Presentation 2011-12-16
Shape similarity estimation method using Procrustes Distance and its application to clothes images
Kyoko SUDO, Jun SHIMAMURA, Masashi MORIMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a method to extract shape similarity index based on the probability of distribution of the feature points, which doesn't require contour extraction or image binarization. Distribution of feature points in shapes by each category is approximately described as a GMM. The category of the target shape is estimated through parameter estimation of the model, and the shape similarity index is obtained. We show that the index is the approximation of Procrustes distance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) shape analysis / Procrustes Distance / GMM / clothes images
Paper # PRMU2011-139
Date of Issue

Conference Information
Committee PRMU
Conference Date 2011/12/8(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) Shape similarity estimation method using Procrustes Distance and its application to clothes images
Sub Title (in English)
Keyword(1) shape analysis
Keyword(2) Procrustes Distance
Keyword(3) GMM
Keyword(4) clothes images
1st Author's Name Kyoko SUDO
1st Author's Affiliation NTT Cyber Space Laboratories, Nippon Telegraph and Telephone Corporation()
2nd Author's Name Jun SHIMAMURA
2nd Author's Affiliation NTT Cyber Space Laboratories, Nippon Telegraph and Telephone Corporation
3rd Author's Name Masashi MORIMOTO
3rd Author's Affiliation NTT Cyber Space Laboratories, Nippon Telegraph and Telephone Corporation
Date 2011-12-16
Paper # PRMU2011-139
Volume (vol) vol.111
Number (no) 353
Page pp.pp.-
#Pages 6
Date of Issue