Presentation 2003/5/22
Robust Facial Parts Detection for Camera Angle by Using Relaxation Matching
Kenji IWATA, Hitoshi HONGO, Kazuhiko YAMAMOTO, Yoshinori NIWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A facial parts detection technique that is robust for camera angle is described. Template matching use the four directional features. Facial parts templates are learned from many directions of faces. Positions of facial parts are detected by relaxation matching using the directional adopted model of facial parts position. Experiments show that facial parts are detectable to the HOIP multi-directional face image database. Detection rate was 96% for ±30° camera angle.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Facial parts detection / Relaxation matching / Four directional features
Paper # PRMU2003-8
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/5/22(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 Facial Parts Detection for Camera Angle by Using Relaxation Matching
Sub Title (in English)
Keyword(1) Facial parts detection
Keyword(2) Relaxation matching
Keyword(3) Four directional features
1st Author's Name Kenji IWATA
1st Author's Affiliation Softopia Japan HOIP-JST()
2nd Author's Name Hitoshi HONGO
2nd Author's Affiliation Softopia Japan HOIP-JST
3rd Author's Name Kazuhiko YAMAMOTO
3rd Author's Affiliation Faculty of Engineering, Gifu University
4th Author's Name Yoshinori NIWA
4th Author's Affiliation Softopia Japan HOIP-JST
Date 2003/5/22
Paper # PRMU2003-8
Volume (vol) vol.103
Number (no) 95
Page pp.pp.-
#Pages 6
Date of Issue