首页 | 本学科首页   官方微博 | 高级检索  
     

用于人脸识别的GFC方法
引用本文:肖沙里,刘宇,周长国,袁浩,徐智敏.用于人脸识别的GFC方法[J].国外电子测量技术,2006,25(11):63-65.
作者姓名:肖沙里  刘宇  周长国  袁浩  徐智敏
作者单位:重庆大学光电技术及系统教育部重点实验室,重庆,400044
摘    要:本文介绍了Gabor-fisher classifier分类器(GFC)人脸识别方法,利用该方法首先对面部图像进行Gabor小波处理,再对得到的增广Gabor特征向量应用增强线性辨别法模型(EFM)以得到辨别特征,该方法对于人脸图像在光照和表情变化的情况下仍然是有效的.该方法的新颖之处在于:(1)引入了Gabor小波,得到的增广特征向量更好地反映了图像的特征;(2)应用EFM在对维数进行降低的同时进行分类特征提取.通过与传统的LDA方法和PCA方法的对比得出,该方法在应用于光照和面部表情变化比较大的FERET数据库时,优势比较明显.

关 键 词:人脸识别  Gabor小波  增强线性辨别法模型  Gabor-Fisher分类器

Face recognition method based on wavelet analysis
Xiao Shali,Liu Yu,Zhou Changguo,Yuan Hao,Xu Zhimin.Face recognition method based on wavelet analysis[J].Foreign Electronic Measurement Technology,2006,25(11):63-65.
Authors:Xiao Shali  Liu Yu  Zhou Changguo  Yuan Hao  Xu Zhimin
Affiliation:Key Laboratory of Opto-electronic Technology and Systems, Ministry of China, Chongqing University, Chongqing 400044
Abstract:The Gabor-fisher classifier (GFC) method for face recognition applies the enhanced fisher linear discriminant model (EFM) to an augmented Gabor feature vector derived from the Gabor wavelet representation of face images. The novelty of this method comes from (1) the derivation of an augmented Gabor feature vector, (2) Dimensionality is further reduced using the EFM by considering both data compression and recognition performance. The new GFC method has more advantags tested on face recognition which were acquired under variable illumination and facial expressions.
Keywords:face recognition  Gabor wavelet  EFM  GFC  
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