人脸表情识别研究摘要.docVIP

摘要 Gabor小波变换和非负矩阵分解相结合的特征提取方法。结合Gabor小波变换的特性，设计了相应的Gabor滤波器组，利用它对面部信息区域进行滤波处理，获取不同的子图信息。接着，对个滤波器滤波产生的子图分别进行非负矩阵分解数据降维及特征选择）关键词： Abstract Facial expression recognition is a new research direction, and it has broad application prospects in the intelligent human-computer interaction. At the same time, facial expression recognition is widely applied in the fields of the traffic, medical treatment and public safety. In recent years, facial expression recognition has been paid close attention by more and more scholars. And this technology has become a hot research in the area of artificial intelligence. Therefore, research on facial expression recognition technology has important theoretical significance and practical application value. Facial expression recognition technology includes image preprocessing, feature extraction and classification. In image preprocessing, a new eye location method based on Sobel edge extraction was proposed. The new method includes three steps for coarse positioning of eyes, segmentation of eyebrows and eyes, and precise position of eyes. After median filtering and normalization for image, the coarse area of eye was located according to the priori knowledge. The segmentation of eyebrows and eyes was implemented according to the segmentation line of eyebrows and eyes, and the line was determined by the gray integral projection curve. Then, the precise location of the eyes was realized according to the boundary of binary image obtained by extracting eye edge with Sobel operator. Compared with the traditional template matching and circle examination of Hough transform, the method proposed has obvious advantages in computing time and is suitable for real-time system. In feature extraction, the feature extraction method based on the Gabor wavelet transform and Non-negative Matrix Factorization was proposed. Considering the characteristics of Gabor wavelet transform，corresponding Gabor filters were designed. The facial information area was filtere