Application of Wavelet Energy Feature in Facial Expression Recognition

This paper proposes a high performance facial expression recognition method based on wavelet energy feature (WEF). As wavelet energy feature can discriminate the texture of expression images, it is used in facial expression recognition for the first time. Fisher's linear discriminants (FLD) can describe the details of the image, so we combine FLD with WEF. WEF is added to the image first, and then FLD is used to feature extraction. Finally, we use the Nearest-Neighbor rule to classify the seven expressions (anger, disgust, fear, happiness, normal, sadness, surprise) of JAFFE. The very high recognition rate obtained in experiments shows the effect of the proposed method.