首页 | 本学科首页   官方微博 | 高级检索  
     

基于Armlets的人脸光照补偿
引用本文:聂祥飞,郭军.基于Armlets的人脸光照补偿[J].计算机应用,2007,27(8):2041-2043.
作者姓名:聂祥飞  郭军
作者单位:[1]重庆三峡学院,物理与电子工程学院,重庆404000 [2]北京邮电大学,信息工程学院,北京100876
基金项目:国家自然科学基金 , 教育部科学技术研究项目 , 重庆市教委资助项目 , 重庆三峡学院校科研和教改项目
摘    要:提出了一种用于非均匀光照条件下人脸识别的光照补偿算法。该算法通过在对数域计算2维Armlets多小波变换来实现人脸光照补偿,然后直接在对数域进行人脸识别。在Yale B人脸库中与其他光照补偿算法进行了比较,实验结果表明,该方法的平均误识率仅为0.18%,优于现有的其他算法。

关 键 词:人脸识别  光照补偿  多小波变换  Armlets
文章编号:1001-9081(2007)08-2041-03
收稿时间:2007-02-09
修稿时间:2007-02-09

Face illumination compensation based on Armlets
NIE Xiang-fei,GUO Jun.Face illumination compensation based on Armlets[J].journal of Computer Applications,2007,27(8):2041-2043.
Authors:NIE Xiang-fei  GUO Jun
Affiliation:1. School of Physics and Electronic Engineering, Chongqing Three Gorges University, Chongqing 404000, China; 2. School of lnformation Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China
Abstract:A new illumination compensation method for face recognition under nonuniform illumination conditions was presented. The method calculated 2-dimensional Armlets (analysis-ready multiwavelets) transform for face illumination compensation in logarithm domain, and then conducted face recognition experiment directly in logarithm domain. The proposed approach was compared with other illumination compensation methods on Yale B face database. The experimental results show that the average error rate of the proposed approach is only 0.18%, which is superior to that of all the existing methods.
Keywords:face recognition  illumination compensation  multiwavelets transform  Armlets
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《计算机应用》浏览原始摘要信息
点击此处可从《计算机应用》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