基于不变矩的人脸识别方法的研究  

A Face Recognition Method Based on Moment Invariants

作　　者：杜平[1] 张燕昆[1] 刘重庆[1] 

机构地区：[1]上海交通大学图像处理与模式识别研究所,上海200030

出　　处：《计算机仿真》2002年第3期78-81,共4页Computer Simulation

基　　金：国家 8 6 3基金 (编号 992 1-0 1)资助项目

摘　　要：人脸识别是模式识别与计算机视觉领域中的一个重要的研究课题 ,在公安、交通、银行、海关以及安全系统等领域有着广泛的应用前景。该文提出了一种基于小波及不变矩矢量的人脸识别方法。利用小波变换减小或消除了表情因素对人脸识别的影响 ,然后利用不变矩矢量作为人脸的特征来进行人脸识别。我们采用了支持向量机和最近邻分类器作为分类器 ,在ORL人脸数据库的基础上进行了测试。实验取得了良好的效果 ,证实了算法的有效性。Face recognition is an active subject in the area of pattern recognition and computer vision, which has a wide range of potential applications in police, traffic, bank, custom and security system, and etc. An approach of face recognition with wavelet and moment invariants is introduced in this paper. Wavelet transform is applied to reduce or eliminate the effect of expression to the face recognition. Moment invariant vector is then abstracted to be the feature vector of face image. The support vector machine and nearest neighbor classifier are adopted to conduct the face recognition task on the basis of ORL database. The experiment result is presented and discussed, which shows the effectiveness of the face recognition scheme proposed.

关 键 词：人脸识别 不变矩 小波变换 支持向量机 最近邻分类器 模式识别 计算机视觉 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]