基于Gabor小波与分类树的人脸表情识别算法研究-信息与通信工程专业论文.docxVIP

Abstract Facial expression recognition is an important part of emotional calculation research, which involves many areas, and have important applications on driving, the network teaching, human-computer interaction etc. Accurate recognition of facial expressions, can promote the development of human-computer interaction intelligent system, and make the computer more effectively supervise the auxiliary work. Firstly, this paper explains the background and the meaning of research, it introduces facial expression of the current situation of domestic and foreign research. Secondly, it introduces the general framework of facial expression recognition, the analysis of the classical method of facial expression recognition and related improvements, and summarizes the advantages and disadvantages. The task in this paper focuses on the key issues of facial expression recognition, such as feature extraction and facial expression classification. The main research contents and innovative work in this paper are shown as follow: In order to obtain a good result of facial expression recognition, the first step is image preprocessing. In this paper, the position of the pupil and the horizontal centerline of mouth have been located quickly and accurately, and according to the position information and the structural characteristics of face, the more efficient expression sub-regions are cut accurately. At the same time, these sub-regions would be normalized. The method of the feature extraction based on Gabor wavelets are discussed in details. Firstly, optimizing the Gabor filter’s window, not only strengthen the Gabor filter feature extraction capability, but also accelerate the convolution time. Then, in order to overcome the high-dimension of Gabor features, a method which codes the different orientation of Gabor’s amplitude at the same scale is proposed. It helps to achieve more effective information while it reduces the dimension of features. Finally, a way which fused the local