Presentation 1994/5/19
Learning Model Structures from Binary Images
Andreas Held, Keiichi Abe,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Based on a newly proposed notion of relational network,a novel learning mechanism for image model acquisition is developed. Starting from a decomposition of two-dimensional binary objects into meaningful parts,first a description of the decomposition in terms of relational networks is obtained.Based on the description of two or more instances of the same concept,generalizations are obtained by first finding matchings between instances.Generalizing itself proceeds on two levels:the topological and the predicate level.After generalizing,the system attempts to find an explanation of the result in terms of natural language.An example underlines the validity of relational networks and illustrates the performance of the proposed system.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Shape recognition / Model acquisition / Learning / Relational network
Paper # PRU94-2
Date of Issue

Conference Information
Committee PRU
Conference Date 1994/5/19(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 Understanding (PRU)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning Model Structures from Binary Images
Sub Title (in English)
Keyword(1) Shape recognition
Keyword(2) Model acquisition
Keyword(3) Learning
Keyword(4) Relational network
1st Author's Name Andreas Held
1st Author's Affiliation Graduate School of Electronic Science and Technology,Shizuoka University()
2nd Author's Name Keiichi Abe
2nd Author's Affiliation Department of Computer Science,Faculty of Engineering,Shizuoka University
Date 1994/5/19
Paper # PRU94-2
Volume (vol) vol.94
Number (no) 50
Page pp.pp.-
#Pages 8
Date of Issue