Presentation 1995/7/27
To Follow Drifting Images By Dynamic Link Architecture Using Local Linear Mapping
Takeshi Mito, Koji Kurata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Von der Malsburg has proposed dynamic link architecture, in which self-organizing map is applied to image recognition by matching data to sample. This method is expected to be tolerant to distotion or rotation of data images. In practice, his group demonstrated face recognition as an application of dynamic link. However the model used in the simulation, which is capable of identification of translated images with original images, can not class rotated images with it. Because images rotated or translated are congruent with original images, we need a model able to regard rotated images as same images. So we propose a new model in which rotated images are also classed with original images and show some results of computer simulation to follow drifting images with black and white level.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) dynamic link / topographic mapping / local linear mapping / matching data to sample / image recognition
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1995/7/27(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) To Follow Drifting Images By Dynamic Link Architecture Using Local Linear Mapping
Sub Title (in English)
Keyword(1) dynamic link
Keyword(2) topographic mapping
Keyword(3) local linear mapping
Keyword(4) matching data to sample
Keyword(5) image recognition
1st Author's Name Takeshi Mito
1st Author's Affiliation Department of Biophysical Engineering, Faculty of Engineering Science, Osaka University()
2nd Author's Name Koji Kurata
2nd Author's Affiliation Department of Biophysical Engineering, Faculty of Engineering Science, Osaka University
Date 1995/7/27
Paper #
Volume (vol) vol.95
Number (no) 189
Page pp.pp.-
#Pages 8
Date of Issue