首页 | 本学科首页   官方微博 | 高级检索  
     

不同光照条件下特征脸方法的改进研究
引用本文:赵静,夏良正,舒志强,赵一凡. 不同光照条件下特征脸方法的改进研究[J]. 计算机应用研究, 2005, 22(6): 240-242
作者姓名:赵静  夏良正  舒志强  赵一凡
作者单位:1. 东南大学,自动控制系,模式识别与智能系统实验室,江苏,南京,210096
2. 南京长城信息系统有限公司,江苏,南京,210004
摘    要:提出了一种针对人脸图像的预处理方法,针对光照条件影响对特征主分量进行了改进研究。首先介绍了特征脸识别方法的起源与实现,然后介绍了添加对自身图像灰度值零均值的预处理方法。基于FERET人脸图像组建特征库和测试库,对特征脸方法中的前三个主分量进行具体分析,得出了其对光照敏感的规律,及在光照影响较为严重的情况下主分量的最佳选取方法。

关 键 词:预处理;主分量分析;特征脸;累加识别率
文章编号:1001-3695(2005)06-0240-03
修稿时间:2004-07-12

Eigenface Optimization Research for Variable Illumination Conditions
ZHAO Jing,XIA Liang-zheng,SHU Zhi-qiang,ZHAO Yi-fan. Eigenface Optimization Research for Variable Illumination Conditions[J]. Application Research of Computers, 2005, 22(6): 240-242
Authors:ZHAO Jing  XIA Liang-zheng  SHU Zhi-qiang  ZHAO Yi-fan
Affiliation:(1.Laboratory of Pattern Recognition & Intelligent System, Dept. of Auto Control, Southeast University, Nanjing Jiangsu 210096, China; 2.Nanjing Greatwall Information System Co.,Ltd., Nanjing Jiangsu 210004, China)
Abstract:A pre-processing method for face images is introduced firstly and the principal components of the eigenfaces are researched for variable illumination conditions. The source and the realization of the eigenface method are introduced and the pre-processing step of the zero mean of every face image is added. Based on the feature database and the probe database from FERET face images, the first three principal components are analysed and the rules of their influences by variable illumination conditions are concluded. The optimal method of choosing principal components is presented when influenced by illumination conditions severely.
Keywords:Pre-processing  Principal Component Analysis(PCA)  Eigenfaces  Cumulative Match Score
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机应用研究》浏览原始摘要信息
点击此处可从《计算机应用研究》下载全文
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