Research On Facial Expression Recognition Based On Selective Feature Extraction And Multiple HMMs

In recent years, the reasons for renewed interest in facial expression recognition are multiple, but mainly due to people have more interest about human computer interaction (HCI). Facial expression recognition is to analyze and detect the special expression state from given expression images or video frames and then to ascertain the subject's specific inborn emotion, achieving smarter and more natural interaction between human beings and computers. The study of facial expression recognition has . found important applied values.In this work, we firstly discuss the background and then analyze the main existing expression recognition algorithms. After analyzing the methods currently used by others, we present the eye feature extraction algorithm based on gray information and Harris corner detection, the expression recognition algorithm based on selective feature extraction and classifier tree, and the expression recognition algorithm based on hybrid features and fusing discrete HMMs. The work are described as below:(1) Eye feature extraction algorithm based on gray information and.Harris corner detection is presented. This method locates the eye areas roughly in the facial sub-image firstly, then locates the pupil areas accurately in the eye areas fixed on the previous step by gray statistical information, and finds out the eye corners through Harris corner detection. Finally, the outline of eye is fitted by using B-spline curves through the detected key points. The eye feature extracted in this paper is the basis of sub-image segmentation. In the same time, they can provide the initial position of AAM searching.(2) Expression recognition algorithm based on selective feature extraction and classifier tree is presented. Because different expression areas have different contribution to each expression, we present selective feature extraction algorithm. In this method, we select some expression features which contribute much to relevant sub-kind expression according to the rough classification results. This method can decrease the computational cost, and increase recognition speed. In the process of recognition, we divide the process into multiple levels according to the clustering principle, and then adopt template matching and improved k-nearest when classifying expression in each level, which decreases the number of clustering and increases recognition rate. (3) Expression recognition algorithm based on hybrid features and fusing discrete HMMs is presented. This method extracts texture variety feature using Gabor wavelet transformation for the eye area, and extracts shape variety feature using improved AAM for the mouth area. At the same time, we fix on the weight contributing to each expression for each expression area by using contribution analysis algorithm when training templates. In the process of recognition, we fuse the probability of each expression area with the weight of each expression area obtained by contribution analysis algorithm, and use the maximal probability as recognition result.(4) A prototype system of facial expression recognition based on image sequence is designed and implemented by using the object-oriented methods. It can be used to prove the effectiveness of above algorithms.