An Investigation into the Impact of Occlusion on Facial Emotion Recognition in the Wild

Emotion recognition from facial expressions is a crucial task in affective computing with applications in human-computer interaction, security and healthcare. However, real-world scenarios often involve partial occlusions of facial features due to factors such as headgear, accessories, face masks and environmental obstructions. This paper discusses the effect of synthetic occlusion on facial emotion recognition on images captured in the wild targeting three main similar emotions: surprise, fear and neutral expressions. An analysis on the effect of such occlusion on each emotion is also performed including a discussion on which parts of the face most affect emotion recognition. This paper finally discusses associated challenges and insights in this field.