8000 GitHub - thanhtinhvan/Emotion-recognize: Using openface
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

thanhtinhvan/Emotion-recognize

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Emotion recognize

This is my thesis project at University. Training a Deep Learning model Convolutional Neural Network (CNNs) to recognize emotion on the faces. Best compatible with Python 2.7 on Ubuntu 16.04.

Result

The CNN model can recognize 5 kinds of emotion: happy, sad, neutral, surprise, angry.

Emotion surprise

Emotion angry

Emotion mix 1

Emotion mix 2

Installation

Use the package manager pip to install foobar.

pip install scikit-learn==0.18.rc2
pip install python-tk
pip install Pillow
  • Download pre-train models for OpenFace and Dlib. In [models] folder, run get-models.sh
  • Download and extract pre-train model for Emotion which I was train at link. Extract as [datas] folder inside [Emotions] folder.

Usage

In Emotion folder, open terminal then:

python main.py

Contributing

Pull requests are welcome. For major changes or can not run, please open an issue first to discuss what you would like to change or your issue. Notes: I will upload my src for lastest version soon.

About

Using openface

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0