Presentation 2000/5/4
Face Recognition Using Weighted Matching by Information of Gabor Features
Kazuhiro HOTTA, Taketoshi MISHIMA, Takio KURITA, Shinji UMEYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we present a face matching method which introduces the image processing of biological vision system and takes attention mechanism into consideration. To imitake the image processing at retina, a contrast filter which resembles the receptive field profile of retinal ganglion cell is used. Gabor filters are also used to imitate the image processing at V1 area. As the saliency(importance)value for attention, the information of Gabor features(output of Gabor filters)is used. In matching process, the information is used as the weight to calculate the similarity between model image and input image. This means that the attention points with high information have much influence to the matching result. To cope with the sale changes of a face, several images with different scales are generated by interpolation method from input image and these images are used as the matching candidates. The proposed method is applied to face detection and recognition task. The effectiveness of the proposed method is confirmed by the experiments using face images captured under various environments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Face detection / Face recognition / Biomimetic features / Contrast filter / Gabor features / Information
Paper # HIP2000-5
Date of Issue

Conference Information
Committee HIP
Conference Date 2000/5/4(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Face Recognition Using Weighted Matching by Information of Gabor Features
Sub Title (in English)
Keyword(1) Face detection
Keyword(2) Face recognition
Keyword(3) Biomimetic features
Keyword(4) Contrast filter
Keyword(5) Gabor features
Keyword(6) Information
1st Author's Name Kazuhiro HOTTA
1st Author's Affiliation Saitama University(JSPS Research Fellow)()
2nd Author's Name Taketoshi MISHIMA
2nd Author's Affiliation Saitama University
3rd Author's Name Takio KURITA
3rd Author's Affiliation Electrotechnical Laboratory
4th Author's Name Shinji UMEYAMA
4th Author's Affiliation Electrotechnical Laboratory
Date 2000/5/4
Paper # HIP2000-5
Volume (vol) vol.100
Number (no) 34
Page pp.pp.-
#Pages 8
Date of Issue