Skip to content

Girish-03/expression_emonet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Continuous and Discrete Expressions detection and visualisation

Emma.gif

This project uses https://github.com/face-analysis/emonet (Paper) to estimate the continuous and discrete emotions in a video. It utilises Facial Alignment Network (FAN) for facial landmark detection, which is used to crop the face image and further fed to EmoNet for expression detection. The results are annotated and on every frame of the video to generate annotated videos with discrete label and changing values of valence and arousal or the continuous values of emotions.

Installation and Usage

Clone the EmoNet repo and install FAN

!git clone https://github.com/face-analysis/emonet
!cp -a /content/emonet/emonet /content/emonet2
!pip install face-alignment

Run Expression detection visualisation.py to generate results.
Input video path can be edited in Line 109 
The 5 or 8 expression model selection can be edited in Line 121

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages