ai-agent

Face Recognition with face_recognition

Name: Face Recognition with face_recognition
Author: ageitgey

Get simple facial recognition for your startup with face_recognition, used by 57k+ GitHub stars, for Python and command line.

56,653 stars13,694 forksPythonHealth Score 9/10Updated 6/25/2026100% free · open source

What it does

Face_recognition is a Python library that provides simple facial recognition capabilities, allowing you to identify and compare faces in images.

Install / run

pip install face_recognition

When to use it

•You need to authenticate users based on their facial identity
•You want to automate the process of tagging people in photos
•You're building a surveillance system that requires face detection and recognition

Quick start

1Clone the repository using `git clone https://github.com/ageitgey/face_recognition.git`
2Navigate to the examples directory using `cd face_recognition/examples`
3Run the face recognition example using `python face_recognition_example.py`
4Use the `face_locations` function to detect faces in an image, like this: `face_locations = face_recognition.face_locations(image)`
5Compare two faces using the `compare_faces` function, like this: `matches = face_recognition.compare_faces([face_encoding], face_encoding_to_check)`

Ready-to-paste prompt

python -m face_recognition `face_recognition examples/obama.jpg examples/biden.jpg -e`

Heads up: Make sure you have the dlib library installed, which is a requirement for face_recognition, and also ensure you're using a compatible version of OpenCV, as face_recognition uses it under the hood

Saves to your device

Topics

face-detection

face-recognition

machine-learning

python

How Face Recognition with face_recognition works

Codeflow

Free to inspect

Face Recognition with face_recognition is a small Python project (~2.7k lines across 28 code files, plus 2 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit 2 months ago, MIT license, has a test suite.

Size

Small codebase

~2.7k lines · 28 code files · 22 min skim

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Python · Docker

No API keys detected

Python 79%Dockerfile 16%Makefile 5%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
pyproject.toml
Dependencies and the commands it exposes
3
face_recognition/__init__.py
Inside face_recognition/ — the main logic begins here
4
examples/alex-lacamoire.png
A worked example — copy this to get going

What's in each folder

face_recognition/Core code — the actual logic4 files

examples/Examples you can copy50 files

docs/Documentation12 files

docker/Deployment / infrastructure6 files

tests/Tests — proof it works9 files

.github/CI / automation (GitHub Actions)2 files