Presentation 2011-07-25
A Gabor Wavelet Pyramid-based Elastic Graph Dynamic Link Model
Yasuomi D. Sato, Yasutaka Kuriya,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We present introduction about technical improvement of the Elastic Graph Matching (EGM) algorithm, using Gabor wavelet pyramid image. One of the most important points is to investigate how advantages of the improved EGM are brought about, in comparison with existing vision technology. In such investigation, we try to solve typical problems in the EGM as follows : (1) computational costs for Gabor feature extraction and (2) memory sizes of Gabor feature representations. We indicate higher potentials of the Gabor wavelet pyramid based EGM than those of the computer vision technique using another pramid image. One of the potentials is correspodence finding. We also imply that down-sampling images in the Gabor pyramid causes loss of local potentials of energy function in the EGM to effectively detect optimal positions on the image.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Gabor Pyramid / Elastic Graph Matching / Correspondence Problem / Object Recognition
Paper # NC2011-23
Date of Issue

Conference Information
Committee NC
Conference Date 2011/7/18(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Gabor Wavelet Pyramid-based Elastic Graph Dynamic Link Model
Sub Title (in English)
Keyword(1) Gabor Pyramid
Keyword(2) Elastic Graph Matching
Keyword(3) Correspondence Problem
Keyword(4) Object Recognition
1st Author's Name Yasuomi D. Sato
1st Author's Affiliation Department of Brain Science and Engineering, Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology:Frankfurt Institute for Advanced Studies (FIAS), Johann Wolfgang Goethe University:RIKEN BSI-TOYOTA Collaboration Center()
2nd Author's Name Yasutaka Kuriya
2nd Author's Affiliation Department of Brain Science and Engineering, Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
Date 2011-07-25
Paper # NC2011-23
Volume (vol) vol.111
Number (no) 157
Page pp.pp.-
#Pages 4
Date of Issue