Presentation 2008-12-18
Recognition of hand shape robust to changes of background using kernel constraint mutual subspace method
Yasuhiro OHKAWA, Kazuhiro FUKUI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a recognition method of hand shape, which is robust to influence of the background. To realize this robust recognition method, the only discriminating features due to a hand should be selectively extracted from an input image. We have realized such selective extraction of feature by using Kernel Constraint Mutual Subspace Method (KCMSM). The effectiveness of the proposed method will be demonstrated through the evaluation experiments using multiple view images of five kinds of hand in various backgrounds.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hand shape recognition / HLAC feature / mutual subspace method / kernel constrained mutual subspace method
Paper # PRMU2008-164
Date of Issue

Conference Information
Committee PRMU
Conference Date 2008/12/11(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) Recognition of hand shape robust to changes of background using kernel constraint mutual subspace method
Sub Title (in English)
Keyword(1) Hand shape recognition
Keyword(2) HLAC feature
Keyword(3) mutual subspace method
Keyword(4) kernel constrained mutual subspace method
1st Author's Name Yasuhiro OHKAWA
1st Author's Affiliation University of Tsukuba, Graduate School of Systems and Information Engineering()
2nd Author's Name Kazuhiro FUKUI
2nd Author's Affiliation University of Tsukuba, Graduate School of Systems and Information Engineering
Date 2008-12-18
Paper # PRMU2008-164
Volume (vol) vol.108
Number (no) 363
Page pp.pp.-
#Pages 6
Date of Issue