An open API service indexing awesome lists of open source software.

https://github.com/harizonelopez/face-detector

This project is a real-time face detection application using OpenCV's deep learning-based face detector. It captures faces from a webcam feed, detects faces with high accuracy using a pre-trained Caffe model, and saves the detected faces as image files labeled with the user's name.
https://github.com/harizonelopez/face-detector

cdn dnn numpy opencv python3

Last synced: about 2 months ago
JSON representation

This project is a real-time face detection application using OpenCV's deep learning-based face detector. It captures faces from a webcam feed, detects faces with high accuracy using a pre-trained Caffe model, and saves the detected faces as image files labeled with the user's name.

Awesome Lists containing this project

README

          

# Real-Time Face Detection System

This project demonstrates real-time face detection using OpenCV's DNN (Deep Neural Network) module and a pre-trained Caffe model. It captures video from your webcam, detects faces in each frame, and displays bounding boxes and confidence scores.

---

## 📸 Demo

*Example only. Actual live webcam will be used.*

---

## ⚙️ Requirements

Make sure you have the following installed:

- Python 3.6+
- flask 3.1+
- OpenCV with DNN module
- NumPy
- setuptools

You can install the dependencies with:

```bash
pip install -r requirements.txt
```

---

## Activate the virtual environment

### On Windows (PowerShell)
```bash
venv\scripts\activate
```

### On macOS/Linux
```bash
source venv/bin/activate
```

---

## 🧠 Model Details

This project uses a deep learning model based on a ResNet10 SSD (Single Shot Multibox Detector) architecture.

### Download the required files:
```bash
`deploy.prototxt`
`res10_300x300_ssd_iter_140000.caffemodel`
```

#### Rename or place them in the same folder as:
```bash
face_model.caffemodel
deploy.prototxt
```

---

## 🚀 How to Run

```bash
python face_detection.py
```

Press `q` to quit the webcam window.

---

## 🎯 Features

- ✅ Real-time face detection from webcam

- ✅ Confidence score display

- ✅ Bounding boxes around detected faces

- ✅ Frames-per-second (FPS) calculation

- ✅ Input validation (model file and webcam check)

- ✅ Auto-clamping to prevent frame-bound errors

- ✅ Train LBPH face recognizer

- ✅ Recognize faces live from webcam

---

## 📌 Notes

- Works best in well-lit environments.

- Accuracy threshold can be modified from `confidence > 0.5` in the `face_detector.py`.

---

## 👨‍💻 Author

- GitHub: @harizonelopez
- Email: @harizonelopez23@gmail.com

---

## 📜 License

MIT License

---