Facial Recognition System from Scratch with OpenCV and TensorFlow

Introduction

This project is a facial recognition system built from scratch. It uses OpenCV for face detection and TensorFlow to train a model based on convolutional neural networks (CNNs).
The main objective is to offer a simple but effective solution for applications such as security, attendance management, or automated access.

---

Main features

Face Detection: OpenCV's cascading algorithms for fast and accurate detection.

Model training: Convolutional neural networks (CNNs) using TensorFlow to classify and recognize faces.

Real-time recognition: Live implementation via webcam or video stream.

Modularity: Code easily customized for specific applications.

---

Facility

Follow these steps to configure and run the project:

1. Clone the GitHub repository:

git clone https://github.com/FredyHoundayi/Computer-Vision-CV-Deep-Learning-DL-.git
cd Computer-Vision-CV-Deep-Learning-DL-

2. Create a virtual environment and activate it:

python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate

3. Install the necessary dependencies:

pip install -r requirements.txt

---

Use

1. Data collection:
   Use the creation_data.py script to automatically collect training images:

python creation_data.py

2. Model training:
   Train a facial recognition model with TensorFlow:

python model6.py

3. Real-time recognition:
   Run the script to identify faces in real time:

python recognition.py

---

Code snippets

Example configuration for data collection:

import cv2

camera = cv2.VideoCapture(0)
while True:
_, frame = camera.read()
cv2.imshow("Capture", frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
camera.release()
cv2.destroyAllWindows()

---

Possible applications

This system can be integrated into various fields, such as:

Secure access control.

Automated monitoring.

Presence management in a company or educational establishment.

---

Contributions

Contributions are welcome! If you'd like to improve this project or suggest new features, please submit a pull request or open an issue on the GitHub repository.

---

License

This project is licensed under the MIT License. See the LICENSE file for details.