Presentation 2007-09-04
Invariant codes for similar transformations and its application to Shape Matching
Eiji Yoshida, Seiichi Mita,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a new method of shape matching. Our proposed method encodes the contour of an object by using the curvature of an object. If two objects are similar (translation, rotation and scaling) in shape, these codes themselves or their cyclic shift have the same values. We have compared our method with other methods such as Fourier descriptor, CSS(curvature scale space) and shape context. We have shown that the computational cost of our method is lower than that of CSS and moreover the recognition rate of our method is nearly the same as CSS.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) shape matching / invariant code / curvature / shape classification
Paper # PRMU2007-73,HIP2007-82
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/8/27(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) Invariant codes for similar transformations and its application to Shape Matching
Sub Title (in English)
Keyword(1) shape matching
Keyword(2) invariant code
Keyword(3) curvature
Keyword(4) shape classification
1st Author's Name Eiji Yoshida
1st Author's Affiliation Toyota Technological Institute()
2nd Author's Name Seiichi Mita
2nd Author's Affiliation Toyota Technological Institute
Date 2007-09-04
Paper # PRMU2007-73,HIP2007-82
Volume (vol) vol.107
Number (no) 206
Page pp.pp.-
#Pages 6
Date of Issue