AffectiveTDA: Using Topological Data Analysis to Improve Analysis and Explainability in Affective Computing



Hamza Elhamdadi, Shaun Canavan, Paul Rosen

 External link (DOI) 

 View presentation:2021-10-27T13:00:00ZGMT-0600Change your timezone on the schedule page
2021-10-27T13:00:00Z

Exemplar figure, described by caption below — Our affective computing visualization calculates persistent homology on 83 facial landmarks (top) to detect the topological features of emotions. By comparing the topology distance of various facial poses (bottom), our approach clusters emotions of anger (brown), disgust (purple), fear (red), happiness (green), sadness (orange), and surprise (blue).

Fast forward

Direct link to video on YouTube: https://youtu.be/KgQhn8BgztQ

Abstract

We present an approach utilizing Topological Data Analysis to study the structure of face poses used in affective computing, i.e., the process of recognizing human emotion. The approach uses a conditional comparison of different emotions, both respective and irrespective of time, with multiple topological distance metrics, dimension reduction techniques, and face subsections (e.g., eyes, nose, mouth, etc.). The results confirm that our topology-based approach captures known patterns, distinctions between emotions, and distinctions between individuals, which is an important step towards more robust and explainable emotion recognition by machines.