Presentation 2012-12-06
Comparison of Hue Feature and Illumination Invariant Color Feature H' in Partial Image Retrieval
Wataru MATSUMOTO, Keisuke KAMEYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Object color plays an important role in image matching. Kobayashi et al., proposed the color invariant feature H' by combining the basic color invariants introduced by Geusebroek et al., and improved the color selectivity under varying illumination conditions. As H' is an angular measure around an axis in the RGB space, it was considered to have similar characteristics as the hue. In this work, partial image matching experiments were tried under varying illumination conditions using H' and hue. The results showed that H' contributes to robust matching due to superior invariance against illumination changes.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) color invariance / partial image retrieval / SIFT / hue
Paper # CS2012-78,IE2012-92
Date of Issue

Conference Information
Committee IE
Conference Date 2012/11/29(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 Image Engineering (IE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Comparison of Hue Feature and Illumination Invariant Color Feature H' in Partial Image Retrieval
Sub Title (in English)
Keyword(1) color invariance
Keyword(2) partial image retrieval
Keyword(3) SIFT
Keyword(4) hue
1st Author's Name Wataru MATSUMOTO
1st Author's Affiliation Graduate School of Systems and Information Engineering University of Tsukuba()
2nd Author's Name Keisuke KAMEYAMA
2nd Author's Affiliation Faculty of Engineering Information and Systems University of Tsukuba
Date 2012-12-06
Paper # CS2012-78,IE2012-92
Volume (vol) vol.112
Number (no) 335
Page pp.pp.-
#Pages 6
Date of Issue