Presentation 2005-10-28
Eye Detection from Color Images Using Separability Filter and Vector Quantization Histogram Method
Qiu Chen, Koji Kotani, Feifei Lee, Tadahiro Ohmi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In an automated face recognition system, eye detection is usually the first important pretreatment for normalizing the size, location and image-plane rotation of the human face. In this paper, we present an approach to accurate eye detection by using separability filter and vector quantization histogram method. Experimental results show the iris detection rate of the proposed algorithm of 98.4% for 63 images of 21 persons without spectacles in the AR database.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Face recognition / VQ / Histogram method / Separability filter
Paper # PRMU2005-97
Date of Issue

Conference Information
Committee PRMU
Conference Date 2005/10/21(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) Eye Detection from Color Images Using Separability Filter and Vector Quantization Histogram Method
Sub Title (in English)
Keyword(1) Face recognition
Keyword(2) VQ
Keyword(3) Histogram method
Keyword(4) Separability filter
1st Author's Name Qiu Chen
1st Author's Affiliation Department of Electronics, Graduate School of Engineering, Tohoku University()
2nd Author's Name Koji Kotani
2nd Author's Affiliation Department of Electronics, Graduate School of Engineering, Tohoku University
3rd Author's Name Feifei Lee
3rd Author's Affiliation Department of Electronics, Graduate School of Engineering, Tohoku University
4th Author's Name Tadahiro Ohmi
4th Author's Affiliation New Industry Creation Hatchery Center, Tohoku University
Date 2005-10-28
Paper # PRMU2005-97
Volume (vol) vol.105
Number (no) 375
Page pp.pp.-
#Pages 5
Date of Issue