Presentation 2004/9/3
Appearance Based 3D Object Recognition Robust against Local Occlusion, Specular Reflection, and Complex Background
Yoshinori Kusachi, Akira Suzuki, Kenichi Arakawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A novel appearance based method for object recognition is proposed, which is robust against occlusion, specular reflection, and complex background. Our method uses a subspace method basically, and in this paper, we describe that co-variance matrix for a large number of images, added to original images with all considerable noises, is calculable with just original images. Experimental results showed our method marked high recognition rates for severely damaged images with occlusion, specular reflection, and complex background.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Appearance / Occlusio / Specular reflection / Complex background / Subspace method / Noises / Destroyed patterns
Paper # PRMU2004-71
Date of Issue

Conference Information
Committee PRMU
Conference Date 2004/9/3(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) Appearance Based 3D Object Recognition Robust against Local Occlusion, Specular Reflection, and Complex Background
Sub Title (in English)
Keyword(1) Appearance
Keyword(2) Occlusio
Keyword(3) Specular reflection
Keyword(4) Complex background
Keyword(5) Subspace method
Keyword(6) Noises
Keyword(7) Destroyed patterns
1st Author's Name Yoshinori Kusachi
1st Author's Affiliation NTT Cyber Space Laboratories()
2nd Author's Name Akira Suzuki
2nd Author's Affiliation NTT Cyber Space Laboratories
3rd Author's Name Kenichi Arakawa
3rd Author's Affiliation NTT Cyber Space Laboratories
Date 2004/9/3
Paper # PRMU2004-71
Volume (vol) vol.104
Number (no) 290
Page pp.pp.-
#Pages 8
Date of Issue