Automatic Recognition of Posed Facial Expression of Emotion in Individuals with Autism Spectrum Disorder

Joseph Manfredonia

Abigail Bangerter

Nikolay V. Manyakov

Seth Ness

David Lewin

Andrew Skalkin

Matthew Boice

Matthew S. Goodwin

Geraldine Dawson

Robert Hendren

Bennett Leventhal

Frederick Shic

Gahan Pandina

Abstract: Facial expression is impaired in autism spectrum disorder (ASD), but rarely systematically studied. We focus on the ability of individuals with ASD to produce facial expressions of emotions in response to a verbal prompt. We used the Janssen Autism Knowledge Engine (JAKE®), including automated facial expression analysis software (FACET) to measure facial expressions in individuals with ASD (n = 144) and a typically developing (TD) comparison group (n = 41). Differences in ability to produce facial expressions were observed between ASD and TD groups, demonstrated by activation of facial action units (happy, scared, surprised, disgusted, but not angry or sad). Activation of facial action units correlated with parent-reported social communication skills. This approach has potential for diagnostic and response to intervention measures.

This publication uses Facial Expression Analysis which is fully integrated into iMotions Lab

Learn more