Haar Wavelet Transform Based Facial Emotion Recognition

Abstract

Abstract. In order to propose an effective emotion recognition system, this paper proposed a novel Haar wavelet transform based emotion recognition system. This system is based on facial expression images obtained by digital camera. Our method used principal component analysis as the dimensionality reduction approach. The support vector machine (SVM) was used as the classifier. The results showed that our method achieved an accuracy of 78.37±1.50%. In all, our method is effective in emotion recognition.