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

频域光照归一化的人脸识别
引用本文:琚生根,周激流,何坤,夏欣,王刚.频域光照归一化的人脸识别[J].电子科技大学学报(社会科学版),2009(6).
作者姓名:琚生根  周激流  何坤  夏欣  王刚
作者单位:四川大学计算机学院;
基金项目:国家自然科学基金(60272095)
摘    要:为了降低人脸识别对环境条件的要求,克服光照对人脸识别的影响,通过分析人脸图像的幅频特性和相频特性,提出了频域光照归一化的人脸识别,对任何光照条件下采集的图像经过归一化后,光照与训练库中完全相同,同时保留了人脸的可区分性。人脸之间差异的信息量一般较少,运用最小非零特征向量作为人脸特征。实验仿真表明,与传统方法相比,频域光照归一化人脸识别方法对光照变化具有鲁棒性。

关 键 词:鲁棒性  人脸识别  光照归一化  相频特性  

Face Recognition Based on Illumination Normalization in Frequency-Domain
JU Sheng-gen,ZHOU Ji-liu,HE Kun,XIA Xin, WANG Gang.Face Recognition Based on Illumination Normalization in Frequency-Domain[J].Journal of University of Electronic Science and Technology of China(Social Sciences Edition),2009(6).
Authors:JU Sheng-gen  ZHOU Ji-liu  HE Kun  XIA Xin    WANG Gang
Institution:JU Sheng-gen,ZHOU Ji-liu,HE Kun,XIA Xin,, WANG Gang(School of Computer Science,Sichuan University Chengdu 610065)
Abstract:In order,to reduce the impact environmental requirements and overcome the effects of illumination on face recognition,a novel recognition method is presented based on normalization illumination in frequency-domain,via analyzing the Amplitude-frequency and phase-frequency characteristics of human faces.Collected images under any light conditions are normalized so that the light is exactly the same for the training images,while retaining the distinctive features of human faces.As the different information of ...
Keywords:characteristic robustness  face recognition  illumination normalization  phase-frequency  
本文献已被 CNKI 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