Fuzzy emotion recognition model for video sequences

Abstract

Automatic facial expression recognition from video clips is a challenging task due to computational complexity, limitations of image analysis and subjectivity. This paper advocates a fuzzy based approach for emotion classification. On the other hand, several proposals have been put forward to enhance the pre-processing stage prior to the classification. This includes a combination of a boundary elliptical model for skin detection, adaptive thresholding, principal component analysis and use of cam-shift for face tracking. The performances of the developed system have been evaluated using TFEID and video clips and compared with Bayes' classifier.