https://github.com/linzaer/face-track-detect-extract

💎 Detect , track and extract the optimal face in multi-target faces (exclude side face and select the optimal face).
https://github.com/linzaer/face-track-detect-extract

detection extract face kalman-tracking mtcnn tensorflow tracking

Last synced: 4 months ago
JSON representation

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

• Host: GitHub
• URL: https://github.com/linzaer/face-track-detect-extract
• Owner: Linzaer
• License: mit
• Created: 2018-08-21T11:12:40.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2019-06-01T08:10:20.000Z (over 6 years ago)
• Last Synced: 2023-11-07T17:15:28.513Z (almost 2 years ago)
• Topics: detection, extract, face, kalman-tracking, mtcnn, tensorflow, tracking
• Language: Python
• Homepage:
• Size: 33.1 MB
• Stars: 557
• Watchers: 24
• Forks: 205
• Open Issues: 14
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Face Detection & Tracking & Extract

![GitHub](https://img.shields.io/github/license/mashape/apistatus.svg)

![PyPI - Python Version](https://img.shields.io/pypi/pyversions/Django.svg)

   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**](https://github.com/davidsandberg/facenet/tree/master/src/align)

	* 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**.

## Results

![alt text](https://raw.githubusercontent.com/wiki/Linzaer/Face-Track-Detect-Extract/pic4.gif "scene 1")

![alt text](https://raw.githubusercontent.com/wiki/Linzaer/Face-Track-Detect-Extract/pic5.jpg "faces extracted")

## Special Thanks to:

*  [**experimenting-with-sort**](https://github.com/ZidanMusk/experimenting-with-sort) 

## License

MIT LICENSE