Low resolution face recognition based on support vector data description

被引：82

作者：

Lee, Sang-Woong ^{[1
]}

Park, Jooyoung

Lee, Seong-Whan

机构：

[1] Korea Univ, Dept Comp Sci & Engn, Anam Dong, Seoul 136713, South Korea

[2] Korea Univ, Dept Control & Instrumentat Engn, Chungnam 339700, South Korea

来源：

PATTERN RECOGNITION | 2006年 / 39卷 / 09期

关键词：

support vector data description (SVDD); face recognition; low resolution; image enhancement;

D O I：

10.1016/j.patcog.2006.04.033

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In the face recognition process, it is important to deal with a facial image of low-resolution. For low-resolution face recognition. we propose a new method of extending the SVDD, which is one of the most well-known support vector learning methods for the one-class problem. The proposed method can recognize a person even with a low-resolution image. (c) 2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：1809 / 1812

页数：4

共 6 条

[1]

Dedeoglu G, 2004, PROC CVPR IEEE, P151

[2]

Hwang BW, 2003, LECT NOTES COMPUT SC, V2688, P557

[3] The pre-image problem in kernel methods [J].

Kwok, JTY ;

Tsang, IWH .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2004, 15 (06) :1517-1525

[4]

Park JS, 2005, LECT NOTES COMPUT SC, V3546, P102

[5] Support vector domain description [J].

Tax, DMJ ;

Duin, RPW .

PATTERN RECOGNITION LETTERS, 1999, 20 (11-13) :1191-1199

[6] Probabilistic recognition of human faces from video [J].

Zhou, SH ;

Krueger, V ;

Chellappa, R .

COMPUTER VISION AND IMAGE UNDERSTANDING, 2003, 91 (1-2) :214-245

← 1 →