一种基于频谱脸和Fisherface的人脸识别新方法  

Face Recognition System Based on Spectrofaces and Fisherface

作　　者：韩凌[1] 王宏[1] 

机构地区：[1]东北大学,辽宁沈阳110004

出　　处：《计算机仿真》2006年第7期187-190,共4页Computer Simulation

基　　金：教育部高等学校骨干教师资助计划(200065)

摘　　要：频谱脸方法主要是采用二维小波变换和傅立叶变换。因为人脸图像的低频部分对人脸的表情变化是不敏感的,所以对人脸图像使用二维小波变换,提取人脸图像的低频部分。再对人脸图像的低频部分使用傅立叶变换,从而获得原人像的一个低维空间的表达。但是频谱脸特征维数仍然较高,所以在频谱脸法的基础上继续提取人脸频谱图像的F isherface特征,降低特征的维数,提高识别效率。利用ORL人脸库进行了实验,实验结果表明该识别系统具有较好的识别能力。A face recognition method based on spectrofaces is used. Spectroface representation combines the wavelet transform with the Fourier transform. We have shown that by decomposing a face image using wavelet transform, the low- frequency face image is less sensitive to the facial expression variations. By decomposing the lowfrequency face image using Fourier transform, we can get the face image with lower -dimensional space. But the dimension of the spectrofaces is still high, so we extract the character of Fisherface from the spectrofaces, in order to reduce the dimension, and enhance the efficiency. The ORL face database was used in the experiment and the result shows that the method presented is effective.

关 键 词：人脸识别 傅立叶变换 小波变换 欧氏距离 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]