Emotion Recognition by a Hybrid System Based on the Features of Distances and the Shapes of the Wrinkles

摘要

Emotion recognition is a key work of research area in brain computer interactions. With theincreasing concerns about affective computing, emotion recognition has attracted more and moreattention in the past decades. Focusing on geometric positions of key parts of the face and welldetecting them is the best way to increase accuracy of emotion recognition systems and reach highclassification rates. In this paper, we propose a hybrid system based on wavelet networks using 1DFast Wavelet Transform. This system combines two approaches: the biometric distances approachwhere we propose a new technique to locate feature points and the wrinkles approach where wepropose a new method to locate the wrinkles regions in the face. The classification rates given byexperimental results show the effectiveness of our proposed approach compared to other methods.