beibinli/affspec

AffSpec

A Facial Affect Analysis System for Autism Spectrum Disorder

Authors: Beibin Li, Sachin Mehta, Deepali Aneja, Claire Foster, Pamela Ventola, Frederick Shic, Linda Shapiro

Contact: [email protected]

If you use any code or gain any useful information from this project, please cite the following paper. Thanks!

Beibin Li, Sachin Mehta, Deepali Aneja, Claire Foster, Pamela Ventola, Frederick Shic, Linda Shapiro.
A Facial Affect Analysis System for Autism Spectrum Disorder.
In 2019 IEEE International Conference on Image Processing (ICIP) 2019 Sep. IEEE.

Installation

After downloading the repository, put the "affspec" folder with your main code.

Note for CUDA (GPU) computing

The PyTorch library support CUDA computing that can boost running speed of deep learning models. If you have a Nvidia GPU, then you can follow the CUDA installation steps before installing PyTorch.

In our empirical experiment, CUDA runs 20 times faster than a modern CPU.

Requirements

Python 3.6+ PyTorch 1.0+ OpenCV2

Alternative Tools

There are lots of other open source tools for affective computing. We list the following ones for their advantages.

• OpenFace
• FEAT

License

MIT License

Q&A

If you have any questions, please contact [email protected].