Presentation 2004/3/10
Universality of Scaling Images with Wavelet Transform and Self-Organizing Maps : Formation of degenerated maps by the multi-resolution maps
Shinji AKIMOTO, Masatoshi SEKINE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a multi-resolution map which uses wavelet transform and multi-layer self-organization maps. We show how the distribution of sample in the image space would change using the multi-resolution maps. It is found that the low-resolution map is formed as degenerated map of high-resolution map. Using this property, multi-resolution template matching is performed and the efficiency of a multi-resolution map is shown.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Wavelet Transform / Self-Organizing-Map / Multi-Resolution / Template Matching
Paper # NC2003-144
Date of Issue

Conference Information
Committee NC
Conference Date 2004/3/10(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) Universality of Scaling Images with Wavelet Transform and Self-Organizing Maps : Formation of degenerated maps by the multi-resolution maps
Sub Title (in English)
Keyword(1) Wavelet Transform
Keyword(2) Self-Organizing-Map
Keyword(3) Multi-Resolution
Keyword(4) Template Matching
1st Author's Name Shinji AKIMOTO
1st Author's Affiliation The Graduate School of Technology, Tokyo University of Agriculture & Technology()
2nd Author's Name Masatoshi SEKINE
2nd Author's Affiliation The Faculty of Technology, Tokyo University of Agriculture & Technology
Date 2004/3/10
Paper # NC2003-144
Volume (vol) vol.103
Number (no) 732
Page pp.pp.-
#Pages 6
Date of Issue