Presentation 2003/1/9
Detecting the existence of glasses and Extracting the facial feature points automatically
Chunsheng HUA, Haiyuan WU, Tadayoshi SHIOYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a new approach to detect the existence of glasses in a color image taken by a single camera. In particular, ragardless of the glasses, facial feature points can be detected automatically, The color information (including skin color and hair color) and the edge information (including edge strength and edge orientation) are extracted from the input image. By using these two pieces of information, the region of face and facial organs can be detected. We calculate the average value of the skin for color similarity in both the cheek and the area that is around the outside corner of eyes, then we can get the ratio of the two average values. In the same way, the ratio of the average values of edge strength in the same areas can be calculated. By using the two ratios, we can detect the existence of of glasses in the input image. From the detected regions of face and facial features, by using the edge information, the position of the mouth, nose and eyes can be predicted fairly correctly. Finally, we extract the facial feature points by using the SUSAN corner detector.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Grasses detection / Facial feature points detection / Integral Projection / SUSAn corner detector
Paper # PRMU2002-184
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/1/9(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) Detecting the existence of glasses and Extracting the facial feature points automatically
Sub Title (in English)
Keyword(1) Grasses detection
Keyword(2) Facial feature points detection
Keyword(3) Integral Projection
Keyword(4) SUSAn corner detector
1st Author's Name Chunsheng HUA
1st Author's Affiliation Department of Machenical and Systems Engineering, Kyoto Institute of Technology()
2nd Author's Name Haiyuan WU
2nd Author's Affiliation Wakayama University
3rd Author's Name Tadayoshi SHIOYAMA
3rd Author's Affiliation Department of Machenical and Systems Engineering, Kyoto Institute of Technology
Date 2003/1/9
Paper # PRMU2002-184
Volume (vol) vol.102
Number (no) 554
Page pp.pp.-
#Pages 6
Date of Issue