Developing emotion recognition for video conference software to support people with autism

TL;DR

An emotion recognition software for the use with a video conference software for autistic individuals which are unable to recognize emotions properly which can get an image out of the video stream, detect the emotion in it with the help of a neural network and display the prediction to the user.

Abstract

We develop an emotion recognition software for the use with a video conference software for autistic individuals which are unable to recognize emotions properly. It can get an image out of the video stream, detect the emotion in it with the help of a neural network and display the prediction to the user. The network is trained on facial landmark features. The software is fully modular to support adaption to different video conference software, programming languages and implementations.

Figures (3)

• Figure 1: Steps for detecting emotions. Photo of face from dataset facialexpression:github
• Figure 2: DNN: Accuracy on training and validation data over 5000 epochs
• Figure 3: CNN: Accuracy on training and validation data over 500 epochs