基于矩—小波描述子的人脸图像识别  

Face image recognition based on image's moment-wavelet descriptors

作　　者：王耀明[1] 刘挺[1] 

机构地区：[1]上海师范大学数理信息学院,上海200234

出　　处：《上海师范大学学报（自然科学版）》2004年第2期42-46,共5页Journal of Shanghai Normal University(Natural Sciences)

基　　金：上海市教委"人脸图像识别研究"(CL200105)

摘　　要：介绍了在Radon变换下的图像矩特征的抽取方法,并得到图像的矩特征矩阵;进而对矩特征矩阵按行向量进行小波变换组成矩-小波描述子特征矩阵,采用矩阵的加权欧氏距离作为人脸图像的匹配识别的算法,产生较好的结果。The writers put forward a method of extracting images moment-feature which can get a moment ?feature matrix of image under Radon transform. Then it applies Wavelet transform to its row vector and get moment-wavelet descriptors feature matrix, and uses the weighted Euclidean-distance as the method of recognizing faces image. At last this article gives a result by the experiments of using this matrix shows that the method has the character of high precision.

关 键 词：RADON变换 矩——小波描述子 人脸图像识别 矩特征矩阵 

分 类 号：G852.11[文化科学—民族体育]