首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于相位重构的光照人脸识别
引用本文:夏小东.基于相位重构的光照人脸识别[J].成都信息工程学院学报,2007,22(4):482-485.
作者姓名:夏小东
作者单位:西南交通大学信号与信息处理四川省重点实验室,四川,成都,610031
摘    要:光照是人脸识别中的一个难题.信号经傅立叶变换后相位谱包含丰富的纹理结构信息,去除幅度谱,对图像进行单纯相位谱重构可以有效地减少光照影响.对角化主成份分析(Diagonal PCA)方法是对主成份分析(PCA)方法的有效改进,其计算量更小识别率更高.采用相位重构图像作为训练样本进行对角化主成份分析来解决光照问题,取得了较为理想的识别效果.

关 键 词:人脸识别  光照变化  主成份分析  对角化主成份分析  相位重构  光照问题  人脸识别  reconstruction  phase  based  illumination  recognition  识别效果  训练样本  重构图像  识别率  计算量  改进  方法  Diagonal  主成份分析  对角化  光照影响  相位谱
文章编号:1671-1742(2007)04-0482-04
收稿时间:2006-10-31

Face recognition under varying illumination based on phase reconstruction
XIA Xiao-dong.Face recognition under varying illumination based on phase reconstruction[J].Journal of Chengdu University of Information Technology,2007,22(4):482-485.
Authors:XIA Xiao-dong
Institution:Provincial Key Lab. of Signal and Information Processing, SWJTU, Chengdu 610031, China
Abstract:The face recognition under varying illumination is still a challenge. In the Fourier representation of the signals the magnitude and phase tend to play different roles and in .some situations the phase contains more illumination information. It is proved that the diagonal PCA is more accurate than the original PCA and it needs less computation. The phase spectrum is combined with the diagonal PCA to solve the problem without performing any pre-processing. The experiment shows that the proposed method can achieve very encouraging performance in varying illumination conditions.
Keywords:face recognition  illumination  diagonal PCA
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号