Presentation 1996/1/26
Automatic Face Recognition : What Representation ?
Nicholas Costen, Ian Craw, Shigeru Akamatsu,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A testbed for automatic face recognition is described and shows an eigenface coding of shape-free texture, with manually coded landmarks, was more effective than correctly shaped faces. Configuration also allowed recognition, with rankings uncorrelated with texture; these combine to signifcantly improve performance. Human results on increasing performance by caricaturing to emphasize distinctive features and decreasing performance by compositing facial parts were reproduced. This suggests faces lie in a high-dimensional manifold, linearly approximated by the two factors, and this representation may be used for human face recognition.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Automatic Face Recognition / Eigenfaces / Representation
Paper # HIP95-32
Date of Issue

Conference Information
Committee HIP
Conference Date 1996/1/26(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 Human Information Processing (HIP)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic Face Recognition : What Representation ?
Sub Title (in English)
Keyword(1) Automatic Face Recognition
Keyword(2) Eigenfaces
Keyword(3) Representation
1st Author's Name Nicholas Costen
1st Author's Affiliation ATR Human Information Processing Research Laboratories()
2nd Author's Name Ian Craw
2nd Author's Affiliation University of Aberdeen, Aberdeen, Scotland
3rd Author's Name Shigeru Akamatsu
3rd Author's Affiliation ATR Human Information Processing Research Laboratories
Date 1996/1/26
Paper # HIP95-32
Volume (vol) vol.95
Number (no) 499
Page pp.pp.-
#Pages 6
Date of Issue