Metadata-Version: 2.4
Name: ctu_face
Version: 0.1.1
Summary: A simple, kid-friendly face recognition library for Python.
Author-email: omar algamel <omeralgamel@gmail.com>
Project-URL: Homepage, https://github.com/yourusername/ctu_face
Project-URL: Bug Tracker, https://github.com/yourusername/ctu_face/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: opencv-contrib-python
Requires-Dist: numpy
Requires-Dist: tqdm
Dynamic: license-file

# ctu_face

A professional, easy-to-use, and lightweight Python library for face recognition. Designed to be simple enough for kids and beginners, yet robust enough for production!

## Features
- **Plug and Play**: Pre-bundled with lightweight ONNX face models. No complex setup or manual model downloads required.
- **Smart "Unknown" Handling**: Automatically loads bundled random faces to prevent false positives and distinguish the user from strangers.
- **Versatile**: Supports live webcams, recorded videos, and single image scans out of the box.

## Installation

```bash
pip install ctu_face
```

## Usage Examples

### 1. Live Webcam Recognition
```python
from ctu_face import FaceAI

# Initialize the AI. It automatically loads unknown faces for accuracy!
ai = FaceAI()

# Add people you want to recognize
ai.add_person("Alice", "alice.jpg")
ai.add_person("Bob", "bob.jpg")

# Start the webcam! (Use camera_id=1 for secondary cameras)
ai.start_webcam(camera_id=0)
```

### 2. Check a Single Image
```python
from ctu_face import FaceAI

ai = FaceAI()
ai.add_person("Alice", "alice.jpg")

# Scan a single image and show the result
ai.check_image("group_photo.jpg")
```

### 3. Check a Video File
```python
from ctu_face import FaceAI

ai = FaceAI()
ai.add_person("Alice", "alice.jpg")

# Scan a recorded video
ai.check_video("party_video.mp4")
```

## Requirements
- `opencv-contrib-python`
- `numpy`
- `tqdm` (for progress bars)

## License
MIT License
