Environment Setup

face_recognition is a robust open-source facial recognition libray with comprehensive documentation. Although primarily designed for Linux systems, it can be installed on Windows with additional dependencies.

Prerequisites

• Operating System: Windows 11
• Development Environment: PyCharm
• Python Version: 3.12

Installing Dependencies

CMake Installation

First, install CMake using pip:

pip install cmake

Visual Studio Build Tools

Install the following components from Visual Studio:

• MSVC v143 - VS 2022 C++ x64/x86 build tools
• Windows 11 SDK

Installing dlib

After instalilng the prerequisites, install dlib:

pip install dlib

Installing face_recognition

Install the main package:

pip install face_recognition

Additional Models

Install the required models from GitHub:

pip install git+https://github.com/ageitgey/face_recognition_models

Setuptools

Install setuptools if not already present:

pip install setuptools

Verification Demo

Test the installation with a simple face detection script:

import face_recognition
from PIL import Image

# Load and process image
input_image = face_recognition.load_image_file("test_image.jpg")
detected_faces = face_recognition.face_locations(input_image)

print(f"Detected {len(detected_faces)} face(s)")

for face in detected_faces:
    top, right, bottom, left = face
    print(f"Face coordinates - Top: {top}, Left: {left}, Bottom: {bottom}, Right: {right}")
    
    # Extract and display face
    face_region = input_image[top:bottom, left:right]
    pil_face = Image.fromarray(face_region)
    pil_face.show()