Investigating the Impact of Cerebral vs Peripheral Visual Issues on Emotion Recognition Using a New Silicone-based Face Mask Prototype

Le résumé fourni par la source

This paper introduces an innovative silicone-based semi-transparent face mask prototype, to cope with limitations of the standard face masks massively adopted as individual protection devices (IPDs) during the COVID-19 pandemic. In particular, the prototype aimed at complying with health-related requirements while preserving the maximum amount of visual information from facial features during social interactions, which is critical for vulnerable populations such as young children, and people with Visual Impairments (VI). We assessed the effectiveness of the developed prototype by performing a test of emotion inference from facial expressions on groups of sighted children and children with peripheral (PVI) and cerebral VI (CVI). Results suggest that the semitransparent mask significantly improves classification accuracy in children with PVI, while children with CVI demonstrate reduced performance in both masked and unmasked conditions. Finally, we trained a connectionist model to learn the relationship between visual facial features and emotion labels and provide a proof of concept regarding its potential to explain the differences in human performance, under distinct hypotheses linking each type of VI to facial emotion processing.Clinical relevance- This work investigates differences in the ability to infer emotions from facial expressions based on the type of VI (cerebral vs peripheral), providing important guidelines for practitioners in the field of visual rehabilitation, and highlighting conditions under which it is critical to adopt IPDs preserving the maximum amount of visual information.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.