Learning Model Structures from Images

Andreas HELD; Keiichi ABE

Learning Model Structures from Images

Andreas HELD, Keiichi ABE

Full Text Views

0

Share
Cite this

Summary :

Based on a newly proposed notion of relational network, a novel learning mechanism for model acquisition is developed. This new mechanism explicitly deals with both qualitative and quantitative relations between parts of an object. Qualitative relations are mirrored in the topology of the network. Quantitative relations appear in the form of generalized predicates, that is, predicates that are graded in their validity over a certain range. Starting from a decomposition of 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. Topological generalization is achieved by a simple rule-based graph generalizer. Generalization of the predicates uses some ideas from MYCIN. After successful generalization, the system attempts to derive a simple and coarse description of the achieved result in terms of near natural language. Several examples underline the validity of relational networks and illustrate the performance of the proposed system.

Publication: IEICE TRANSACTIONS on Information Vol.E77-D No.11 pp.1281-1290

Publication Date: 1994/11/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Computer Vision)

Category

Cite this

Copy

Andreas HELD, Keiichi ABE, "Learning Model Structures from Images" in IEICE TRANSACTIONS on Information, vol. E77-D, no. 11, pp. 1281-1290, November 1994, doi: .
Abstract: Based on a newly proposed notion of relational network, a novel learning mechanism for model acquisition is developed. This new mechanism explicitly deals with both qualitative and quantitative relations between parts of an object. Qualitative relations are mirrored in the topology of the network. Quantitative relations appear in the form of generalized predicates, that is, predicates that are graded in their validity over a certain range. Starting from a decomposition of 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. Topological generalization is achieved by a simple rule-based graph generalizer. Generalization of the predicates uses some ideas from MYCIN. After successful generalization, the system attempts to derive a simple and coarse description of the achieved result in terms of near natural language. Several examples underline the validity of relational networks and illustrate the performance of the proposed system.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e77-d_11_1281/_p

Copy

@ARTICLE{e77-d_11_1281,
author={Andreas HELD, Keiichi ABE, },
journal={IEICE TRANSACTIONS on Information},
title={Learning Model Structures from Images},
year={1994},
volume={E77-D},
number={11},
pages={1281-1290},
abstract={Based on a newly proposed notion of relational network, a novel learning mechanism for model acquisition is developed. This new mechanism explicitly deals with both qualitative and quantitative relations between parts of an object. Qualitative relations are mirrored in the topology of the network. Quantitative relations appear in the form of generalized predicates, that is, predicates that are graded in their validity over a certain range. Starting from a decomposition of 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. Topological generalization is achieved by a simple rule-based graph generalizer. Generalization of the predicates uses some ideas from MYCIN. After successful generalization, the system attempts to derive a simple and coarse description of the achieved result in terms of near natural language. Several examples underline the validity of relational networks and illustrate the performance of the proposed system.},
keywords={},
doi={},
ISSN={},
month={November},}

Copy

TY - JOUR
TI - Learning Model Structures from Images
T2 - IEICE TRANSACTIONS on Information
SP - 1281
EP - 1290
AU - Andreas HELD
AU - Keiichi ABE
PY - 1994
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E77-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 1994
AB - Based on a newly proposed notion of relational network, a novel learning mechanism for model acquisition is developed. This new mechanism explicitly deals with both qualitative and quantitative relations between parts of an object. Qualitative relations are mirrored in the topology of the network. Quantitative relations appear in the form of generalized predicates, that is, predicates that are graded in their validity over a certain range. Starting from a decomposition of 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. Topological generalization is achieved by a simple rule-based graph generalizer. Generalization of the predicates uses some ideas from MYCIN. After successful generalization, the system attempts to derive a simple and coarse description of the achieved result in terms of near natural language. Several examples underline the validity of relational networks and illustrate the performance of the proposed system.
ER -