基于小波变换和图像矩特征的人脸识别算法  

An Efficient Algorithm of Face Image Recognition Using Moment Feature Based on The Wavelet Transform

作　　者：崔新春[1] 张文龙[2] 宫剑[2] 

机构地区：[1]曲阜师范大学电教系,曲阜273165 [2]上海师范大学数理信息学院,上海200234

出　　处：《计算机科学》2002年第9期76-77,46,共3页Computer Science

摘　　要：自从1962年Hu[1]提出在模式识别中采用矩不变性以来,矩函数由于具有不随图像平移、变比、旋转而变化的不变性质被广泛用于图像分析[2]中,如不变模式识别,物体分类姿态估计图像编码与重构纹理分割等.Since the moment method is introduced by Hu in 1962. more and more attention was payed on it and has been widely used in the field of image processing. As it has the congenital weakness of large amount of computing,it is difficult to use it in realtime image retrieval. Wavelet transform is an efficient way to deduce the demention of an image . In this paper , An efficient algorithm of face image recognition using moment feature based on wavelet transform is presented. First. applying wavelet transform on the images to be processed,and then get the moment feature of the imags and then begin face image recognition.

关 键 词：人脸识别算法 图像矩特征 小波变换 模式识别 计算机视觉 图像处理 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]