Emotion recognition in autism spectrum disorder: does stylization help?

Abstract

We investigate the effect that stylized facial expressions have on the perception and categorization of emotions by participants with high-functioning Autism Spectrum Disorder (ASD) in contrast to two control samples: one with Attention-Deficit/Hyperactivity Disorder (ADHD), and one with neurotypically developed peers (NTD). Realtime Non-Photorealistic Rendering (NPR) techniques with different levels of abstraction are applied to stylize two animated virtual characters performing expressions for six basic emotions. Our results show that the accuracy rates of the ASD group were unaffected by the NPR styles and reached about the same performance as for the characters with realistic-looking appearance. This effect, however, was not seen in the ADHD and NTD groups.