跳到主要导航 跳到搜索 跳到主要内容

COMBINING CLASSIFIERS FOR FACE RECOGNITION

  • Xiaoguang Lu*
  • , Yunhong Wang
  • , K. Jain*
  • *此作品的通讯作者
  • Michigan State University
  • CAS - Institute of Automation

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Current two-dimensional face recognition approaches can obtain a good performance only under constrained environments. However, in the real applications, face appearance changes significantly due to different illumination, pose, and expression. Face recognizers based on different representations of the input face images have different sensitivity to these variations. Therefore, a combination of different face classifiers which can integrate the complementary information should lead to improved classification accuracy. We use the sum rule and RBF-based integration strategies to combine three commonly used face classifiers based on PCA, ICA and LDA representations. Experiments conducted on a face database containing 206 subjects (2,060 face images) show that the proposed classifier combination approaches outperform individual classifiers.

源语言英语
主期刊名Proceedings - 2003 International Conference on Multimedia and Expo, ICME
出版商IEEE Computer Society
III3-III16
ISBN(电子版)0780379659
DOI
出版状态已出版 - 2003
已对外发布
活动2003 International Conference on Multimedia and Expo, ICME 2003 - Baltimore, 美国
期限: 6 7月 20039 7月 2003

出版系列

姓名Proceedings - IEEE International Conference on Multimedia and Expo
3
ISSN(印刷版)1945-7871
ISSN(电子版)1945-788X

会议

会议2003 International Conference on Multimedia and Expo, ICME 2003
国家/地区美国
Baltimore
时期6/07/039/07/03

学术指纹

探究 'COMBINING CLASSIFIERS FOR FACE RECOGNITION' 的科研主题。它们共同构成独一无二的学术指纹。

引用此