Systematic review of various feature extraction techniques for facial emotion recognition system

Abstract

Facial emotion recognition (FER) is the task of recognising human emotions from images and videos. Communicating through facial emotions is a kind of non-verbal communication and it reflects a person's inner thoughts and mental states. In the present study, various existing geometric and appearance based feature extraction techniques used in FER are reviewed in tabular form. The main motive of this paper is to analyse the performance of these techniques on the bases of accuracy on different datasets like JAFFE, CK+, CK and MMI. After extensive research on feature extraction techniques for FERS, it is found that the appearance feature-based techniques achieved maximum accuracy and more favourable as compared to geometric feature-based techniques. Finally, the paper concludes with the various challenges encountered for feature extraction in the field of FERS which need to be addressed in the future.