Application of General Type-2 Fuzzy Set in Emotion Recognition from Facial Expression

摘要

This paper proposes a new technique for emotion recognition of an unknown subject using General Type-2 Fuzzy sets (GT2FS). The proposed technique includes two steps- first, a type-2 fuzzy face-space is created with the background knowledge of facial features of different subjects containing differ-ent emotions. Second, the emotion of an unknown facial expression is deter-mined based on the consensus of the measured facial features with the fuzzy face-space. The GT2FS has been used here to model the fuzzy face space. The general type-2 fuzzy involves both primary and secondary membership distributions which have been obtained here by formulating and solving an op-timization problem. The optimization problem here attempts to minimize the difference between two decoded signals: the first one being the type-1 defuzzi-fication of the average primary membership distributions obtained from n-subjects, while the second one refers to the type-2 defuzzified signal for a given primary distribution with secondary memberships as unknown. The uncertainty management policy adopted using general type-2 fuzzy set has resulted in a classification accuracy of 96.67%.