Presentation 2008-06-19
Shape Segmentation Based on Learning of Deformation Models
Ruiqi GUO, Shinichiro OMACHI, Hirotomo ASO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a novel framework of shape segmentation based on the learning of deformation models of multiple shapes. Given a shape to be segmented, other shapes of the same category are taken as reference for segmentation. The transformation model from the target image to every other image is then estimated. Finally, normalized-cut graph partition is applied to the graph constructed based on the dissimiliarity of local patches in the target image, and a segmentation of the shape is carried out. Experimental results for images from MPEG7 shape database show the effectiveness of the proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) shape segmentation / shape matching / deformation model / graph partition
Paper # DE2008-1,PRMU2008-19
Date of Issue

Conference Information
Committee PRMU
Conference Date 2008/6/12(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Shape Segmentation Based on Learning of Deformation Models
Sub Title (in English)
Keyword(1) shape segmentation
Keyword(2) shape matching
Keyword(3) deformation model
Keyword(4) graph partition
1st Author's Name Ruiqi GUO
1st Author's Affiliation School of Engineering, Tohoku University()
2nd Author's Name Shinichiro OMACHI
2nd Author's Affiliation Graduate School of Engineering, Tohoku University
3rd Author's Name Hirotomo ASO
3rd Author's Affiliation Graduate School of Engineering, Tohoku University
Date 2008-06-19
Paper # DE2008-1,PRMU2008-19
Volume (vol) vol.108
Number (no) 94
Page pp.pp.-
#Pages 5
Date of Issue