fix: Python 3.10 does not support tomlib (#43 )

Merge pull request #42 from yakhyo/feat/standardize-outputs
feat: Standardize detection output and several other updates
2025-12-30 09:02:25 +00:00 · 2025-12-24 00:51:36 +09:00 · 2025-12-24 00:38:32 +09:00 · 2025-12-24 00:34:24 +09:00 · 2025-12-24 00:00:00 +09:00 · 2025-12-23 23:59:15 +09:00
35 changed files with 1885 additions and 208 deletions
--- a/.github/logos/gaze_crop.png
+++ b/.github/logos/gaze_crop.png
--- a/.github/logos/gaze_org.png
+++ b/.github/logos/gaze_org.png
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -10,14 +10,20 @@ on:
      - main
      - develop

+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
  test:
-    runs-on: ubuntu-latest
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 15

    strategy:
      fail-fast: false
      matrix:
-        python-version: ["3.10", "3.11", "3.12", "3.13"]
+        os: [ubuntu-latest, macos-latest, windows-latest]
+        python-version: ["3.11", "3.13"]

    steps:
      - name: Checkout code
@@ -27,7 +33,7 @@ jobs:
        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python-version }}
-          cache: 'pip'
+          cache: "pip"

      - name: Install dependencies
        run: |
@@ -38,21 +44,18 @@ jobs:
        run: |
          python -c "import onnxruntime as ort; print('Available providers:', ort.get_available_providers())"

-      - name: Lint with ruff (if available)
-        run: |
-          pip install ruff || true
-          ruff check . --exit-zero || true
-        continue-on-error: true
+      - name: Lint with ruff
+        run: ruff check .

      - name: Run tests
        run: pytest -v --tb=short

      - name: Test package imports
-        run: |
-          python -c "from uniface import RetinaFace, ArcFace, Landmark106, AgeGender; print('All imports successful')"
+        run: python -c "import uniface; print(f'uniface {uniface.__version__} loaded with {len(uniface.__all__)} exports')"

  build:
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    needs: test

    steps:
@@ -63,7 +66,7 @@ jobs:
        uses: actions/setup-python@v5
        with:
          python-version: "3.10"
-          cache: 'pip'
+          cache: "pip"

      - name: Install build tools
        run: |
@@ -84,4 +87,3 @@ jobs:
          name: dist-python-${{ github.sha }}
          path: dist/
          retention-days: 7
-
--- a/.github/workflows/publish.yml
+++ b/.github/workflows/publish.yml
@@ -5,9 +5,14 @@ on:
    tags:
      - "v*.*.*"  # Trigger only on version tags like v0.1.9

+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
 jobs:
  validate:
    runs-on: ubuntu-latest
+    timeout-minutes: 5
    outputs:
      version: ${{ steps.get_version.outputs.version }}
      tag_version: ${{ steps.get_version.outputs.tag_version }}
@@ -16,13 +21,18 @@ jobs:
      - name: Checkout code
        uses: actions/checkout@v4

+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
      - name: Get version from tag and pyproject.toml
        id: get_version
        run: |
          TAG_VERSION=${GITHUB_REF#refs/tags/v}
          echo "tag_version=$TAG_VERSION" >> $GITHUB_OUTPUT

-          PYPROJECT_VERSION=$(grep -Po '(?<=^version = ")[^"]*' pyproject.toml)
+          PYPROJECT_VERSION=$(python -c "import tomllib; print(tomllib.load(open('pyproject.toml','rb'))['project']['version'])")
          echo "version=$PYPROJECT_VERSION" >> $GITHUB_OUTPUT

          echo "Tag version: v$TAG_VERSION"
@@ -38,12 +48,13 @@ jobs:

  test:
    runs-on: ubuntu-latest
+    timeout-minutes: 15
    needs: validate

    strategy:
      fail-fast: false
      matrix:
-        python-version: ["3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.11", "3.13"]

    steps:
      - name: Checkout code
@@ -65,6 +76,7 @@ jobs:

  publish:
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    needs: [validate, test]
    permissions:
      contents: write
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -21,11 +21,28 @@ Thank you for considering contributing to UniFace! We welcome contributions of a

 ### Code Style

+This project uses [Ruff](https://docs.astral.sh/ruff/) for linting and formatting.
+
+```bash
+# Check for linting errors
+ruff check .
+
+# Auto-fix linting errors
+ruff check . --fix
+
+# Format code
+ruff format .
+```
+
+**Guidelines:**
 - Follow PEP8 guidelines
 - Use type hints (Python 3.10+)
 - Write docstrings for public APIs
+- Line length: 120 characters
 - Keep code simple and readable

+All PRs must pass `ruff check .` before merging.
+
 ## Development Setup

 ```bash
@@ -51,6 +68,7 @@ Example notebooks demonstrating library usage:
 | Face Recognition | [face_analyzer.ipynb](examples/face_analyzer.ipynb) |
 | Face Verification | [face_verification.ipynb](examples/face_verification.ipynb) |
 | Face Search | [face_search.ipynb](examples/face_search.ipynb) |
+| Face Anonymization | [face_anonymization.ipynb](examples/face_anonymization.ipynb) |

 ## Questions?

--- a/MODELS.md
+++ b/MODELS.md
@@ -404,6 +404,47 @@ print(f"Detected {len(np.unique(mask))} facial components")

 ---

+## Anti-Spoofing Models
+
+### MiniFASNet Family
+
+Lightweight face anti-spoofing models for liveness detection. Detect if a face is real (live) or fake (photo, video replay, mask).
+
+| Model Name | Size   | Scale | Use Case                      |
+| ---------- | ------ | ----- | ----------------------------- |
+| `V1SE`   | 1.2 MB | 4.0   | Squeeze-and-excitation variant |
+| `V2` ⭐  | 1.2 MB | 2.7   | **Recommended default**       |
+
+**Dataset**: Trained on face anti-spoofing datasets
+**Output**: Returns (label_idx, score) where label_idx: 0=Fake, 1=Real
+
+#### Usage
+
+```python
+from uniface import RetinaFace
+from uniface.spoofing import MiniFASNet
+from uniface.constants import MiniFASNetWeights
+
+# Default (V2, recommended)
+detector = RetinaFace()
+spoofer = MiniFASNet()
+
+# V1SE variant
+spoofer = MiniFASNet(model_name=MiniFASNetWeights.V1SE)
+
+# Detect and check liveness
+faces = detector.detect(image)
+for face in faces:
+    label_idx, score = spoofer.predict(image, face['bbox'])
+    # label_idx: 0 = Fake, 1 = Real
+    label = 'Real' if label_idx == 1 else 'Fake'
+    print(f"{label}: {score:.1%}")
+```
+
+**Note**: Requires face bounding box from a detector. Use with RetinaFace, SCRFD, or YOLOv5Face.
+
+---
+
 ## Model Updates

 Models are automatically downloaded and cached on first use. Cache location: `~/.uniface/models/`
@@ -445,6 +486,7 @@ python scripts/download_model.py --model MNET_V2
 - **Face Recognition Training**: [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition) - ArcFace, MobileFace, SphereFace training code
 - **Gaze Estimation Training**: [yakhyo/gaze-estimation](https://github.com/yakhyo/gaze-estimation) - MobileGaze training code and pretrained weights
 - **Face Parsing Training**: [yakhyo/face-parsing](https://github.com/yakhyo/face-parsing) - BiSeNet training code and pretrained weights
+- **Face Anti-Spoofing**: [yakhyo/face-anti-spoofing](https://github.com/yakhyo/face-anti-spoofing) - MiniFASNet ONNX inference (weights from [minivision-ai/Silent-Face-Anti-Spoofing](https://github.com/minivision-ai/Silent-Face-Anti-Spoofing))
 - **InsightFace**: [deepinsight/insightface](https://github.com/deepinsight/insightface) - Model architectures and pretrained weights

 ### Papers
--- a/QUICKSTART.md
+++ b/QUICKSTART.md
@@ -39,9 +39,9 @@ faces = detector.detect(image)
 # Print results
 for i, face in enumerate(faces):
    print(f"Face {i+1}:")
-    print(f"  Confidence: {face['confidence']:.2f}")
-    print(f"  BBox: {face['bbox']}")
-    print(f"  Landmarks: {len(face['landmarks'])} points")
+    print(f"  Confidence: {face.confidence:.2f}")
+    print(f"  BBox: {face.bbox}")
+    print(f"  Landmarks: {len(face.landmarks)} points")
 ```

 **Output:**
@@ -70,9 +70,9 @@ image = cv2.imread("photo.jpg")
 faces = detector.detect(image)

 # Extract visualization data
-bboxes = [f['bbox'] for f in faces]
-scores = [f['confidence'] for f in faces]
-landmarks = [f['landmarks'] for f in faces]
+bboxes = [f.bbox for f in faces]
+scores = [f.confidence for f in faces]
+landmarks = [f.landmarks for f in faces]

 # Draw on image
 draw_detections(
@@ -113,8 +113,8 @@ faces2 = detector.detect(image2)

 if faces1 and faces2:
    # Extract embeddings
-    emb1 = recognizer.get_normalized_embedding(image1, faces1[0]['landmarks'])
-    emb2 = recognizer.get_normalized_embedding(image2, faces2[0]['landmarks'])
+    emb1 = recognizer.get_normalized_embedding(image1, faces1[0].landmarks)
+    emb2 = recognizer.get_normalized_embedding(image2, faces2[0].landmarks)

    # Compute similarity (cosine similarity)
    similarity = np.dot(emb1, emb2.T)[0][0]
@@ -159,9 +159,9 @@ while True:
    faces = detector.detect(frame)

    # Draw results
-    bboxes = [f['bbox'] for f in faces]
-    scores = [f['confidence'] for f in faces]
-    landmarks = [f['landmarks'] for f in faces]
+    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,
@@ -199,7 +199,7 @@ faces = detector.detect(image)

 # Predict attributes
 for i, face in enumerate(faces):
-    gender, age = age_gender.predict(image, face['bbox'])
+    gender, age = age_gender.predict(image, face.bbox)
    gender_str = 'Female' if gender == 0 else 'Male'
    print(f"Face {i+1}: {gender_str}, {age} years old")
 ```
@@ -230,7 +230,7 @@ image = cv2.imread("photo.jpg")
 faces = detector.detect(image)

 if faces:
-    landmarks = landmarker.get_landmarks(image, faces[0]['bbox'])
+    landmarks = landmarker.get_landmarks(image, faces[0].bbox)
    print(f"Detected {len(landmarks)} landmarks")

    # Draw landmarks
@@ -262,8 +262,7 @@ faces = detector.detect(image)

 # Estimate gaze for each face
 for i, face in enumerate(faces):
-    bbox = face['bbox']
-    x1, y1, x2, y2 = map(int, bbox[:4])
+    x1, y1, x2, y2 = map(int, face.bbox[:4])
    face_crop = image[y1:y2, x1:x2]

    if face_crop.size > 0:
@@ -271,7 +270,7 @@ for i, face in enumerate(faces):
        print(f"Face {i+1}: pitch={np.degrees(pitch):.1f}°, yaw={np.degrees(yaw):.1f}°")

        # Draw gaze direction
-        draw_gaze(image, bbox, pitch, yaw)
+        draw_gaze(image, face.bbox, pitch, yaw)

 cv2.imwrite("gaze_output.jpg", image)
 ```
@@ -328,7 +327,138 @@ Detected 12 facial components

 ---

-## 9. Batch Processing (3 minutes)
+## 9. Face Anonymization (2 minutes)
+
+Automatically blur faces for privacy protection:
+
+```python
+from uniface.privacy import anonymize_faces
+import cv2
+
+# One-liner: automatic detection and blurring
+image = cv2.imread("group_photo.jpg")
+anonymized = anonymize_faces(image, method='pixelate')
+cv2.imwrite("anonymized.jpg", anonymized)
+print("Faces anonymized successfully!")
+```
+
+**Manual control with custom parameters:**
+
+```python
+from uniface import RetinaFace
+from uniface.privacy import BlurFace
+
+# Initialize detector and blurrer
+detector = RetinaFace()
+blurrer = BlurFace(method='gaussian', blur_strength=5.0)
+
+# Detect and anonymize
+faces = detector.detect(image)
+anonymized = blurrer.anonymize(image, faces)
+cv2.imwrite("output.jpg", anonymized)
+```
+
+**Available blur methods:**
+
+```python
+# Pixelation (news media standard)
+blurrer = BlurFace(method='pixelate', pixel_blocks=8)
+
+# Gaussian blur (smooth, natural)
+blurrer = BlurFace(method='gaussian', blur_strength=4.0)
+
+# Black boxes (maximum privacy)
+blurrer = BlurFace(method='blackout', color=(0, 0, 0))
+
+# Elliptical blur (natural face shape)
+blurrer = BlurFace(method='elliptical', blur_strength=3.0, margin=30)
+
+# Median blur (edge-preserving)
+blurrer = BlurFace(method='median', blur_strength=3.0)
+```
+
+**Webcam anonymization:**
+
+```python
+import cv2
+from uniface import RetinaFace
+from uniface.privacy import BlurFace
+
+detector = RetinaFace()
+blurrer = BlurFace(method='pixelate')
+cap = cv2.VideoCapture(0)
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+    frame = blurrer.anonymize(frame, faces, inplace=True)
+
+    cv2.imshow('Anonymized', frame)
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+**Command-line tool:**
+
+```bash
+# Anonymize image with pixelation
+python scripts/run_anonymization.py --image photo.jpg
+
+# Real-time webcam anonymization
+python scripts/run_anonymization.py --webcam --method gaussian
+
+# Custom blur strength
+python scripts/run_anonymization.py --image photo.jpg --method gaussian --blur-strength 5.0
+```
+
+---
+
+## 10. Face Anti-Spoofing (2 minutes)
+
+Detect if a face is real or fake (photo, video replay, mask):
+
+```python
+from uniface import RetinaFace
+from uniface.spoofing import MiniFASNet
+
+detector = RetinaFace()
+spoofer = MiniFASNet()  # Uses V2 by default
+
+image = cv2.imread("photo.jpg")
+faces = detector.detect(image)
+
+for i, face in enumerate(faces):
+    label_idx, score = spoofer.predict(image, face.bbox)
+    # label_idx: 0 = Fake, 1 = Real
+    label = 'Real' if label_idx == 1 else 'Fake'
+    print(f"Face {i+1}: {label} ({score:.1%})")
+```
+
+**Output:**
+
+```
+Face 1: Real (98.5%)
+```
+
+**Command-line tool:**
+
+```bash
+# Image
+python scripts/run_spoofing.py --image photo.jpg
+
+# Webcam
+python scripts/run_spoofing.py --source 0
+```
+
+---
+
+## 11. Batch Processing (3 minutes)

 Process multiple images:

@@ -361,7 +491,7 @@ print("Done!")

 ---

-## 10. Model Selection
+## 12. Model Selection

 Choose the right model for your use case:

@@ -503,6 +633,7 @@ Explore interactive examples for common tasks:
 | **Face Verification** | Compare two faces to verify identity | [face_verification.ipynb](examples/face_verification.ipynb) |
 | **Face Search** | Find a person in a group photo | [face_search.ipynb](examples/face_search.ipynb) |
 | **Face Parsing** | Segment face into semantic components | [face_parsing.ipynb](examples/face_parsing.ipynb) |
+| **Face Anonymization** | Blur or pixelate faces for privacy protection | [face_anonymization.ipynb](examples/face_anonymization.ipynb) |
 | **Gaze Estimation** | Estimate gaze direction | [gaze_estimation.ipynb](examples/gaze_estimation.ipynb) |

 ### Additional Resources
--- a/README.md
+++ b/README.md
@@ -1,11 +1,15 @@
 # UniFace: All-in-One Face Analysis Library

+<div align="center">
+
 [![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 [![Python](https://img.shields.io/badge/Python-3.10%2B-blue)](https://www.python.org/)
 [![PyPI](https://img.shields.io/pypi/v/uniface.svg)](https://pypi.org/project/uniface/)
 [![CI](https://github.com/yakhyo/uniface/actions/workflows/ci.yml/badge.svg)](https://github.com/yakhyo/uniface/actions)
-[![Downloads](https://pepy.tech/badge/uniface)](https://pepy.tech/project/uniface)
-[![DeepWiki](https://img.shields.io/badge/DeepWiki-yakhyo%2Funiface-blue.svg?logo=data:image/png;base64,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)](https://deepwiki.com/yakhyo/uniface)
+[![Downloads](https://static.pepy.tech/badge/uniface)](https://pepy.tech/project/uniface)
+[![DeepWiki](https://img.shields.io/badge/DeepWiki-AI_Docs-blue.svg?logo=bookstack)](https://deepwiki.com/yakhyo/uniface)
+
+</div>

 <div align="center">
    <img src=".github/logos/logo_web.webp" width=75%>
@@ -23,6 +27,8 @@
 - **Face Parsing**: BiSeNet-based semantic segmentation with 19 facial component classes
 - **Gaze Estimation**: Real-time gaze direction prediction with MobileGaze
 - **Attribute Analysis**: Age, gender, and emotion detection
+- **Anti-Spoofing**: Face liveness detection with MiniFASNet models
+- **Face Anonymization**: Privacy-preserving face blurring with 5 methods (pixelate, gaussian, blackout, elliptical, median)
 - **Face Alignment**: Precise alignment for downstream tasks
 - **Hardware Acceleration**: ARM64 optimizations (Apple Silicon), CUDA (NVIDIA), CPU fallback
 - **Simple API**: Intuitive factory functions and clean interfaces
@@ -99,9 +105,9 @@ faces = detector.detect(image)

 # Process results
 for face in faces:
-    bbox = face['bbox']  # [x1, y1, x2, y2]
-    confidence = face['confidence']
-    landmarks = face['landmarks']  # 5-point landmarks
+    bbox = face.bbox  # np.ndarray [x1, y1, x2, y2]
+    confidence = face.confidence
+    landmarks = face.landmarks  # np.ndarray (5, 2) landmarks
    print(f"Face detected with confidence: {confidence:.2f}")
 ```

@@ -119,8 +125,8 @@ recognizer = ArcFace()
 faces1 = detector.detect(image1)
 faces2 = detector.detect(image2)

-embedding1 = recognizer.get_normalized_embedding(image1, faces1[0]['landmarks'])
-embedding2 = recognizer.get_normalized_embedding(image2, faces2[0]['landmarks'])
+embedding1 = recognizer.get_normalized_embedding(image1, faces1[0].landmarks)
+embedding2 = recognizer.get_normalized_embedding(image2, faces2[0].landmarks)

 # Compare faces
 similarity = compute_similarity(embedding1, embedding2)
@@ -136,7 +142,7 @@ detector = RetinaFace()
 landmarker = Landmark106()

 faces = detector.detect(image)
-landmarks = landmarker.get_landmarks(image, faces[0]['bbox'])
+landmarks = landmarker.get_landmarks(image, faces[0].bbox)
 # Returns 106 (x, y) landmark points
 ```

@@ -149,7 +155,7 @@ detector = RetinaFace()
 age_gender = AgeGender()

 faces = detector.detect(image)
-gender, age = age_gender.predict(image, faces[0]['bbox'])
+gender, age = age_gender.predict(image, faces[0].bbox)
 gender_str = 'Female' if gender == 0 else 'Male'
 print(f"{gender_str}, {age} years old")
 ```
@@ -166,15 +172,14 @@ gaze_estimator = MobileGaze()

 faces = detector.detect(image)
 for face in faces:
-    bbox = face['bbox']
-    x1, y1, x2, y2 = map(int, bbox[:4])
+    x1, y1, x2, y2 = map(int, face.bbox[:4])
    face_crop = image[y1:y2, x1:x2]

    pitch, yaw = gaze_estimator.estimate(face_crop)
    print(f"Gaze: pitch={np.degrees(pitch):.1f}°, yaw={np.degrees(yaw):.1f}°")

    # Visualize
-    draw_gaze(image, bbox, pitch, yaw)
+    draw_gaze(image, face.bbox, pitch, yaw)
 ```

 ### Face Parsing
@@ -198,6 +203,77 @@ vis_result = vis_parsing_maps(face_rgb, mask, save_image=False)
 print(f"Unique classes: {len(np.unique(mask))}")
 ```

+### Face Anti-Spoofing
+
+Detect if a face is real or fake (photo, video replay, mask):
+
+```python
+from uniface import RetinaFace
+from uniface.spoofing import MiniFASNet
+
+detector = RetinaFace()
+spoofer = MiniFASNet()  # Uses V2 by default
+
+faces = detector.detect(image)
+for face in faces:
+    label_idx, score = spoofer.predict(image, face.bbox)
+    # label_idx: 0 = Fake, 1 = Real
+    label = 'Real' if label_idx == 1 else 'Fake'
+    print(f"{label}: {score:.1%}")
+```
+
+### Face Anonymization
+
+Protect privacy by blurring or pixelating faces with 5 different methods:
+
+```python
+from uniface import RetinaFace
+from uniface.privacy import BlurFace, anonymize_faces
+import cv2
+
+# Method 1: One-liner with automatic detection
+image = cv2.imread("photo.jpg")
+anonymized = anonymize_faces(image, method='pixelate')
+cv2.imwrite("anonymized.jpg", anonymized)
+
+# Method 2: Manual control with custom parameters
+detector = RetinaFace()
+blurrer = BlurFace(method='gaussian', blur_strength=5.0)
+
+faces = detector.detect(image)
+anonymized = blurrer.anonymize(image, faces)
+
+# Available blur methods:
+methods = {
+    'pixelate': BlurFace(method='pixelate', pixel_blocks=10),      # Blocky effect (news media standard)
+    'gaussian': BlurFace(method='gaussian', blur_strength=3.0),    # Smooth, natural blur
+    'blackout': BlurFace(method='blackout', color=(0, 0, 0)),      # Solid color boxes (maximum privacy)
+    'elliptical': BlurFace(method='elliptical', margin=20),        # Soft oval blur (natural face shape)
+    'median': BlurFace(method='median', blur_strength=3.0)         # Edge-preserving blur
+}
+
+# Real-time webcam anonymization
+cap = cv2.VideoCapture(0)
+detector = RetinaFace()
+blurrer = BlurFace(method='pixelate')
+
+while True:
+    ret, frame = cap.read()
+    if not ret:
+        break
+
+    faces = detector.detect(frame)
+    frame = blurrer.anonymize(frame, faces, inplace=True)
+
+    cv2.imshow('Anonymized', frame)
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()
+```
+
+
 ---

 ## Documentation
@@ -216,6 +292,7 @@ print(f"Unique classes: {len(np.unique(mask))}")
 from uniface.detection import RetinaFace, SCRFD
 from uniface.recognition import ArcFace
 from uniface.landmark import Landmark106
+from uniface.privacy import BlurFace, anonymize_faces

 from uniface.constants import SCRFDWeights

@@ -310,6 +387,12 @@ faces = detect_faces(image, method='retinaface', conf_thresh=0.8)  # methods: re
 | ---------- | ---------------------------------------- | ------------------------------------ |
 | `BiSeNet` | `model_name=ParsingWeights.RESNET18`, `input_size=(512, 512)` | 19 facial component classes; BiSeNet architecture with ResNet backbone |

+**Anti-Spoofing**
+
+| Class         | Key params (defaults)                     | Notes                                |
+| ------------- | ----------------------------------------- | ------------------------------------ |
+| `MiniFASNet` | `model_name=MiniFASNetWeights.V2`       | Returns (label_idx, score); 0=Fake, 1=Real |
+
 ---

 ## Model Performance
@@ -357,6 +440,7 @@ Interactive examples covering common face analysis tasks:
 | **Face Verification** | Compare two faces to verify identity | [face_verification.ipynb](examples/face_verification.ipynb) |
 | **Face Search** | Find a person in a group photo | [face_search.ipynb](examples/face_search.ipynb) |
 | **Face Parsing** | Segment face into semantic components | [face_parsing.ipynb](examples/face_parsing.ipynb) |
+| **Face Anonymization** | Blur or pixelate faces for privacy protection | [face_anonymization.ipynb](examples/face_anonymization.ipynb) |
 | **Gaze Estimation** | Estimate gaze direction from face images | [gaze_estimation.ipynb](examples/gaze_estimation.ipynb) |

 ### Webcam Face Detection
@@ -377,9 +461,9 @@ while True:
    faces = detector.detect(frame)

    # Extract data for visualization
-    bboxes = [f['bbox'] for f in faces]
-    scores = [f['confidence'] for f in faces]
-    landmarks = [f['landmarks'] for f in faces]
+    bboxes = [f.bbox for f in faces]
+    scores = [f.confidence for f in faces]
+    landmarks = [f.landmarks for f in faces]

    draw_detections(
        image=frame,
@@ -413,7 +497,7 @@ for person_id, image_path in person_images.items():
    faces = detector.detect(image)
    if faces:
        embedding = recognizer.get_normalized_embedding(
-            image, faces[0]['landmarks']
+            image, faces[0].landmarks
        )
        database[person_id] = embedding

@@ -422,7 +506,7 @@ query_image = cv2.imread("query.jpg")
 query_faces = detector.detect(query_image)
 if query_faces:
    query_embedding = recognizer.get_normalized_embedding(
-        query_image, query_faces[0]['landmarks']
+        query_image, query_faces[0].landmarks
    )

    # Find best match
@@ -551,6 +635,8 @@ uniface/
 │   ├── parsing/         # Face parsing
 │   ├── gaze/            # Gaze estimation
 │   ├── attribute/       # Age, gender, emotion
+│   ├── spoofing/        # Face anti-spoofing
+│   ├── privacy/         # Face anonymization & blurring
 │   ├── onnx_utils.py    # ONNX Runtime utilities
 │   ├── model_store.py   # Model download & caching
 │   └── visualization.py # Drawing utilities
@@ -568,6 +654,7 @@ uniface/
 - **Face Recognition Training**: [yakhyo/face-recognition](https://github.com/yakhyo/face-recognition) - ArcFace, MobileFace, SphereFace training code
 - **Face Parsing Training**: [yakhyo/face-parsing](https://github.com/yakhyo/face-parsing) - BiSeNet face parsing training code and pretrained weights
 - **Gaze Estimation Training**: [yakhyo/gaze-estimation](https://github.com/yakhyo/gaze-estimation) - MobileGaze training code and pretrained weights
+- **Face Anti-Spoofing**: [yakhyo/face-anti-spoofing](https://github.com/yakhyo/face-anti-spoofing) - MiniFASNet ONNX inference (weights from [minivision-ai/Silent-Face-Anti-Spoofing](https://github.com/minivision-ai/Silent-Face-Anti-Spoofing))
 - **InsightFace**: [deepinsight/insightface](https://github.com/deepinsight/insightface) - Model architectures and pretrained weights

 ## Contributing
--- a/examples/face_alignment.ipynb
+++ b/examples/face_alignment.ipynb
@@ -48,7 +48,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "1.3.1\n"
+      "1.6.0\n"
     ]
    }
   ],
@@ -140,13 +140,13 @@
    "\n",
    "    # Draw detections\n",
    "    bbox_image = image.copy()\n",
-    "    bboxes = [f['bbox'] for f in faces]\n",
-    "    scores = [f['confidence'] for f in faces]\n",
-    "    landmarks = [f['landmarks'] for f in faces]\n",
+    "    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",
    "\n",
    "    # Align first detected face (returns aligned image and inverse transform matrix)\n",
-    "    first_landmarks = faces[0]['landmarks']\n",
+    "    first_landmarks = faces[0].landmarks\n",
    "    aligned_image, _ = face_alignment(image, first_landmarks, image_size=112)\n",
    "\n",
    "    # Convert BGR to RGB for visualization\n",
@@ -202,7 +202,8 @@
   "source": [
    "## Notes\n",
    "\n",
-    "- `detect()` returns a list of face dictionaries with `bbox`, `confidence`, `landmarks`\n",
+    "- `detect()` returns a list of `Face` objects with `bbox`, `confidence`, `landmarks` attributes\n",
+    "- Access attributes using dot notation: `face.bbox`, `face.landmarks`\n",
    "- `face_alignment()` uses 5-point landmarks to align and crop the face\n",
    "- Default output size is 112x112 (standard for face recognition models)\n"
   ]
--- a/examples/face_analyzer.ipynb
+++ b/examples/face_analyzer.ipynb
@@ -44,7 +44,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "1.3.1\n"
+      "1.6.0\n"
     ]
    }
   ],
--- a/examples/face_anonymization.ipynb
+++ b/examples/face_anonymization.ipynb
--- a/examples/face_detection.ipynb
+++ b/examples/face_detection.ipynb
@@ -44,7 +44,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "1.3.1\n"
+      "1.6.0\n"
     ]
    }
   ],
@@ -153,14 +153,14 @@
    "# Load image\n",
    "image = cv2.imread(image_path)\n",
    "\n",
-    "# Detect faces - returns list of face dictionaries\n",
+    "# Detect faces - returns list of Face objects\n",
    "faces = detector.detect(image)\n",
    "print(f'Detected {len(faces)} face(s)')\n",
    "\n",
    "# Unpack face data for visualization\n",
-    "bboxes = [f['bbox'] for f in faces]\n",
-    "scores = [f['confidence'] for f in faces]\n",
-    "landmarks = [f['landmarks'] for f in faces]\n",
+    "bboxes = [f.bbox for f in faces]\n",
+    "scores = [f.confidence for f in faces]\n",
+    "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",
@@ -211,9 +211,9 @@
    "faces = detector.detect(image, max_num=2)\n",
    "print(f'Detected {len(faces)} face(s)')\n",
    "\n",
-    "bboxes = [f['bbox'] for f in faces]\n",
-    "scores = [f['confidence'] for f in faces]\n",
-    "landmarks = [f['landmarks'] for f in faces]\n",
+    "bboxes = [f.bbox for f in faces]\n",
+    "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",
    "\n",
@@ -258,9 +258,9 @@
    "faces = detector.detect(image, max_num=5)\n",
    "print(f'Detected {len(faces)} face(s)')\n",
    "\n",
-    "bboxes = [f['bbox'] for f in faces]\n",
-    "scores = [f['confidence'] for f in faces]\n",
-    "landmarks = [f['landmarks'] for f in faces]\n",
+    "bboxes = [f.bbox for f in faces]\n",
+    "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",
    "\n",
@@ -274,7 +274,8 @@
   "source": [
    "## Notes\n",
    "\n",
-    "- `detect()` returns a list of dictionaries with keys: `bbox`, `confidence`, `landmarks`\n",
+    "- `detect()` returns a list of `Face` objects with attributes: `bbox`, `confidence`, `landmarks`\n",
+    "- Access attributes using dot notation: `face.bbox`, `face.confidence`, `face.landmarks`\n",
    "- Adjust `conf_thresh` and `nms_thresh` for your use case\n",
    "- Use `max_num` to limit detected faces"
   ]
--- a/examples/face_parsing.ipynb
+++ b/examples/face_parsing.ipynb
@@ -46,7 +46,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "UniFace version: 1.5.0\n"
+      "UniFace version: 1.6.0\n"
     ]
    }
   ],
@@ -365,7 +365,7 @@
 ],
 "metadata": {
  "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
@@ -379,7 +379,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.10.0"
+   "version": "3.13.5"
  }
 },
 "nbformat": 4,
--- a/examples/face_search.ipynb
+++ b/examples/face_search.ipynb
@@ -42,7 +42,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "1.3.1\n"
+      "1.6.0\n"
     ]
    }
   ],
--- a/examples/face_verification.ipynb
+++ b/examples/face_verification.ipynb
@@ -37,7 +37,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "1.3.1\n"
+      "1.6.0\n"
     ]
    }
   ],
--- a/examples/gaze_estimation.ipynb
+++ b/examples/gaze_estimation.ipynb
@@ -44,7 +44,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
-      "UniFace version: 1.4.0\n"
+      "UniFace version: 1.6.0\n"
     ]
    }
   ],
@@ -152,8 +152,7 @@
    "\n",
    "    # Estimate gaze for each face\n",
    "    for i, face in enumerate(faces):\n",
-    "        bbox = face['bbox']\n",
-    "        x1, y1, x2, y2 = map(int, bbox[:4])\n",
+    "        x1, y1, x2, y2 = map(int, face.bbox[:4])\n",
    "        face_crop = image[y1:y2, x1:x2]\n",
    "\n",
    "        if face_crop.size > 0:\n",
@@ -164,7 +163,7 @@
    "            print(f'    Face {i+1}: pitch={pitch_deg:.1f}°, yaw={yaw_deg:.1f}°')\n",
    "\n",
    "            # Draw gaze without angle text\n",
-    "            draw_gaze(image, bbox, pitch, yaw, draw_angles=False)\n",
+    "            draw_gaze(image, face.bbox, pitch, yaw, draw_angles=False)\n",
    "\n",
    "    # Convert BGR to RGB for display\n",
    "    original_rgb = cv2.cvtColor(original, cv2.COLOR_BGR2RGB)\n",
@@ -249,7 +248,7 @@
 ],
 "metadata": {
  "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
@@ -263,7 +262,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.10.0"
+   "version": "3.13.5"
  }
 },
 "nbformat": 4,
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "uniface"
-version = "1.5.3"
+version = "1.6.0"
 description = "UniFace: A Comprehensive Library for Face Detection, Recognition, Landmark Analysis, Face Parsing, Gaze Estimation, Age, and Gender Detection"
 readme = "README.md"
 license = { text = "MIT" }
@@ -9,7 +9,7 @@ maintainers = [
    { name = "Yakhyokhuja Valikhujaev", email = "yakhyo9696@gmail.com" },
 ]

-requires-python = ">=3.10,<3.14"
+requires-python = ">=3.11,<3.14"
 keywords = [
    "face-detection",
    "face-recognition",
@@ -34,7 +34,6 @@ classifiers = [
    "License :: OSI Approved :: MIT License",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
@@ -73,7 +72,7 @@ uniface = ["py.typed"]

 [tool.ruff]
 line-length = 120
-target-version = "py310"
+target-version = "py311"
 exclude = [
    ".git",
    ".ruff_cache",
--- a/scripts/README.md
+++ b/scripts/README.md
@@ -7,6 +7,7 @@ Scripts for testing UniFace features.
 | Script | Description |
 |--------|-------------|
 | `run_detection.py` | Face detection on image or webcam |
+| `run_anonymization.py` | Face anonymization/blurring for privacy |
 | `run_age_gender.py` | Age and gender prediction |
 | `run_emotion.py` | Emotion detection (7 or 8 emotions) |
 | `run_gaze_estimation.py` | Gaze direction estimation |
@@ -26,6 +27,11 @@ Scripts for testing UniFace features.
 python scripts/run_detection.py --image assets/test.jpg
 python scripts/run_detection.py --webcam

+# Face anonymization
+python scripts/run_anonymization.py --image assets/test.jpg --method pixelate
+python scripts/run_anonymization.py --webcam --method gaussian
+python scripts/run_anonymization.py --image photo.jpg --method pixelate --pixel-blocks 5
+
 # Age and gender
 python scripts/run_age_gender.py --image assets/test.jpg
 python scripts/run_age_gender.py --webcam
--- a/scripts/run_anonymization.py
+++ b/scripts/run_anonymization.py
@@ -0,0 +1,207 @@
+# Face anonymization/blurring for privacy
+# Usage: python run_anonymization.py --image path/to/image.jpg --method pixelate
+#        python run_anonymization.py --webcam --method gaussian
+
+import argparse
+import os
+
+import cv2
+
+from uniface import RetinaFace
+from uniface.privacy import BlurFace
+
+
+def process_image(
+    detector,
+    blurrer: BlurFace,
+    image_path: str,
+    save_dir: str = 'outputs',
+    show_detections: bool = False,
+):
+    """Process a single image."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    # Detect faces
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    # Optionally draw detection boxes before blurring
+    if show_detections and faces:
+        from uniface.visualization import draw_detections
+
+        preview = image.copy()
+        bboxes = [face['bbox'] for face in faces]
+        scores = [face['confidence'] for face in faces]
+        landmarks = [face['landmarks'] for face in faces]
+        draw_detections(preview, bboxes, scores, landmarks)
+
+        # Show preview
+        cv2.imshow('Detections (Press any key to continue)', preview)
+        cv2.waitKey(0)
+        cv2.destroyAllWindows()
+
+    # Anonymize faces
+    if faces:
+        anonymized = blurrer.anonymize(image, faces)
+    else:
+        anonymized = image
+
+    # Save output
+    os.makedirs(save_dir, exist_ok=True)
+    basename = os.path.splitext(os.path.basename(image_path))[0]
+    output_path = os.path.join(save_dir, f'{basename}_anonymized.jpg')
+    cv2.imwrite(output_path, anonymized)
+    print(f'Output saved: {output_path}')
+
+
+def run_webcam(detector, blurrer: BlurFace):
+    """Run real-time anonymization on webcam."""
+    cap = cv2.VideoCapture(0)
+    if not cap.isOpened():
+        print('Cannot open webcam')
+        return
+
+    print("Press 'q' to quit")
+
+    while True:
+        ret, frame = cap.read()
+        frame = cv2.flip(frame, 1)  # mirror for natural interaction
+        if not ret:
+            break
+
+        # Detect and anonymize
+        faces = detector.detect(frame)
+        if faces:
+            frame = blurrer.anonymize(frame, faces, inplace=True)
+
+        # Display info
+        cv2.putText(
+            frame,
+            f'Faces blurred: {len(faces)} | Method: {blurrer.method}',
+            (10, 30),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.7,
+            (0, 255, 0),
+            2,
+        )
+
+        cv2.imshow('Face Anonymization (Press q to quit)', frame)
+
+        if cv2.waitKey(1) & 0xFF == ord('q'):
+            break
+
+    cap.release()
+    cv2.destroyAllWindows()
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description='Face anonymization using various blur methods',
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Anonymize image with pixelation (default)
+  python run_anonymization.py --image photo.jpg
+
+  # Use Gaussian blur with custom strength
+  python run_anonymization.py --image photo.jpg --method gaussian --blur-strength 5.0
+
+  # Real-time webcam anonymization
+  python run_anonymization.py --webcam --method pixelate
+
+  # Black boxes for maximum privacy
+  python run_anonymization.py --image photo.jpg --method blackout
+
+  # Custom pixelation intensity
+  python run_anonymization.py --image photo.jpg --method pixelate --pixel-blocks 5
+        """,
+    )
+
+    # Input/output
+    parser.add_argument('--image', type=str, help='Path to input image')
+    parser.add_argument('--webcam', action='store_true', help='Use webcam for real-time anonymization')
+    parser.add_argument('--save-dir', type=str, default='outputs', help='Output directory (default: outputs)')
+
+    # Blur method
+    parser.add_argument(
+        '--method',
+        type=str,
+        default='pixelate',
+        choices=['gaussian', 'pixelate', 'blackout', 'elliptical', 'median'],
+        help='Blur method (default: pixelate)',
+    )
+
+    # Method-specific parameters
+    parser.add_argument(
+        '--blur-strength',
+        type=float,
+        default=3.0,
+        help='Blur strength for gaussian/elliptical/median (default: 3.0)',
+    )
+    parser.add_argument(
+        '--pixel-blocks',
+        type=int,
+        default=20,
+        help='Number of pixel blocks for pixelate (default: 10, lower=more pixelated)',
+    )
+    parser.add_argument(
+        '--color',
+        type=str,
+        default='0,0,0',
+        help='Fill color for blackout as R,G,B (default: 0,0,0 for black)',
+    )
+    parser.add_argument('--margin', type=int, default=20, help='Margin for elliptical blur (default: 20)')
+
+    # Detection
+    parser.add_argument(
+        '--conf-thresh',
+        type=float,
+        default=0.5,
+        help='Detection confidence threshold (default: 0.5)',
+    )
+
+    # Visualization
+    parser.add_argument(
+        '--show-detections',
+        action='store_true',
+        help='Show detection boxes before blurring (image mode only)',
+    )
+
+    args = parser.parse_args()
+
+    # Validate input
+    if not args.image and not args.webcam:
+        parser.error('Either --image or --webcam must be specified')
+
+    # Parse color
+    color_values = [int(x) for x in args.color.split(',')]
+    if len(color_values) != 3:
+        parser.error('--color must be in format R,G,B (e.g., 0,0,0)')
+    color = tuple(color_values)
+
+    # Initialize detector
+    print(f'Initializing face detector (conf_thresh={args.conf_thresh})...')
+    detector = RetinaFace(conf_thresh=args.conf_thresh)
+
+    # Initialize blurrer
+    print(f'Initializing blur method: {args.method}')
+    blurrer = BlurFace(
+        method=args.method,
+        blur_strength=args.blur_strength,
+        pixel_blocks=args.pixel_blocks,
+        color=color,
+        margin=args.margin,
+    )
+
+    # Run
+    if args.webcam:
+        run_webcam(detector, blurrer)
+    else:
+        process_image(detector, blurrer, args.image, args.save_dir, args.show_detections)
+
+
+if __name__ == '__main__':
+    main()
--- a/scripts/run_spoofing.py
+++ b/scripts/run_spoofing.py
@@ -0,0 +1,201 @@
+# Face Anti-Spoofing Detection
+# Usage:
+#   Image: python run_spoofing.py --image path/to/image.jpg
+#   Video: python run_spoofing.py --video path/to/video.mp4
+#   Webcam: python run_spoofing.py --source 0
+
+import argparse
+import os
+from pathlib import Path
+
+import cv2
+import numpy as np
+
+from uniface import RetinaFace
+from uniface.constants import MiniFASNetWeights
+from uniface.spoofing import create_spoofer
+
+
+def draw_spoofing_result(
+    image: np.ndarray,
+    bbox: list,
+    label_idx: int,
+    score: float,
+    thickness: int = 2,
+) -> None:
+    """Draw bounding box with anti-spoofing result.
+
+    Args:
+        image: Input image to draw on.
+        bbox: Bounding box in [x1, y1, x2, y2] format.
+        label_idx: Prediction label index (0 = Fake, 1 = Real).
+        score: Confidence score (0.0 to 1.0).
+        thickness: Line thickness for bounding box.
+    """
+    x1, y1, x2, y2 = map(int, bbox[:4])
+
+    # Color based on result (green for real, red for fake)
+    is_real = label_idx == 1
+    color = (0, 255, 0) if is_real else (0, 0, 255)
+
+    # Draw bounding box
+    cv2.rectangle(image, (x1, y1), (x2, y2), color, thickness)
+
+    # Prepare label
+    label = 'Real' if is_real else 'Fake'
+    text = f'{label}: {score:.1%}'
+
+    # Draw label background
+    (tw, th), baseline = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2)
+    cv2.rectangle(image, (x1, y1 - th - 10), (x1 + tw + 10, y1), color, -1)
+
+    # Draw label text
+    cv2.putText(image, text, (x1 + 5, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2)
+
+
+def process_image(detector, spoofer, image_path: str, save_dir: str = 'outputs') -> None:
+    """Process a single image for face anti-spoofing detection."""
+    image = cv2.imread(image_path)
+    if image is None:
+        print(f"Error: Failed to load image from '{image_path}'")
+        return
+
+    # Detect faces
+    faces = detector.detect(image)
+    print(f'Detected {len(faces)} face(s)')
+
+    if not faces:
+        print('No faces detected in the image.')
+        return
+
+    # Run anti-spoofing on each face
+    for i, face in enumerate(faces, 1):
+        label_idx, score = spoofer.predict(image, face['bbox'])
+        # label_idx: 0 = Fake, 1 = Real
+        label = 'Real' if label_idx == 1 else 'Fake'
+        print(f'  Face {i}: {label} ({score:.1%})')
+
+        # Draw result on image
+        draw_spoofing_result(image, face['bbox'], label_idx, score)
+
+    # Save output
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, f'{Path(image_path).stem}_spoofing.jpg')
+    cv2.imwrite(output_path, image)
+    print(f'Output saved: {output_path}')
+
+
+def process_video(detector, spoofer, source, save_dir: str = 'outputs') -> None:
+    """Process video or webcam stream for face anti-spoofing detection."""
+    # Handle webcam or video file
+    if isinstance(source, int) or source.isdigit():
+        cap = cv2.VideoCapture(int(source))
+        is_webcam = True
+        output_name = 'webcam_spoofing.mp4'
+    else:
+        cap = cv2.VideoCapture(source)
+        is_webcam = False
+        output_name = f'{Path(source).stem}_spoofing.mp4'
+
+    if not cap.isOpened():
+        print(f'Error: Failed to open video source: {source}')
+        return
+
+    # Get video properties
+    fps = int(cap.get(cv2.CAP_PROP_FPS)) if not is_webcam else 30
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+
+    # Setup video writer
+    os.makedirs(save_dir, exist_ok=True)
+    output_path = os.path.join(save_dir, output_name)
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    writer = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+    print("Processing video... Press 'q' to quit")
+    frame_count = 0
+
+    try:
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+
+            frame_count += 1
+
+            # Detect faces
+            faces = detector.detect(frame)
+
+            # Run anti-spoofing on each face
+            for face in faces:
+                label_idx, score = spoofer.predict(frame, face['bbox'])
+                draw_spoofing_result(frame, face['bbox'], label_idx, score)
+
+            # Write frame
+            writer.write(frame)
+
+            # Display frame
+            cv2.imshow('Face Anti-Spoofing', frame)
+            if cv2.waitKey(1) & 0xFF == ord('q'):
+                print('Stopped by user.')
+                break
+
+    finally:
+        cap.release()
+        writer.release()
+        cv2.destroyAllWindows()
+
+    print(f'Processed {frame_count} frames')
+    if not is_webcam:
+        print(f'Output saved: {output_path}')
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Face Anti-Spoofing Detection')
+    parser.add_argument('--image', type=str, help='Path to input image')
+    parser.add_argument('--video', type=str, help='Path to input video')
+    parser.add_argument('--source', type=str, help='Video source (0 for webcam)')
+    parser.add_argument(
+        '--model',
+        type=str,
+        default='v2',
+        choices=['v1se', 'v2'],
+        help='Model variant: v1se or v2 (default: v2)',
+    )
+    parser.add_argument('--scale', type=float, default=None, help='Custom crop scale (default: auto)')
+    parser.add_argument('--save_dir', type=str, default='outputs', help='Output directory')
+    args = parser.parse_args()
+
+    # Check that at least one input source is provided
+    if not any([args.image, args.video, args.source]):
+        parser.print_help()
+        print('\nError: Please provide --image, --video, or --source')
+        return
+
+    # Select model variant
+    model_name = MiniFASNetWeights.V1SE if args.model == 'v1se' else MiniFASNetWeights.V2
+
+    # Initialize models
+    print(f'Initializing models (MiniFASNet {args.model.upper()})...')
+    detector = RetinaFace()
+    spoofer = create_spoofer(model_name=model_name, scale=args.scale)
+
+    # Process input
+    if args.image:
+        if not os.path.exists(args.image):
+            print(f'Error: Image not found: {args.image}')
+            return
+        process_image(detector, spoofer, args.image, args.save_dir)
+
+    elif args.video:
+        if not os.path.exists(args.video):
+            print(f'Error: Video not found: {args.video}')
+            return
+        process_video(detector, spoofer, args.video, args.save_dir)
+
+    elif args.source:
+        process_video(detector, spoofer, args.source, args.save_dir)
+
+
+if __name__ == '__main__':
+    main()
--- a/uniface/init.py
+++ b/uniface/init.py
@@ -13,7 +13,7 @@

 __license__ = 'MIT'
 __author__ = 'Yakhyokhuja Valikhujaev'
-__version__ = '1.5.3'
+__version__ = '1.6.0'


 from uniface.face_utils import compute_similarity, face_alignment
@@ -40,7 +40,9 @@ from .detection import (
 from .gaze import MobileGaze, create_gaze_estimator
 from .landmark import Landmark106, create_landmarker
 from .parsing import BiSeNet, create_face_parser
+from .privacy import BlurFace, anonymize_faces
 from .recognition import ArcFace, MobileFace, SphereFace, create_recognizer
+from .spoofing import MiniFASNet, create_spoofer

 __all__ = [
    '__author__',
@@ -55,6 +57,7 @@ __all__ = [
    'create_gaze_estimator',
    'create_landmarker',
    'create_recognizer',
+    'create_spoofer',
    'detect_faces',
    'list_available_detectors',
    # Detection models
@@ -74,6 +77,11 @@ __all__ = [
    # Attribute models
    'AgeGender',
    'Emotion',
+    # Spoofing models
+    'MiniFASNet',
+    # Privacy
+    'BlurFace',
+    'anonymize_faces',
    # Utilities
    'compute_similarity',
    'draw_detections',
--- a/uniface/analyzer.py
+++ b/uniface/analyzer.py
@@ -36,41 +36,24 @@ class FaceAnalyzer:

    def analyze(self, image: np.ndarray) -> List[Face]:
        """Analyze faces in an image."""
-        detections = self.detector.detect(image)
-        Logger.debug(f'Detected {len(detections)} face(s)')
+        faces = self.detector.detect(image)
+        Logger.debug(f'Detected {len(faces)} face(s)')

-        faces = []
-        for idx, detection in enumerate(detections):
-            bbox = detection['bbox']
-            confidence = detection['confidence']
-            landmarks = detection['landmarks']
-
-            embedding = None
+        for idx, face in enumerate(faces):
            if self.recognizer is not None:
                try:
-                    embedding = self.recognizer.get_normalized_embedding(image, landmarks)
-                    Logger.debug(f'  Face {idx + 1}: Extracted embedding with shape {embedding.shape}')
+                    face.embedding = self.recognizer.get_normalized_embedding(image, face.landmarks)
+                    Logger.debug(f'  Face {idx + 1}: Extracted embedding with shape {face.embedding.shape}')
                except Exception as e:
                    Logger.warning(f'  Face {idx + 1}: Failed to extract embedding: {e}')

-            age, gender = None, None
            if self.age_gender is not None:
                try:
-                    gender, age = self.age_gender.predict(image, bbox)
-                    Logger.debug(f'  Face {idx + 1}: Age={age}, Gender={gender}')
+                    face.gender, face.age = self.age_gender.predict(image, face.bbox)
+                    Logger.debug(f'  Face {idx + 1}: Age={face.age}, Gender={face.gender}')
                except Exception as e:
                    Logger.warning(f'  Face {idx + 1}: Failed to predict age/gender: {e}')

-            face = Face(
-                bbox=bbox,
-                confidence=confidence,
-                landmarks=landmarks,
-                embedding=embedding,
-                age=age,
-                gender=gender,
-            )
-            faces.append(face)
-
        Logger.info(f'Analysis complete: {len(faces)} face(s) processed')
        return faces

--- a/uniface/constants.py
+++ b/uniface/constants.py
@@ -119,6 +119,20 @@ class ParsingWeights(str, Enum):
    RESNET34 = "parsing_resnet34"


+class MiniFASNetWeights(str, Enum):
+    """
+    MiniFASNet: Lightweight Face Anti-Spoofing models.
+    Trained on face anti-spoofing datasets.
+    https://github.com/yakhyo/face-anti-spoofing
+
+    Model Variants:
+    - V1SE: Uses scale=4.0 for face crop (squeese-and-excitation version)
+    - V2: Uses scale=2.7 for face crop (improved version)
+    """
+    V1SE = "minifasnet_v1se"
+    V2   = "minifasnet_v2"
+
+
 MODEL_URLS: Dict[Enum, str] = {
    # RetinaFace
    RetinaFaceWeights.MNET_025:      'https://github.com/yakhyo/uniface/releases/download/weights/retinaface_mv1_0.25.onnx',
@@ -161,6 +175,9 @@ MODEL_URLS: Dict[Enum, str] = {
    # Parsing
    ParsingWeights.RESNET18:         'https://github.com/yakhyo/face-parsing/releases/download/weights/resnet18.onnx',
    ParsingWeights.RESNET34:         'https://github.com/yakhyo/face-parsing/releases/download/weights/resnet34.onnx',
+    # Anti-Spoofing (MiniFASNet)
+    MiniFASNetWeights.V1SE:          'https://github.com/yakhyo/face-anti-spoofing/releases/download/weights/MiniFASNetV1SE.onnx',
+    MiniFASNetWeights.V2:            'https://github.com/yakhyo/face-anti-spoofing/releases/download/weights/MiniFASNetV2.onnx',
 }

 MODEL_SHA256: Dict[Enum, str] = {
@@ -205,6 +222,9 @@ MODEL_SHA256: Dict[Enum, str] = {
    # Face Parsing
    ParsingWeights.RESNET18:         '0d9bd318e46987c3bdbfacae9e2c0f461cae1c6ac6ea6d43bbe541a91727e33f',
    ParsingWeights.RESNET34:         '5b805bba7b5660ab7070b5a381dcf75e5b3e04199f1e9387232a77a00095102e',
+    # Anti-Spoofing (MiniFASNet)
+    MiniFASNetWeights.V1SE:          'ebab7f90c7833fbccd46d3a555410e78d969db5438e169b6524be444862b3676',
+    MiniFASNetWeights.V2:            'b32929adc2d9c34b9486f8c4c7bc97c1b69bc0ea9befefc380e4faae4e463907',
 }

 CHUNK_SIZE = 8192
--- a/uniface/detection/init.py
+++ b/uniface/detection/init.py
@@ -7,6 +7,8 @@ from typing import Any, Dict, List

 import numpy as np

+from uniface.face import Face
+
 from .base import BaseDetector
 from .retinaface import RetinaFace
 from .scrfd import SCRFD
@@ -16,7 +18,7 @@ from .yolov5 import YOLOv5Face
 _detector_cache: Dict[str, BaseDetector] = {}


-def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs) -> List[Dict[str, Any]]:
+def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs) -> List[Face]:
    """
    High-level face detection function.

@@ -26,18 +28,18 @@ def detect_faces(image: np.ndarray, method: str = 'retinaface', **kwargs) -> Lis
        **kwargs: Additional arguments passed to the detector.

    Returns:
-        List[Dict[str, Any]]: A list of dictionaries, where each dictionary represents a detected face and contains:
-            - 'bbox' (List[float]): [x1, y1, x2, y2] bounding box coordinates.
-            - 'confidence' (float): The confidence score of the detection.
-            - 'landmarks' (List[List[float]]): 5-point facial landmarks.
+        List[Face]: A list of Face objects, each containing:
+            - bbox (np.ndarray): [x1, y1, x2, y2] bounding box coordinates.
+            - confidence (float): The confidence score of the detection.
+            - landmarks (np.ndarray): 5-point facial landmarks with shape (5, 2).

    Example:
        >>> from uniface import detect_faces
        >>> image = cv2.imread("your_image.jpg")
        >>> faces = detect_faces(image, method='retinaface', conf_thresh=0.8)
        >>> for face in faces:
-        ...     print(f"Found face with confidence: {face['confidence']}")
-        ...     print(f"BBox: {face['bbox']}")
+        ...     print(f"Found face with confidence: {face.confidence}")
+        ...     print(f"BBox: {face.bbox}")
    """
    method_name = method.lower()

--- a/uniface/detection/base.py
+++ b/uniface/detection/base.py
@@ -7,6 +7,8 @@ from typing import Any, Dict, List

 import numpy as np

+from uniface.face import Face
+

 class BaseDetector(ABC):
    """
@@ -21,7 +23,7 @@ class BaseDetector(ABC):
        self.config = kwargs

    @abstractmethod
-    def detect(self, image: np.ndarray, **kwargs) -> List[Dict[str, Any]]:
+    def detect(self, image: np.ndarray, **kwargs) -> List[Face]:
        """
        Detect faces in an image.

@@ -30,18 +32,17 @@ class BaseDetector(ABC):
            **kwargs: Additional detection parameters

        Returns:
-            List[Dict[str, Any]]: List of detected faces, where each dictionary contains:
-                - 'bbox' (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
-                - 'confidence' (float): Detection confidence score (0.0 to 1.0)
-                - 'landmarks' (np.ndarray): Facial landmarks with shape (5, 2) for 5-point landmarks
-                  or (68, 2) for 68-point landmarks. Empty array if not supported.
+            List[Face]: List of detected Face objects, each containing:
+                - bbox (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - confidence (float): Detection confidence score (0.0 to 1.0)
+                - landmarks (np.ndarray): Facial landmarks with shape (5, 2) for 5-point landmarks

        Example:
            >>> faces = detector.detect(image)
            >>> for face in faces:
-            ...     bbox = face['bbox']  # np.ndarray with shape (4,)
-            ...     confidence = face['confidence']  # float
-            ...     landmarks = face['landmarks']  # np.ndarray with shape (5, 2)
+            ...     bbox = face.bbox  # np.ndarray with shape (4,)
+            ...     confidence = face.confidence  # float
+            ...     landmarks = face.landmarks  # np.ndarray with shape (5, 2)
        """
        pass

--- a/uniface/detection/retinaface.py
+++ b/uniface/detection/retinaface.py
@@ -2,7 +2,7 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo

-from typing import Any, Dict, List, Literal, Tuple
+from typing import Any, List, Literal, Tuple

 import numpy as np

@@ -14,6 +14,7 @@ from uniface.common import (
    resize_image,
 )
 from uniface.constants import RetinaFaceWeights
+from uniface.face import Face
 from uniface.log import Logger
 from uniface.model_store import verify_model_weights
 from uniface.onnx_utils import create_onnx_session
@@ -154,7 +155,7 @@ class RetinaFace(BaseDetector):
        max_num: int = 0,
        metric: Literal['default', 'max'] = 'max',
        center_weight: float = 2.0,
-    ) -> List[Dict[str, Any]]:
+    ) -> List[Face]:
        """
        Perform face detection on an input image and return bounding boxes and facial landmarks.

@@ -168,19 +169,19 @@ class RetinaFace(BaseDetector):
                when using the "default" metric. Defaults to 2.0.

        Returns:
-            List[Dict[str, Any]]: List of face detection dictionaries, each containing:
-                - 'bbox' (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
-                - 'confidence' (float): Detection confidence score (0.0 to 1.0)
-                - 'landmarks' (np.ndarray): 5-point facial landmarks with shape (5, 2)
+            List[Face]: List of Face objects, each containing:
+                - bbox (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - confidence (float): Detection confidence score (0.0 to 1.0)
+                - landmarks (np.ndarray): 5-point facial landmarks with shape (5, 2)

        Example:
            >>> faces = detector.detect(image)
            >>> for face in faces:
-            ...     bbox = face['bbox']  # np.ndarray with shape (4,)
-            ...     confidence = face['confidence']  # float
-            ...     landmarks = face['landmarks']  # np.ndarray with shape (5, 2)
+            ...     bbox = face.bbox  # np.ndarray with shape (4,)
+            ...     confidence = face.confidence  # float
+            ...     landmarks = face.landmarks  # np.ndarray with shape (5, 2)
            ...     # Can pass landmarks directly to recognition
-            ...     embedding = recognizer.get_normalized_embedding(image, landmarks)
+            ...     embedding = recognizer.get_normalized_embedding(image, face.landmarks)
        """

        original_height, original_width = image.shape[:2]
@@ -229,12 +230,12 @@ class RetinaFace(BaseDetector):

        faces = []
        for i in range(detections.shape[0]):
-            face_dict = {
-                'bbox': detections[i, :4],
-                'confidence': float(detections[i, 4]),
-                'landmarks': landmarks[i],
-            }
-            faces.append(face_dict)
+            face = Face(
+                bbox=detections[i, :4],
+                confidence=float(detections[i, 4]),
+                landmarks=landmarks[i],
+            )
+            faces.append(face)

        return faces

@@ -350,19 +351,12 @@ if __name__ == '__main__':

        # Process each detected face
        for face in faces:
-            # Extract bbox and landmarks from dictionary
-            bbox = face['bbox']  # [x1, y1, x2, y2]
-            landmarks = face['landmarks']  # [[x1, y1], [x2, y2], ...]
-            confidence = face['confidence']
+            # Extract bbox and landmarks from Face object
+            draw_bbox(frame, face.bbox, face.confidence)

-            # Pass bbox and confidence separately
-            draw_bbox(frame, bbox, confidence)
-
-            # Convert landmarks to numpy array format if needed
-            if landmarks is not None and len(landmarks) > 0:
-                # Convert list of [x, y] pairs to numpy array
-                points = np.array(landmarks, dtype=np.float32)  # Shape: (5, 2)
-                draw_keypoints(frame, points)
+            # Draw landmarks if available
+            if face.landmarks is not None and len(face.landmarks) > 0:
+                draw_keypoints(frame, face.landmarks)

        # Display face count
        cv2.putText(
--- a/uniface/detection/scrfd.py
+++ b/uniface/detection/scrfd.py
@@ -2,13 +2,14 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo

-from typing import Any, Dict, List, Literal, Tuple
+from typing import Any, List, Literal, Tuple

 import cv2
 import numpy as np

 from uniface.common import distance2bbox, distance2kps, non_max_suppression, resize_image
 from uniface.constants import SCRFDWeights
+from uniface.face import Face
 from uniface.log import Logger
 from uniface.model_store import verify_model_weights
 from uniface.onnx_utils import create_onnx_session
@@ -193,7 +194,7 @@ class SCRFD(BaseDetector):
        max_num: int = 0,
        metric: Literal['default', 'max'] = 'max',
        center_weight: float = 2.0,
-    ) -> List[Dict[str, Any]]:
+    ) -> List[Face]:
        """
        Perform face detection on an input image and return bounding boxes and facial landmarks.

@@ -207,19 +208,19 @@ class SCRFD(BaseDetector):
                when using the "default" metric. Defaults to 2.0.

        Returns:
-            List[Dict[str, Any]]: List of face detection dictionaries, each containing:
-                - 'bbox' (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
-                - 'confidence' (float): Detection confidence score (0.0 to 1.0)
-                - 'landmarks' (np.ndarray): 5-point facial landmarks with shape (5, 2)
+            List[Face]: List of Face objects, each containing:
+                - bbox (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - confidence (float): Detection confidence score (0.0 to 1.0)
+                - landmarks (np.ndarray): 5-point facial landmarks with shape (5, 2)

        Example:
            >>> faces = detector.detect(image)
            >>> for face in faces:
-            ...     bbox = face['bbox']  # np.ndarray with shape (4,)
-            ...     confidence = face['confidence']  # float
-            ...     landmarks = face['landmarks']  # np.ndarray with shape (5, 2)
+            ...     bbox = face.bbox  # np.ndarray with shape (4,)
+            ...     confidence = face.confidence  # float
+            ...     landmarks = face.landmarks  # np.ndarray with shape (5, 2)
            ...     # Can pass landmarks directly to recognition
-            ...     embedding = recognizer.get_normalized_embedding(image, landmarks)
+            ...     embedding = recognizer.get_normalized_embedding(image, face.landmarks)
        """

        original_height, original_width = image.shape[:2]
@@ -280,12 +281,12 @@ class SCRFD(BaseDetector):

        faces = []
        for i in range(detections.shape[0]):
-            face_dict = {
-                'bbox': detections[i, :4],
-                'confidence': float(detections[i, 4]),
-                'landmarks': landmarks[i],
-            }
-            faces.append(face_dict)
+            face = Face(
+                bbox=detections[i, :4],
+                confidence=float(detections[i, 4]),
+                landmarks=landmarks[i],
+            )
+            faces.append(face)

        return faces

@@ -324,19 +325,12 @@ if __name__ == '__main__':

        # Process each detected face
        for face in faces:
-            # Extract bbox and landmarks from dictionary
-            bbox = face['bbox']  # [x1, y1, x2, y2]
-            landmarks = face['landmarks']  # [[x1, y1], [x2, y2], ...]
-            confidence = face['confidence']
+            # Extract bbox and landmarks from Face object
+            draw_bbox(frame, face.bbox, face.confidence)

-            # Pass bbox and confidence separately
-            draw_bbox(frame, bbox, confidence)
-
-            # Convert landmarks to numpy array format if needed
-            if landmarks is not None and len(landmarks) > 0:
-                # Convert list of [x, y] pairs to numpy array
-                points = np.array(landmarks, dtype=np.float32)  # Shape: (5, 2)
-                draw_keypoints(frame, points)
+            # Draw landmarks if available
+            if face.landmarks is not None and len(face.landmarks) > 0:
+                draw_keypoints(frame, face.landmarks)

        # Display face count
        cv2.putText(
--- a/uniface/detection/yolov5.py
+++ b/uniface/detection/yolov5.py
@@ -2,13 +2,14 @@
 # Author: Yakhyokhuja Valikhujaev
 # GitHub: https://github.com/yakhyo

-from typing import Any, Dict, List, Literal, Tuple
+from typing import Any, List, Literal, Tuple

 import cv2
 import numpy as np

 from uniface.common import non_max_suppression
 from uniface.constants import YOLOv5FaceWeights
+from uniface.face import Face
 from uniface.log import Logger
 from uniface.model_store import verify_model_weights
 from uniface.onnx_utils import create_onnx_session
@@ -259,7 +260,7 @@ class YOLOv5Face(BaseDetector):
        max_num: int = 0,
        metric: Literal['default', 'max'] = 'max',
        center_weight: float = 2.0,
-    ) -> List[Dict[str, Any]]:
+    ) -> List[Face]:
        """
        Perform face detection on an input image and return bounding boxes and facial landmarks.

@@ -273,19 +274,19 @@ class YOLOv5Face(BaseDetector):
                when using the "default" metric. Defaults to 2.0.

        Returns:
-            List[Dict[str, Any]]: List of face detection dictionaries, each containing:
-                - 'bbox' (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
-                - 'confidence' (float): Detection confidence score (0.0 to 1.0)
-                - 'landmarks' (np.ndarray): 5-point facial landmarks with shape (5, 2)
+            List[Face]: List of Face objects, each containing:
+                - bbox (np.ndarray): Bounding box coordinates with shape (4,) as [x1, y1, x2, y2]
+                - confidence (float): Detection confidence score (0.0 to 1.0)
+                - landmarks (np.ndarray): 5-point facial landmarks with shape (5, 2)

        Example:
            >>> faces = detector.detect(image)
            >>> for face in faces:
-            ...     bbox = face['bbox']  # np.ndarray with shape (4,)
-            ...     confidence = face['confidence']  # float
-            ...     landmarks = face['landmarks']  # np.ndarray with shape (5, 2)
+            ...     bbox = face.bbox  # np.ndarray with shape (4,)
+            ...     confidence = face.confidence  # float
+            ...     landmarks = face.landmarks  # np.ndarray with shape (5, 2)
            ...     # Can pass landmarks directly to recognition
-            ...     embedding = recognizer.get_normalized_embedding(image, landmarks)
+            ...     embedding = recognizer.get_normalized_embedding(image, face.landmarks)
        """

        original_height, original_width = image.shape[:2]
@@ -330,11 +331,11 @@ class YOLOv5Face(BaseDetector):

        faces = []
        for i in range(detections.shape[0]):
-            face_dict = {
-                'bbox': detections[i, :4],
-                'confidence': float(detections[i, 4]),
-                'landmarks': landmarks[i],
-            }
-            faces.append(face_dict)
+            face = Face(
+                bbox=detections[i, :4],
+                confidence=float(detections[i, 4]),
+                landmarks=landmarks[i],
+            )
+            faces.append(face)

        return faces
--- a/uniface/gaze/init.py
+++ b/uniface/gaze/init.py
@@ -51,8 +51,4 @@ def create_gaze_estimator(method: str = 'mobilegaze', **kwargs) -> BaseGazeEstim
        raise ValueError(f"Unsupported gaze estimation method: '{method}'. Available: {available}")


-__all__ = [
-    'create_gaze_estimator',
-    'MobileGaze',
-    'BaseGazeEstimator',
-]
+__all__ = ['create_gaze_estimator', 'MobileGaze', 'BaseGazeEstimator']
--- a/uniface/privacy/init.py
+++ b/uniface/privacy/init.py
@@ -0,0 +1,52 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from typing import Optional
+
+import numpy as np
+
+from .blur import BlurFace
+
+
+def anonymize_faces(
+    image: np.ndarray,
+    detector: Optional[object] = None,
+    method: str = 'pixelate',
+    blur_strength: float = 3.0,
+    pixel_blocks: int = 10,
+    conf_thresh: float = 0.5,
+    **kwargs,
+) -> np.ndarray:
+    """One-line face anonymization with automatic detection.
+
+    Args:
+        image (np.ndarray): Input image (BGR format).
+        detector: Face detector instance. Creates RetinaFace if None.
+        method (str): Blur method name. Defaults to 'pixelate'.
+        blur_strength (float): Blur intensity. Defaults to 3.0.
+        pixel_blocks (int): Block count for pixelate. Defaults to 10.
+        conf_thresh (float): Detection confidence threshold. Defaults to 0.5.
+        **kwargs: Additional detector arguments.
+
+    Returns:
+        np.ndarray: Anonymized image.
+
+    Example:
+        >>> from uniface.privacy import anonymize_faces
+        >>> anonymized = anonymize_faces(image, method='pixelate')
+    """
+    if detector is None:
+        try:
+            from uniface import RetinaFace
+
+            detector = RetinaFace(conf_thresh=conf_thresh, **kwargs)
+        except ImportError as err:
+            raise ImportError('Could not import RetinaFace. Please ensure UniFace is properly installed.') from err
+
+    faces = detector.detect(image)
+    blurrer = BlurFace(method=method, blur_strength=blur_strength, pixel_blocks=pixel_blocks)
+    return blurrer.anonymize(image, faces)
+
+
+__all__ = ['BlurFace', 'anonymize_faces']
--- a/uniface/privacy/blur.py
+++ b/uniface/privacy/blur.py
@@ -0,0 +1,193 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from typing import Dict, List, Tuple, Union
+
+import cv2
+import numpy as np
+
+__all__ = ['BlurFace']
+
+
+def _gaussian_blur(region: np.ndarray, strength: float = 3.0) -> np.ndarray:
+    """Apply Gaussian blur to a region."""
+    h, w = region.shape[:2]
+    kernel_size = max(3, int((min(h, w) / 7) * strength)) | 1
+    return cv2.GaussianBlur(region, (kernel_size, kernel_size), 0)
+
+
+def _median_blur(region: np.ndarray, strength: float = 3.0) -> np.ndarray:
+    """Apply median blur to a region."""
+    h, w = region.shape[:2]
+    kernel_size = max(3, int((min(h, w) / 7) * strength)) | 1
+    return cv2.medianBlur(region, kernel_size)
+
+
+def _pixelate_blur(region: np.ndarray, blocks: int = 10) -> np.ndarray:
+    """Apply pixelation to a region."""
+    h, w = region.shape[:2]
+    temp_h, temp_w = max(1, h // blocks), max(1, w // blocks)
+    temp = cv2.resize(region, (temp_w, temp_h), interpolation=cv2.INTER_LINEAR)
+    return cv2.resize(temp, (w, h), interpolation=cv2.INTER_NEAREST)
+
+
+def _blackout_blur(region: np.ndarray, color: Tuple[int, int, int] = (0, 0, 0)) -> np.ndarray:
+    """Replace region with solid color."""
+    return np.full_like(region, color)
+
+
+class EllipticalBlur:
+    """Elliptical blur with soft, feathered edges.
+
+    This blur applies Gaussian blur within an elliptical mask that follows
+    the natural oval shape of faces, requiring full image context for proper blending.
+
+    Args:
+        blur_strength (float): Blur intensity multiplier. Defaults to 3.0.
+        margin (int): Extra pixels to extend ellipse beyond bbox. Defaults to 20.
+    """
+
+    def __init__(self, blur_strength: float = 3.0, margin: int = 20):
+        self.blur_strength = blur_strength
+        self.margin = margin
+
+    def __call__(
+        self,
+        image: np.ndarray,
+        bboxes: List[Union[Tuple, List]],
+        inplace: bool = False,
+    ) -> np.ndarray:
+        if not inplace:
+            image = image.copy()
+
+        h, w = image.shape[:2]
+
+        for bbox in bboxes:
+            x1, y1, x2, y2 = map(int, bbox)
+            center_x, center_y = (x1 + x2) // 2, (y1 + y2) // 2
+            axes_x = (x2 - x1) // 2 + self.margin
+            axes_y = (y2 - y1) // 2 + self.margin
+
+            # Create soft elliptical mask
+            mask = np.zeros((h, w), dtype=np.float32)
+            cv2.ellipse(mask, (center_x, center_y), (axes_x, axes_y), 0, 0, 360, 255, -1)
+            mask = cv2.GaussianBlur(mask, (51, 51), 0) / 255.0
+            mask = mask[:, :, np.newaxis]
+
+            kernel_size = max(3, int((min(axes_y, axes_x) * 2 / 7) * self.blur_strength)) | 1
+            blurred = cv2.GaussianBlur(image, (kernel_size, kernel_size), 0)
+            image = (blurred * mask + image * (1 - mask)).astype(np.uint8)
+
+        return image
+
+
+class BlurFace:
+    """Face blurring with multiple anonymization methods.
+
+    Args:
+        method (str): Blur method - 'gaussian', 'pixelate', 'blackout', 'elliptical', or 'median'.
+            Defaults to 'pixelate'.
+        blur_strength (float): Intensity for gaussian/elliptical/median. Defaults to 3.0.
+        pixel_blocks (int): Block count for pixelate. Defaults to 10.
+        color (Tuple[int, int, int]): Fill color (BGR) for blackout. Defaults to (0, 0, 0).
+        margin (int): Edge margin for elliptical. Defaults to 20.
+
+    Example:
+        >>> blurrer = BlurFace(method='pixelate')
+        >>> anonymized = blurrer.anonymize(image, faces)
+    """
+
+    VALID_METHODS = {'gaussian', 'pixelate', 'blackout', 'elliptical', 'median'}
+
+    def __init__(
+        self,
+        method: str = 'pixelate',
+        blur_strength: float = 3.0,
+        pixel_blocks: int = 15,
+        color: Tuple[int, int, int] = (0, 0, 0),
+        margin: int = 20,
+    ):
+        self.method = method.lower()
+        self._blur_strength = blur_strength
+        self._pixel_blocks = pixel_blocks
+        self._color = color
+        self._margin = margin
+
+        if self.method not in self.VALID_METHODS:
+            raise ValueError(f"Invalid blur method: '{method}'. Choose from: {sorted(self.VALID_METHODS)}")
+
+        if self.method == 'elliptical':
+            self._elliptical = EllipticalBlur(blur_strength, margin)
+
+    def _blur_region(self, region: np.ndarray) -> np.ndarray:
+        if self.method == 'gaussian':
+            return _gaussian_blur(region, self._blur_strength)
+        elif self.method == 'median':
+            return _median_blur(region, self._blur_strength)
+        elif self.method == 'pixelate':
+            return _pixelate_blur(region, self._pixel_blocks)
+        elif self.method == 'blackout':
+            return _blackout_blur(region, self._color)
+
+    def anonymize(
+        self,
+        image: np.ndarray,
+        faces: List[Dict],
+        inplace: bool = False,
+    ) -> np.ndarray:
+        """Anonymize faces in an image.
+
+        Args:
+            image (np.ndarray): Input image (BGR format).
+            faces (List[Dict]): Face detections with 'bbox' key containing [x1, y1, x2, y2].
+            inplace (bool): Modify image in-place if True. Defaults to False.
+
+        Returns:
+            np.ndarray: Image with anonymized faces.
+        """
+        if not faces:
+            return image if inplace else image.copy()
+
+        bboxes = [face['bbox'] for face in faces]
+        return self.blur_regions(image, bboxes, inplace)
+
+    def blur_regions(
+        self,
+        image: np.ndarray,
+        bboxes: List[Union[Tuple, List]],
+        inplace: bool = False,
+    ) -> np.ndarray:
+        """Blur specific rectangular regions in an image.
+
+        Args:
+            image (np.ndarray): Input image (BGR format).
+            bboxes (List): Bounding boxes as [x1, y1, x2, y2].
+            inplace (bool): Modify image in-place if True. Defaults to False.
+
+        Returns:
+            np.ndarray: Image with blurred regions.
+        """
+        if not bboxes:
+            return image if inplace else image.copy()
+
+        if self.method == 'elliptical':
+            return self._elliptical(image, bboxes, inplace)
+
+        if not inplace:
+            image = image.copy()
+
+        h, w = image.shape[:2]
+
+        for bbox in bboxes:
+            x1, y1, x2, y2 = map(int, bbox)
+            x1, y1 = max(0, x1), max(0, y1)
+            x2, y2 = min(w, x2), min(h, y2)
+
+            if x2 > x1 and y2 > y1:
+                image[y1:y2, x1:x2] = self._blur_region(image[y1:y2, x1:x2])
+
+        return image
+
+    def __repr__(self) -> str:
+        return f"BlurFace(method='{self.method}')"
--- a/uniface/recognition/init.py
+++ b/uniface/recognition/init.py
@@ -55,10 +55,4 @@ def create_recognizer(method: str = 'arcface', **kwargs) -> BaseRecognizer:
        raise ValueError(f"Unsupported method: '{method}'. Available: {available}")


-__all__ = [
-    'create_recognizer',
-    'ArcFace',
-    'MobileFace',
-    'SphereFace',
-    'BaseRecognizer',
-]
+__all__ = ['create_recognizer', 'BaseRecognizer', 'ArcFace', 'MobileFace', 'SphereFace']
--- a/uniface/spoofing/init.py
+++ b/uniface/spoofing/init.py
@@ -0,0 +1,64 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from typing import Optional
+
+from uniface.constants import MiniFASNetWeights
+
+from .base import BaseSpoofer
+from .minifasnet import MiniFASNet
+
+__all__ = [
+    'BaseSpoofer',
+    'MiniFASNet',
+    'MiniFASNetWeights',
+    'create_spoofer',
+]
+
+
+def create_spoofer(
+    model_name: MiniFASNetWeights = MiniFASNetWeights.V2,
+    scale: Optional[float] = None,
+) -> MiniFASNet:
+    """
+    Factory function to create a face anti-spoofing model.
+
+    This is a convenience function that creates a MiniFASNet instance
+    with the specified model variant and optional custom scale.
+
+    Args:
+        model_name (MiniFASNetWeights): The model variant to use.
+            Options:
+                - MiniFASNetWeights.V2: Improved version (default), uses scale=2.7
+                - MiniFASNetWeights.V1SE: Squeeze-and-excitation version, uses scale=4.0
+            Defaults to MiniFASNetWeights.V2.
+        scale (Optional[float]): Custom crop scale factor for face region.
+            If None, uses the default scale for the selected model variant.
+
+    Returns:
+        MiniFASNet: An initialized face anti-spoofing model.
+
+    Example:
+        >>> from uniface.spoofing import create_spoofer, MiniFASNetWeights
+        >>> from uniface import RetinaFace
+        >>>
+        >>> # Create with default settings (V2 model)
+        >>> spoofer = create_spoofer()
+        >>>
+        >>> # Create with V1SE model
+        >>> spoofer = create_spoofer(model_name=MiniFASNetWeights.V1SE)
+        >>>
+        >>> # Create with custom scale
+        >>> spoofer = create_spoofer(scale=3.0)
+        >>>
+        >>> # Use with face detector
+        >>> detector = RetinaFace()
+        >>> faces = detector.detect(image)
+        >>> for face in faces:
+        ...     label_idx, score = spoofer.predict(image, face['bbox'])
+        ...     # label_idx: 0 = Fake, 1 = Real
+        ...     label = 'Real' if label_idx == 1 else 'Fake'
+        ...     print(f'{label}: {score:.2%}')
+    """
+    return MiniFASNet(model_name=model_name, scale=scale)
--- a/uniface/spoofing/base.py
+++ b/uniface/spoofing/base.py
@@ -0,0 +1,117 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from abc import ABC, abstractmethod
+from typing import List, Tuple, Union
+
+import numpy as np
+
+
+class BaseSpoofer(ABC):
+    """
+    Abstract base class for all face anti-spoofing models.
+
+    This class defines the common interface that all anti-spoofing models must implement,
+    ensuring consistency across different spoofing detection methods. Anti-spoofing models
+    detect whether a face is real (live person) or fake (photo, video, mask, etc.).
+
+    The prediction returns a tuple of (label_idx, score):
+        - label_idx: 0 = Fake (spoof), 1 = Real (live)
+        - score: Confidence score for the predicted label (0.0 to 1.0)
+    """
+
+    @abstractmethod
+    def _initialize_model(self) -> None:
+        """
+        Initialize the underlying model for inference.
+
+        This method should handle loading model weights, creating the
+        inference session (e.g., ONNX Runtime), and any necessary
+        setup procedures to prepare the model for prediction.
+
+        Raises:
+            RuntimeError: If the model fails to load or initialize.
+        """
+        raise NotImplementedError('Subclasses must implement the _initialize_model method.')
+
+    @abstractmethod
+    def preprocess(self, image: np.ndarray, bbox: Union[List, np.ndarray]) -> np.ndarray:
+        """
+        Preprocess the input image for model inference.
+
+        This method should crop the face region using the bounding box,
+        resize it to the model's expected input size, and normalize
+        the pixel values as required by the model.
+
+        Args:
+            image (np.ndarray): Input image in BGR format with shape (H, W, C).
+            bbox (Union[List, np.ndarray]): Face bounding box in [x1, y1, x2, y2] format.
+
+        Returns:
+            np.ndarray: The preprocessed image tensor ready for inference,
+                        typically with shape (1, C, H, W).
+        """
+        raise NotImplementedError('Subclasses must implement the preprocess method.')
+
+    @abstractmethod
+    def postprocess(self, outputs: np.ndarray) -> Tuple[int, float]:
+        """
+        Postprocess raw model outputs into prediction result.
+
+        This method takes the raw output from the model's inference and
+        converts it into a label index and confidence score.
+
+        Args:
+            outputs (np.ndarray): Raw outputs from the model inference (logits).
+
+        Returns:
+            Tuple[int, float]: A tuple of (label_idx, score) where:
+                - label_idx: 0 = Fake (spoof), 1 = Real (live)
+                - score: Confidence score for the predicted label (0.0 to 1.0)
+        """
+        raise NotImplementedError('Subclasses must implement the postprocess method.')
+
+    @abstractmethod
+    def predict(self, image: np.ndarray, bbox: Union[List, np.ndarray]) -> Tuple[int, float]:
+        """
+        Perform end-to-end anti-spoofing prediction on a face.
+
+        This method orchestrates the full pipeline: preprocessing the input,
+        running inference, and postprocessing to return the prediction.
+
+        Args:
+            image (np.ndarray): Input image in BGR format containing the face.
+            bbox (Union[List, np.ndarray]): Face bounding box in [x1, y1, x2, y2] format.
+                This is typically obtained from a face detector.
+
+        Returns:
+            Tuple[int, float]: A tuple of (label_idx, score) where:
+                - label_idx: 0 = Fake (spoof), 1 = Real (live)
+                - score: Confidence score for the predicted label (0.0 to 1.0)
+
+        Example:
+            >>> spoofer = MiniFASNet()
+            >>> detector = RetinaFace()
+            >>> faces = detector.detect(image)
+            >>> for face in faces:
+            ...     label_idx, score = spoofer.predict(image, face['bbox'])
+            ...     label = 'Real' if label_idx == 1 else 'Fake'
+            ...     print(f'{label}: {score:.2%}')
+        """
+        raise NotImplementedError('Subclasses must implement the predict method.')
+
+    def __call__(self, image: np.ndarray, bbox: Union[List, np.ndarray]) -> Tuple[int, float]:
+        """
+        Provides a convenient, callable shortcut for the `predict` method.
+
+        Args:
+            image (np.ndarray): Input image in BGR format.
+            bbox (Union[List, np.ndarray]): Face bounding box in [x1, y1, x2, y2] format.
+
+        Returns:
+            Tuple[int, float]: A tuple of (label_idx, score) where:
+                - label_idx: 0 = Fake (spoof), 1 = Real (live)
+                - score: Confidence score for the predicted label (0.0 to 1.0)
+        """
+        return self.predict(image, bbox)
--- a/uniface/spoofing/minifasnet.py
+++ b/uniface/spoofing/minifasnet.py
@@ -0,0 +1,225 @@
+# Copyright 2025 Yakhyokhuja Valikhujaev
+# Author: Yakhyokhuja Valikhujaev
+# GitHub: https://github.com/yakhyo
+
+from typing import List, Optional, Tuple, Union
+
+import cv2
+import numpy as np
+
+from uniface.constants import MiniFASNetWeights
+from uniface.log import Logger
+from uniface.model_store import verify_model_weights
+from uniface.onnx_utils import create_onnx_session
+
+from .base import BaseSpoofer
+
+__all__ = ['MiniFASNet']
+
+# Default crop scales for each model variant
+DEFAULT_SCALES = {
+    MiniFASNetWeights.V1SE: 4.0,
+    MiniFASNetWeights.V2: 2.7,
+}
+
+
+class MiniFASNet(BaseSpoofer):
+    """
+    MiniFASNet: Lightweight Face Anti-Spoofing with ONNX Runtime.
+
+    MiniFASNet is a face anti-spoofing model that detects whether a face is real
+    (live person) or fake (photo, video replay, mask, etc.). It supports two model
+    variants: V1SE (with squeeze-and-excitation) and V2 (improved version).
+
+    The model takes a face region cropped from the image using a bounding box
+    and predicts whether it's a real or spoofed face.
+
+    Reference:
+        https://github.com/yakhyo/face-anti-spoofing
+
+    Args:
+        model_name (MiniFASNetWeights): The enum specifying the model variant to load.
+            Options: V1SE (scale=4.0), V2 (scale=2.7).
+            Defaults to `MiniFASNetWeights.V2`.
+        scale (Optional[float]): Custom crop scale factor for face region.
+            If None, uses the default scale for the selected model variant.
+            V1SE uses 4.0, V2 uses 2.7.
+
+    Attributes:
+        scale (float): Crop scale factor for face region extraction.
+        input_size (Tuple[int, int]): Model input dimensions (width, height).
+
+    Example:
+        >>> from uniface.spoofing import MiniFASNet
+        >>> from uniface import RetinaFace
+        >>>
+        >>> detector = RetinaFace()
+        >>> spoofer = MiniFASNet()
+        >>>
+        >>> # Detect faces and check if they are real
+        >>> faces = detector.detect(image)
+        >>> for face in faces:
+        ...     label_idx, score = spoofer.predict(image, face['bbox'])
+        ...     # label_idx: 0 = Fake, 1 = Real
+        ...     label = 'Real' if label_idx == 1 else 'Fake'
+        ...     print(f'{label}: {score:.2%}')
+    """
+
+    def __init__(
+        self,
+        model_name: MiniFASNetWeights = MiniFASNetWeights.V2,
+        scale: Optional[float] = None,
+    ) -> None:
+        Logger.info(f'Initializing MiniFASNet with model={model_name.name}')
+
+        # Use default scale for the model variant if not specified
+        self.scale = scale if scale is not None else DEFAULT_SCALES.get(model_name, 2.7)
+
+        self.model_path = verify_model_weights(model_name)
+        self._initialize_model()
+
+    def _initialize_model(self) -> None:
+        """
+        Initialize the ONNX model from the stored model path.
+
+        Raises:
+            RuntimeError: If the model fails to load or initialize.
+        """
+        try:
+            self.session = create_onnx_session(self.model_path)
+
+            # Get input configuration
+            input_cfg = self.session.get_inputs()[0]
+            self.input_name = input_cfg.name
+            # Input shape is (batch, channels, height, width) - we need (width, height)
+            self.input_size = tuple(input_cfg.shape[2:4][::-1])  # (width, height)
+
+            # Get output configuration
+            output_cfg = self.session.get_outputs()[0]
+            self.output_name = output_cfg.name
+
+            Logger.info(f'MiniFASNet initialized with input size {self.input_size}, scale={self.scale}')
+
+        except Exception as e:
+            Logger.error(f"Failed to load MiniFASNet model from '{self.model_path}'", exc_info=True)
+            raise RuntimeError(f'Failed to initialize MiniFASNet model: {e}') from e
+
+    def _xyxy_to_xywh(self, bbox: Union[List, np.ndarray]) -> List[int]:
+        """Convert bounding box from [x1, y1, x2, y2] to [x, y, w, h] format."""
+        x1, y1, x2, y2 = bbox[:4]
+        return [int(x1), int(y1), int(x2 - x1), int(y2 - y1)]
+
+    def _crop_face(self, image: np.ndarray, bbox_xywh: List[int]) -> np.ndarray:
+        """
+        Crop and resize face region from image using scale factor.
+
+        The crop is centered on the face bounding box and scaled to capture
+        more context around the face, which is important for anti-spoofing.
+
+        Args:
+            image: Input image in BGR format.
+            bbox_xywh: Face bounding box in [x, y, w, h] format.
+
+        Returns:
+            Cropped and resized face region.
+        """
+        src_h, src_w = image.shape[:2]
+        x, y, box_w, box_h = bbox_xywh
+
+        # Calculate the scale to apply based on image and face size
+        scale = min((src_h - 1) / box_h, (src_w - 1) / box_w, self.scale)
+        new_w = box_w * scale
+        new_h = box_h * scale
+
+        # Calculate center of the bounding box
+        center_x = x + box_w / 2
+        center_y = y + box_h / 2
+
+        # Calculate new bounding box coordinates
+        x1 = max(0, int(center_x - new_w / 2))
+        y1 = max(0, int(center_y - new_h / 2))
+        x2 = min(src_w - 1, int(center_x + new_w / 2))
+        y2 = min(src_h - 1, int(center_y + new_h / 2))
+
+        # Crop and resize
+        cropped = image[y1 : y2 + 1, x1 : x2 + 1]
+        resized = cv2.resize(cropped, self.input_size)
+
+        return resized
+
+    def preprocess(self, image: np.ndarray, bbox: Union[List, np.ndarray]) -> np.ndarray:
+        """
+        Preprocess the input image for model inference.
+
+        Crops the face region, converts to float32, and arranges
+        dimensions for the model (NCHW format).
+
+        Args:
+            image: Input image in BGR format with shape (H, W, C).
+            bbox: Face bounding box in [x1, y1, x2, y2] format.
+
+        Returns:
+            Preprocessed image tensor with shape (1, C, H, W).
+        """
+        # Convert bbox format
+        bbox_xywh = self._xyxy_to_xywh(bbox)
+
+        # Crop and resize face region
+        face = self._crop_face(image, bbox_xywh)
+
+        # Convert to float32 (no normalization needed for this model)
+        face = face.astype(np.float32)
+
+        # HWC -> CHW -> NCHW
+        face = np.transpose(face, (2, 0, 1))
+        face = np.expand_dims(face, axis=0)
+
+        return face
+
+    def _softmax(self, x: np.ndarray) -> np.ndarray:
+        """Apply softmax to logits along axis 1."""
+        e_x = np.exp(x - np.max(x, axis=1, keepdims=True))
+        return e_x / e_x.sum(axis=1, keepdims=True)
+
+    def postprocess(self, outputs: np.ndarray) -> Tuple[int, float]:
+        """
+        Postprocess raw model outputs into prediction result.
+
+        Applies softmax to convert logits to probabilities and
+        returns the predicted label index and confidence score.
+
+        Args:
+            outputs: Raw outputs from the model inference (logits).
+
+        Returns:
+            Tuple[int, float]: A tuple of (label_idx, score) where:
+                - label_idx: 0 = Fake (spoof), 1 = Real (live)
+                - score: Confidence score for the predicted label (0.0 to 1.0)
+        """
+        probs = self._softmax(outputs)
+        label_idx = int(np.argmax(probs))
+        score = float(probs[0, label_idx])
+
+        return label_idx, score
+
+    def predict(self, image: np.ndarray, bbox: Union[List, np.ndarray]) -> Tuple[int, float]:
+        """
+        Perform end-to-end anti-spoofing prediction on a face.
+
+        Args:
+            image: Input image in BGR format containing the face.
+            bbox: Face bounding box in [x1, y1, x2, y2] format.
+
+        Returns:
+            Tuple[int, float]: A tuple of (label_idx, score) where:
+                - label_idx: 0 = Fake (spoof), 1 = Real (live)
+                - score: Confidence score for the predicted label (0.0 to 1.0)
+        """
+        # Preprocess
+        input_tensor = self.preprocess(image, bbox)
+
+        # Run inference
+        outputs = self.session.run([self.output_name], {self.input_name: input_tensor})[0]
+
+        # Postprocess and return
+        return self.postprocess(outputs)
Author	SHA1	Message	Date
Yakhyokhuja Valikhujaev	7c98a60d26	fix: Python 3.10 does not support tomlib (#43 )	2025-12-24 00:51:36 +09:00
Yakhyokhuja Valikhujaev	d97a3b2cb2	Merge pull request #42 from yakhyo/feat/standardize-outputs feat: Standardize detection output and several other updates	2025-12-24 00:38:32 +09:00
yakhyo	2200ba063c	docs: Update related docs and ruff formatting	2025-12-24 00:34:24 +09:00
yakhyo	9bcbfa65c2	feat: Update detection module output to datalasses	2025-12-24 00:00:00 +09:00
yakhyo	96306a0910	feat: Update github actions	2025-12-23 23:59:15 +09:00
Yakhyokhuja Valikhujaev	3389aa3e4c	feat: Add MiniFasNet for Face Anti Spoofing (#41 )	2025-12-20 22:34:47 +09:00
Yakhyokhuja Valikhujaev	b282e6ccc1	docs: Update related docs to face anonymization (#40 )	2025-12-20 21:27:26 +09:00
Yakhyokhuja Valikhujaev	d085c6a822	feat: Add face blurring for privacy (#39 ) * feat: Add face blurring for privacy * chore: Revert back the version	2025-12-20 20:57:42 +09:00