Face Recognition Project

This repository contains the implementation of a face recognition model that I developed during my second year of college. The project utilizes Python and several powerful libraries to recognize and manipulate faces in images and real-time video feeds.

Overview

This face recognition project is built using the following key libraries:

• OpenCV: For image processing and computer vision tasks.
• NumPy: For numerical computations.
• face_recognition: For state-of-the-art face recognition with deep learning.

The model achieves an accuracy of 99.38% on the Labeled Faces in the Wild benchmark.

Features

1. Find Faces in Pictures

Detects all faces in a given image.

import face_recognition

image = face_recognition.load_image_file("your_file.jpg")
face_locations = face_recognition.face_locations(image)

2. Find and Manipulate Facial Features Identifies the locations and outlines of each person's eyes, nose, mouth, and chin.

import face_recognition

image = face_recognition.load_image_file("your_file.jpg")
face_landmarks_list = face_recognition.face_landmarks(image)

3. Identify Faces in Pictures Recognizes known faces from a set of images.

import face_recognition

known_image = face_recognition.load_image_file("known_person.jpg")
unknown_image = face_recognition.load_image_file("unknown_person.jpg")

known_encoding = face_recognition.face_encodings(known_image)[0]
unknown_encoding = face_recognition.face_encodings(unknown_image)[0]

results = face_recognition.compare_faces([known_encoding], unknown_encoding)

4. Real-Time Face Recognition Performs face recognition in real-time using a webcam feed

import face_recognition
import cv2

video_capture = cv2.VideoCapture(0)

while True:
    ret, frame = video_capture.read()
    rgb_frame = frame[:, :, ::-1]
    face_locations = face_recognition.face_locations(rgb_frame)
    face_encodings = face_recognition.face_encodings(rgb_frame, face_locations)

    for (top, right, bottom, left), face_encoding in zip(face_locations, face_encodings):
        # Add your known face encodings and names here
        matches = face_recognition.compare_faces(known_face_encodings, face_encoding)
        name = "Unknown"

        if True in matches:
            first_match_index = matches.index(True)
            name = known_face_names[first_match_index]

        cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
        cv2.putText(frame, name, (left + 6, bottom - 6), cv2.FONT_HERSHEY_DUPLEX, 0.5, (255, 255, 255), 1)

    cv2.imshow('Video', frame)

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

video_capture.release()
cv2.destroyAllWindows()

Installation

Prerequisites Python 3.3+ or Python 2.7 macOS, Linux, or Windows (limited support) Install Required Libraries Install dlib and its Python bindings:

Installation guide for dlib

Install face_recognition library:

pip3 install face_recognition

Install other dependencies:

pip3 install numpy opencv-python

Face Recognition Project

This repository contains the implementation of a face recognition model that I developed during my second year of college. The project utilizes Python and several powerful libraries to recognize and manipulate faces in images and real-time video feeds.

Usage

Command-Line Interface

You can use the face_recognition command-line tool to recognize faces in a folder of images:

face_recognition ./known_people/ ./unknown_people/

Python Scripts

Check the examples directory for detailed examples on how to use the library for different tasks such as face detection, facial feature extraction, and real-time recognition.

Contributions

Contributions, issues, and feature requests are welcome! Feel free to check the issues page for any open issues or to create a new one.

License

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

Acknowledgements

Special thanks to:

• Davis King for creating dlib.
• The contributors of the face_recognition library.
• The developers of OpenCV and NumPy for their excellent tools.