Face Recognition under Variable Illumination by Weighted-Subband Edge Enhancement

被引:0
作者
Lai, Zhao-Rong [1 ]
Dai, Dao-Qing [1 ]
Pen, Chuan-Xian [1 ]
机构
[1] Sun Yat Sen Univ, Ctr Comp Vis, Xin Gang Xi Rd 135, Guangzhou, Guangdong, Peoples R China
来源
PATTERN RECOGNITION | 2012年 / 321卷
关键词
face recognition; weighted subbands; edge enhancement; wavelet decomposition; division histogram equalization; division border smoothing; DISCRETE COSINE TRANSFORM; NORMALIZATION; MODELS;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This article presents a novel weighted-subband method based on wavelet for face recognition under variable illumination. Different levels of subbands contain different features of the edge of a human face image. Through assigning a weight to each subband, we can strengthen the features beneficial to recognition, and weaken the features detrimental to recognition. To make the edge of human face stand out, a new histogram equalization and border smoothing method is implemented before weighted-subband edge enhancement. Experiments on the Extended YaleB Database show promising performance.
引用
收藏
页码:324 / +
页数:3
相关论文
共 17 条
[1]  
[Anonymous], 1992, CBMS-NSF Reg. Conf. Ser. in Appl. Math
[2]  
[Anonymous], FACE RECOGNITION
[3]   Total variation models for variable lighting face recognition [J].
Chen, Terrence ;
Yin, Wotao ;
Zhou, Xiang Sean ;
Comaniciu, Dorin ;
Huang, Thomas S. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (09) :1519-1524
[4]   Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain [J].
Chen, Weilong ;
Er, Meng Joo ;
Wu, Shiqian .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2006, 36 (02) :458-466
[5]   Use of matrix polar decomposition for illumination-tolerant face recognition in discrete cosine transform domain [J].
Ezoji, M. ;
Faez, K. .
IET IMAGE PROCESSING, 2011, 5 (01) :25-35
[6]   From few to many: Illumination cone models for face recognition under variable lighting and pose [J].
Georghiades, AS ;
Belhumeur, PN ;
Kriegman, DJ .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (06) :643-660
[7]   Acquiring linear subspaces for face recognition under variable lighting [J].
Lee, KC ;
Ho, J ;
Kriegman, DJ .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2005, 27 (05) :684-698
[8]  
Martinez A., 1998, The AR Face Database Technical Report 24
[9]  
CVC
[10]  
Pan H, 2011, CHIN CONTR CONF, P3268