Presentation 1997/6/20
Robust face recognition under drastic changes of conditions of image acquisition
Masaki Sohma, Kenji Nagao,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a new algorithm for face recognition which can deal with drastic changes of conditions of image aquisition. Unlike the recent approach based on KL transform that captures the features of faces only in static way, the present method exploits information of the changes of images more explicitly. For instance, if we change the direction of illuminant, it sometimes produces extremely different pictures of faces. Our method can handle such changes of face images, by defining a perturbation space that is obtained from the learing set of individual face pairs with two types of image acquisition condtitions. Empirical results shows the effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) face recognition / KL expansion / maharanobis metric
Paper # PRMU97-48
Date of Issue

Conference Information
Committee PRMU
Conference Date 1997/6/20(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) Robust face recognition under drastic changes of conditions of image acquisition
Sub Title (in English)
Keyword(1) face recognition
Keyword(2) KL expansion
Keyword(3) maharanobis metric
1st Author's Name Masaki Sohma
1st Author's Affiliation Matsushita Research Institute Tokyo, Inc.()
2nd Author's Name Kenji Nagao
2nd Author's Affiliation Matsushita Research Institute Tokyo, Inc.
Date 1997/6/20
Paper # PRMU97-48
Volume (vol) vol.97
Number (no) 113
Page pp.pp.-
#Pages 7
Date of Issue