A Review of Deep Learning Methods in Automatic Facial Micro-expression Recognition

Abstract

Facial expression analysis to understand human emotion is the base for affective computing. Until the last decade, researchers mainly used facial macro-expressions for classification and detection problems. Micro-expressions are the tiny muscle moments in the face that occur as responses to feelings and emotions. They often reveal true emotions that a person attempts to suppress, hide, mask, or conceal. These expressions reflect a person’s real emotional state. They can be used to achieve a range of goals, including public protection, criminal interrogation, clinical assessment, and diagnosis. It is still relatively new to utilize computer vision to assess facial micro-expressions in video sequences. Accurate machine analysis of facial micro-expression is now conceivable due to rapid progress in computational methodologies and video acquisition methods, as opposed to a decade ago when this had been a realm of therapists and assessment seemed to be manual. Even though the research of facial micro-expressions has become a longstanding topic in psychology, this is still a comparatively recent computational science with substantial obstacles. This paper a provides a comprehensive review of current databases and various deep learning methodologies to analyze micro-expressions. The automation of these procedures is broken down into individual steps, which are documented and debated.