Face Track Detect Extract

💎 Detect , track and extract the optimal face in multi-target faces (exclude side face and select the optimal face).

From Linzaer·Updated June 14, 2026·View on GitHub·

This project can **detect** , **track** and **extract** the **optimal** face in multi-target faces (exclude side face and select the optimal face). The project is written primarily in Python, distributed under the MIT License license, first published in 2018. Key topics include: detection, extract, face, kalman-tracking, mtcnn.

Face Detection & Tracking & Extract

GitHub
PyPI - Python Version

This project can detect , track and extract the optimal face in multi-target faces (exclude side face and select the optimal face).

Introduction

Dependencies:
- Python 3.5+
- Tensorflow
- MTCNN
- Scikit-learn
- Numpy
- Numba
- Opencv-python
- Filterpy

Run

To run the python version of the code :

sh
python3 start.py

Then you can find faces extracted stored in the floder ./facepics .
If you want to draw 5 face landmarks on the face extracted,you just add the argument face_landmarks

sh
python3 start.py --face_landmarks

What can this project do?

You can run it to extract the optimal face for everyone from a lot of videos and use it as a training set for CNN Training.
You can also send the extracted face to the backend for Face Recognition.