        // Check if argv[2] is a number (camera_id) or a path (landmark_model)
+        if (std::isdigit(argv[2][0]) && strlen(argv[2]) <= 2) {
+            camera_id = std::atoi(argv[2]);
+        } else {
+            landmark_path = argv[2];
+            if (argc >= 4) {
+                camera_id = std::atoi(argv[3]);
+            }
+        }
+    }
+
+    try {
+        // Load detector
+        std::cout << "Loading detector: " << detector_path << std::endl;
+        uniface::RetinaFace detector(detector_path);
+        std::cout << "Detector loaded!" << std::endl;
+
+        // Load landmark model if provided
+        std::unique_ptr<uniface::Landmark106> landmarker;
+        if (!landmark_path.empty()) {
+            std::cout << "Loading landmarker: " << landmark_path << std::endl;
+            landmarker = std::make_unique<uniface::Landmark106>(landmark_path);
+            std::cout << "Landmarker loaded!" << std::endl;
+        }
+
+        // Open camera
+        cv::VideoCapture cap(camera_id);
+        if (!cap.isOpened()) {
+            std::cerr << "Error: Cannot open camera " << camera_id << std::endl;
+            return 1;
+        }
+
+        const int frame_width = static_cast<int>(cap.get(cv::CAP_PROP_FRAME_WIDTH));
+        const int frame_height = static_cast<int>(cap.get(cv::CAP_PROP_FRAME_HEIGHT));
+        std::cout << "\nCamera opened: " << frame_width << "x" << frame_height << std::endl;
+        std::cout << "Press 'q' to quit, 's' to save screenshot, 'l' to toggle landmarks"
+                  << std::endl;
+
+        cv::Mat frame;
+        int frame_count = 0;
+        double total_time = 0.0;
+        bool show_landmarks = true;  // Toggle for 106-point landmarks
+
+        while (true) {
+            cap >> frame;
+            if (frame.empty()) {
+                std::cerr << "Error: Empty frame captured" << std::endl;
+                break;
+            }
+
+            const auto start = std::chrono::high_resolution_clock::now();
+
+            // Detect faces
+            const auto faces = detector.detect(frame);
+
+            // Get 106-point landmarks if available
+            std::vector<uniface::Landmarks> all_landmarks;
+            if (landmarker && show_landmarks) {
+                all_landmarks.reserve(faces.size());
+                for (const auto& face : faces) {
+                    all_landmarks.push_back(landmarker->getLandmarks(frame, face.bbox));
+                }
+            }
+
+            const auto end = std::chrono::high_resolution_clock::now();
+            const std::chrono::duration<double, std::milli> elapsed = end - start;
+            const double inference_time = elapsed.count();
+
+            ++frame_count;
+            total_time += inference_time;
+            const double avg_time = total_time / static_cast<double>(frame_count);
+            const double fps = 1000.0 / avg_time;
+
+            // Draw results
+            for (size_t i = 0; i < faces.size(); ++i) {
+                const auto& face = faces[i];
+
+                // Draw bounding box
+                cv::rectangle(frame, face.bbox, cv::Scalar(0, 255, 0), 2);
+
+                // Draw 5-point landmarks from detector
+                for (size_t j = 0; j < face.landmarks.size(); ++j) {
+                    cv::Scalar color;
+                    if (j < 2) {
+                        color = cv::Scalar(255, 0, 0);  // Eyes - Blue
+                    } else if (j == 2) {
+                        color = cv::Scalar(0, 255, 0);  // Nose - Green
+                    } else {
+                        color = cv::Scalar(0, 0, 255);  // Mouth - Red
+                    }
+                    cv::circle(frame, face.landmarks[j], 3, color, -1);
+                }
+
+                // Draw 106-point landmarks if available
+                if (i < all_landmarks.size()) {
+                    const auto& lm = all_landmarks[i];
+
+                    // Draw all 106 points
+                    for (const auto& pt : lm.points) {
+                        cv::circle(frame, pt, 1, cv::Scalar(0, 255, 255), -1);
+                    }
+                }
+
+                // Draw confidence
+                const std::string conf_text = cv::format("%.2f", face.confidence);
+                const cv::Point text_org(
+                    static_cast<int>(face.bbox.x), static_cast<int>(face.bbox.y) - 5
+                );
+                cv::putText(
+                    frame,
+                    conf_text,
+                    text_org,
+                    cv::FONT_HERSHEY_SIMPLEX,
+                    0.5,
+                    cv::Scalar(0, 255, 0),
+                    1
+                );
+            }
+
+            // Draw info overlay
+            std::string mode = landmarker
+                                 ? (show_landmarks ? "Detection + 106 Landmarks" : "Detection Only")
+                                 : "Detection Only";
+            const std::string info_text = cv::format(
+                "FPS: %.1f | Faces: %zu | Time: %.1fms", fps, faces.size(), inference_time
+            );
+            cv::putText(
+                frame,
+                info_text,
+                cv::Point(10, 30),
+                cv::FONT_HERSHEY_SIMPLEX,
+                0.7,
+                cv::Scalar(0, 255, 0),
+                2
+            );
+            cv::putText(
+                frame,
+                mode,
+                cv::Point(10, 60),
+                cv::FONT_HERSHEY_SIMPLEX,
+                0.6,
+                cv::Scalar(255, 255, 0),
+                2
+            );
+
+            cv::imshow("Uniface - Face Detection & Landmarks", frame);
+
+            const char key = static_cast<char>(cv::waitKey(1));
+            if (key == 'q' || key == 27) {
+                break;
+            } else if (key == 's') {
+                const std::string filename = cv::format("screenshot_%d.jpg", frame_count);
+                cv::imwrite(filename, frame);
+                std::cout << "Screenshot saved: " << filename << std::endl;
+            } else if (key == 'l' && landmarker) {
+                show_landmarks = !show_landmarks;
+                std::cout << "106-point landmarks: " << (show_landmarks ? "ON" : "OFF")
+                          << std::endl;
+            }
+        }
+
+        cap.release();
+        cv::destroyAllWindows();
+
+        std::cout << "\n=== Statistics ===" << std::endl;
+        std::cout << "Total frames: " << frame_count << std::endl;
+        std::cout << "Average inference time: " << (total_time / frame_count) << " ms" << std::endl;
+
+    } catch (const cv::Exception& e) {
+        std::cerr << "OpenCV Error: " << e.what() << std::endl;
+        return 1;
+    } catch (const std::exception& e) {
+        std::cerr << "Error: " << e.what() << std::endl;
+        return 1;
+    }
+
+    return 0;
+}

uniface-cpp/include/uniface/analyzer.hpp

@@ -0,0 +1,63 @@
+#ifndef UNIFACE_ANALYZER_HPP_
+#define UNIFACE_ANALYZER_HPP_
+
+#include "uniface/detector.hpp"
+#include "uniface/landmarker.hpp"
+#include "uniface/recognizer.hpp"
+#include "uniface/types.hpp"
+
+#include <memory>
+#include <optional>
+#include <string>
+#include <vector>
+
+namespace uniface {
+
+// Result of face analysis
+struct AnalyzedFace {
+    Face face;                           // detection result (bbox, confidence, 5-point landmarks)
+    std::optional<Landmarks> landmarks;  // 106-point landmarks (if landmarker loaded)
+    std::optional<Embedding> embedding;  // face embedding (if recognizer loaded)
+};
+
+// Unified face analysis combining detection, recognition, and landmarks
+class FaceAnalyzer {
+public:
+    FaceAnalyzer() = default;
+    ~FaceAnalyzer() = default;
+
+    FaceAnalyzer(const FaceAnalyzer&) = delete;
+    FaceAnalyzer& operator=(const FaceAnalyzer&) = delete;
+    FaceAnalyzer(FaceAnalyzer&&) = default;
+    FaceAnalyzer& operator=(FaceAnalyzer&&) = default;
+
+    // Load components (returns *this for chaining)
+    FaceAnalyzer& loadDetector(const std::string& path, const DetectorConfig& config = DetectorConfig{});
+    FaceAnalyzer& loadRecognizer(const std::string& path, const RecognizerConfig& config = RecognizerConfig{});
+    FaceAnalyzer& loadLandmarker(const std::string& path, const LandmarkerConfig& config = LandmarkerConfig{});
+
+    // Analyze faces in BGR image (throws if detector not loaded)
+    [[nodiscard]] std::vector<AnalyzedFace> analyze(const cv::Mat& image);
+
+    // Component checks
+    [[nodiscard]] bool hasDetector() const noexcept { return detector_ != nullptr; }
+    [[nodiscard]] bool hasRecognizer() const noexcept { return recognizer_ != nullptr; }
+    [[nodiscard]] bool hasLandmarker() const noexcept { return landmarker_ != nullptr; }
+
+    // Direct component access
+    [[nodiscard]] RetinaFace* detector() noexcept { return detector_.get(); }
+    [[nodiscard]] ArcFace* recognizer() noexcept { return recognizer_.get(); }
+    [[nodiscard]] Landmark106* landmarker() noexcept { return landmarker_.get(); }
+    [[nodiscard]] const RetinaFace* detector() const noexcept { return detector_.get(); }
+    [[nodiscard]] const ArcFace* recognizer() const noexcept { return recognizer_.get(); }
+    [[nodiscard]] const Landmark106* landmarker() const noexcept { return landmarker_.get(); }
+
+private:
+    std::unique_ptr<RetinaFace> detector_;
+    std::unique_ptr<ArcFace> recognizer_;
+    std::unique_ptr<Landmark106> landmarker_;
+};
+
+}  // namespace uniface
+
+#endif  // UNIFACE_ANALYZER_HPP_

uniface-cpp/include/uniface/detector.hpp

@@ -0,0 +1,47 @@
+#ifndef UNIFACE_DETECTOR_HPP_
+#define UNIFACE_DETECTOR_HPP_
+
+#include "uniface/types.hpp"
+
+#include <array>
+#include <string>
+#include <vector>
+
+#include <opencv2/dnn.hpp>
+
+namespace uniface {
+
+// RetinaFace detector using OpenCV DNN backend
+class RetinaFace {
+public:
+    explicit RetinaFace(
+        const std::string& model_path,
+        float conf_thresh = 0.5f,
+        float nms_thresh = 0.4f,
+        cv::Size input_size = cv::Size(640, 640)
+    );
+
+    // Detect faces in BGR image, returns bboxes + 5-point landmarks
+    [[nodiscard]] std::vector<Face> detect(const cv::Mat& image);
+
+    // Accessors
+    [[nodiscard]] float getConfidenceThreshold() const noexcept { return confidence_threshold_; }
+    [[nodiscard]] float getNmsThreshold() const noexcept { return nms_threshold_; }
+    [[nodiscard]] cv::Size getInputSize() const noexcept { return input_size_; }
+
+    void setConfidenceThreshold(float threshold) noexcept { confidence_threshold_ = threshold; }
+    void setNmsThreshold(float threshold) noexcept { nms_threshold_ = threshold; }
+
+private:
+    cv::dnn::Net net_;
+    float confidence_threshold_;
+    float nms_threshold_;
+    cv::Size input_size_;
+    std::vector<std::array<float, 4>> anchors_;
+
+    void generateAnchors();
+};
+
+}  // namespace uniface
+
+#endif  // UNIFACE_DETECTOR_HPP_

uniface-cpp/include/uniface/landmarker.hpp

@@ -0,0 +1,32 @@
+#ifndef UNIFACE_LANDMARKER_HPP_
+#define UNIFACE_LANDMARKER_HPP_
+
+#include "uniface/types.hpp"
+
+#include <string>
+
+#include <opencv2/dnn.hpp>
+
+namespace uniface {
+
+// 106-point facial landmark detector
+class Landmark106 {
+public:
+    explicit Landmark106(const std::string& model_path, const LandmarkerConfig& config = LandmarkerConfig{});
+
+    // Detect 106 landmarks for a face, returns points in original image coordinates
+    [[nodiscard]] Landmarks getLandmarks(const cv::Mat& image, const cv::Rect2f& bbox);
+
+    [[nodiscard]] cv::Size getInputSize() const noexcept { return config_.input_size; }
+
+private:
+    cv::dnn::Net net_;
+    LandmarkerConfig config_;
+
+    [[nodiscard]] cv::Mat preprocess(const cv::Mat& image, const cv::Rect2f& bbox, cv::Mat& transform);
+    [[nodiscard]] Landmarks postprocess(const cv::Mat& predictions, const cv::Mat& transform);
+};
+
+}  // namespace uniface
+
+#endif  // UNIFACE_LANDMARKER_HPP_

uniface-cpp/include/uniface/recognizer.hpp

@@ -0,0 +1,37 @@
+#ifndef UNIFACE_RECOGNIZER_HPP_
+#define UNIFACE_RECOGNIZER_HPP_
+
+#include "uniface/types.hpp"
+
+#include <string>
+
+#include <opencv2/dnn.hpp>
+
+namespace uniface {
+
+// ArcFace face recognition (MobileNet/ResNet backbones)
+class ArcFace {
+public:
+    explicit ArcFace(const std::string& model_path, const RecognizerConfig& config = RecognizerConfig{});
+
+    // Get 512-dim embedding from pre-aligned 112x112 face
+    [[nodiscard]] Embedding getEmbedding(const cv::Mat& aligned_face);
+
+    // Get 512-dim embedding with automatic alignment
+    [[nodiscard]] Embedding getEmbedding(const cv::Mat& image, const std::array<cv::Point2f, 5>& landmarks);
+
+    // Get L2-normalized embedding with automatic alignment
+    [[nodiscard]] Embedding getNormalizedEmbedding(const cv::Mat& image, const std::array<cv::Point2f, 5>& landmarks);
+
+    [[nodiscard]] cv::Size getInputSize() const noexcept { return config_.input_size; }
+
+private:
+    cv::dnn::Net net_;
+    RecognizerConfig config_;
+
+    [[nodiscard]] cv::Mat preprocess(const cv::Mat& face_image);
+};
+
+}  // namespace uniface
+
+#endif  // UNIFACE_RECOGNIZER_HPP_

uniface-cpp/include/uniface/types.hpp

@@ -0,0 +1,45 @@
+#ifndef UNIFACE_TYPES_HPP_
+#define UNIFACE_TYPES_HPP_
+
+#include <array>
+#include <vector>
+
+#include <opencv2/core.hpp>
+
+namespace uniface {
+
+// Detected face with bbox, confidence, and 5-point landmarks
+struct Face {
+    cv::Rect2f bbox;
+    float confidence;
+    std::array<cv::Point2f, 5> landmarks;  // left_eye, right_eye, nose, left_mouth, right_mouth
+};
+
+// 512-dimensional face embedding
+using Embedding = std::array<float, 512>;
+
+// 106-point facial landmarks
+struct Landmarks {
+    std::array<cv::Point2f, 106> points;
+};
+
+// Configuration structs
+struct DetectorConfig {
+    float conf_thresh = 0.5f;
+    float nms_thresh = 0.4f;
+    cv::Size input_size = cv::Size(640, 640);
+};
+
+struct RecognizerConfig {
+    float input_mean = 127.5f;
+    float input_std = 127.5f;
+    cv::Size input_size = cv::Size(112, 112);
+};
+
+struct LandmarkerConfig {
+    cv::Size input_size = cv::Size(192, 192);
+};
+
+}  // namespace uniface
+
+#endif  // UNIFACE_TYPES_HPP_

uniface-cpp/include/uniface/uniface.hpp

@@ -0,0 +1,11 @@
+#ifndef UNIFACE_HPP_
+#define UNIFACE_HPP_
+
+#include "uniface/analyzer.hpp"
+#include "uniface/detector.hpp"
+#include "uniface/landmarker.hpp"
+#include "uniface/recognizer.hpp"
+#include "uniface/types.hpp"
+#include "uniface/utils.hpp"
+
+#endif  // UNIFACE_HPP_