Presentation 1999/12/16
Integration of Viewpoint Dependent Classifiers for Viewpoint Invariant Face Recognition
Takio KURITA, Hiroyuki SHIMAI, Takashi TAKAHASHI, Takaomi SHIGEHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a viewpoint invariant face recognition method in which several viewpoint dependent classifiers are combined by a gating network. The gating network is trained such that one of the classifiers is selected dpending on the viewpoint of a given input face image. Multinomial logit model is used for both of the viewpoint dependent classifiers and the gating network. The unsupervised and supervised learning algorithms are presented within a framework of maximum-likelihood estimation. Experimental results of view invariant face recognition are shown using a face images captured from several different viewpoints.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) face recognition / view invariant / mixture of experts / multiple classifier
Paper # PRMU99-170
Date of Issue

Conference Information
Committee PRMU
Conference Date 1999/12/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Integration of Viewpoint Dependent Classifiers for Viewpoint Invariant Face Recognition
Sub Title (in English)
Keyword(1) face recognition
Keyword(2) view invariant
Keyword(3) mixture of experts
Keyword(4) multiple classifier
1st Author's Name Takio KURITA
1st Author's Affiliation Electrotechnical Laboratory()
2nd Author's Name Hiroyuki SHIMAI
2nd Author's Affiliation Saitama University
3rd Author's Name Takashi TAKAHASHI
3rd Author's Affiliation University of Tsukuba (JSPS Research Fellow)
4th Author's Name Takaomi SHIGEHARA
4th Author's Affiliation Saitama University
Date 1999/12/16
Paper # PRMU99-170
Volume (vol) vol.99
Number (no) 514
Page pp.pp.-
#Pages 8
Date of Issue