| Nowadays with the rapid development of modern technology, artificial intelligence as a new rising subject has been becoming a focus of attention. Facial expression recognition as the cross area of machine learning, pattern recognition and automaton which belong to the branches of AI, has got widely attention and become to an active studying area due to its application to man-machine conversation, telecommunication, law execution, psychology study.Face image is one of the most important human biologic feature which includes plenty rich information. Meanwhile human face as the visual object of images and videos is taking an important position of status in the studying area of computer vision, pattern recognition and multimedia technology. Facial expression is one of the most powerful shortcuts of communicating emotions and expressing intentions which is usually classified to seven classes: anger, disgust, fear, happiness, neutral, sadness and surprise. To find a way of automatically classifying the human expression is significant to the human computer intercommunion and has potential application value in the area of computer assistant training and tele-educating etc.This paper presents a method for facial expression recognition based Fast Wavelet Transform -Projection-BP Neural Network (FWT-Project-BPNN) approaches. Firstly, the fast wavelet transform was carried out to compress the preprocessed images'data on the basis of not losing essential image information. Then after-FWT we projected the horizontal high frequency sub-image to a horizontal vector and the vertical high frequency sub image to a vertical vector respectively. The feature vectors were got by connecting the expression images'horizontal projection with transposed vertical projection. Finally, BP Neural Network (BPNN) is used to make a classification. Experimental results indicate that the proposed method can be simple, high ration of recognition, but it still need to be improved on the capability of extensiveness. |
PDF Full Text Request