Presentation 1997/6/20
Face Recognition System using Temporal Image Sequence
Osamu Yamaguchi, Kazuhiro Fukui, Ken-ichi Maeda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a face recognition system for human interface and security using temporal image sequence. As input we utilize several images of a face rather than a single shot so that the influence of facial expression and face direction can be attenuated. For the identification of the face, we essentially compute the subspace from the image sequence and apply the "Mutual Subspace Method" that defines the similarity by the angle between the computed subspace and those of pre-registered faces. It is naturally assumed that a registered face retains its form. We generate numerous normalized face patterns by the system and demonstrate the effectivity through the experimental results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Face recognition / Temporal image sequence / Mutual subspace method
Paper # PRMU97-50
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)
Vice Chair

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) Face Recognition System using Temporal Image Sequence
Sub Title (in English)
Keyword(1) Face recognition
Keyword(2) Temporal image sequence
Keyword(3) Mutual subspace method
1st Author's Name Osamu Yamaguchi
1st Author's Affiliation TOSHIBlA Kansai Research Laboratories()
2nd Author's Name Kazuhiro Fukui
2nd Author's Affiliation TOSHIBlA Kansai Research Laboratories
3rd Author's Name Ken-ichi Maeda
3rd Author's Affiliation TOSHIBlA Kansai Research Laboratories
Date 1997/6/20
Paper # PRMU97-50
Volume (vol) vol.97
Number (no) 113
Page pp.pp.-
#Pages 8
Date of Issue