Image transformation using a feature map of multiply descent cost competitive learning

Yasuo Matsuyama

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Summary form only given. It was shown that the feature map obtained by multiple descent cost competitive self-organization can be used for the transformation of images combined with the supervision of an outside intelligence. The example of the change of emotional expression of a face was considered. The task of the first module was to locate the prospective edges. Basically, two orthogonally oriented preliminary networks (horizontal and vertical) are sufficient. This is true because a homogeneous region can be outlined using only vertical and horizontal edges. A prospective edge selection (preliminary) network consists of two types of neurons: image neurons and edge neurons. Each image neuron corresponds to a pixel in the image. Between each image neuron is an edge neuron, one corresponding to every possible edge location for the desired orientation. The goal of the vertical network is to find the prospective vertical edges in the horizontal direction.

Original languageEnglish
Title of host publicationProceedings. IJCNN - International Joint Conference on Neural Networks
Editors Anon
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages936
Number of pages1
ISBN (Print)0780301641
Publication statusPublished - 1992
Externally publishedYes
EventInternational Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA
Duration: 1991 Jul 81991 Jul 12

Other

OtherInternational Joint Conference on Neural Networks - IJCNN-91-Seattle
CitySeattle, WA, USA
Period91/7/891/7/12

Fingerprint

Neurons
Costs
Pixels

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Matsuyama, Y. (1992). Image transformation using a feature map of multiply descent cost competitive learning. In Anon (Ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks (pp. 936). Piscataway, NJ, United States: Publ by IEEE.

Image transformation using a feature map of multiply descent cost competitive learning. / Matsuyama, Yasuo.

Proceedings. IJCNN - International Joint Conference on Neural Networks. ed. / Anon. Piscataway, NJ, United States : Publ by IEEE, 1992. p. 936.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Matsuyama, Y 1992, Image transformation using a feature map of multiply descent cost competitive learning. in Anon (ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks. Publ by IEEE, Piscataway, NJ, United States, pp. 936, International Joint Conference on Neural Networks - IJCNN-91-Seattle, Seattle, WA, USA, 91/7/8.
Matsuyama Y. Image transformation using a feature map of multiply descent cost competitive learning. In Anon, editor, Proceedings. IJCNN - International Joint Conference on Neural Networks. Piscataway, NJ, United States: Publ by IEEE. 1992. p. 936
Matsuyama, Yasuo. / Image transformation using a feature map of multiply descent cost competitive learning. Proceedings. IJCNN - International Joint Conference on Neural Networks. editor / Anon. Piscataway, NJ, United States : Publ by IEEE, 1992. pp. 936
@inproceedings{51a35de6e9174a89929c5aec13667807,
title = "Image transformation using a feature map of multiply descent cost competitive learning",
abstract = "Summary form only given. It was shown that the feature map obtained by multiple descent cost competitive self-organization can be used for the transformation of images combined with the supervision of an outside intelligence. The example of the change of emotional expression of a face was considered. The task of the first module was to locate the prospective edges. Basically, two orthogonally oriented preliminary networks (horizontal and vertical) are sufficient. This is true because a homogeneous region can be outlined using only vertical and horizontal edges. A prospective edge selection (preliminary) network consists of two types of neurons: image neurons and edge neurons. Each image neuron corresponds to a pixel in the image. Between each image neuron is an edge neuron, one corresponding to every possible edge location for the desired orientation. The goal of the vertical network is to find the prospective vertical edges in the horizontal direction.",
author = "Yasuo Matsuyama",
year = "1992",
language = "English",
isbn = "0780301641",
pages = "936",
editor = "Anon",
booktitle = "Proceedings. IJCNN - International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Image transformation using a feature map of multiply descent cost competitive learning

AU - Matsuyama, Yasuo

PY - 1992

Y1 - 1992

N2 - Summary form only given. It was shown that the feature map obtained by multiple descent cost competitive self-organization can be used for the transformation of images combined with the supervision of an outside intelligence. The example of the change of emotional expression of a face was considered. The task of the first module was to locate the prospective edges. Basically, two orthogonally oriented preliminary networks (horizontal and vertical) are sufficient. This is true because a homogeneous region can be outlined using only vertical and horizontal edges. A prospective edge selection (preliminary) network consists of two types of neurons: image neurons and edge neurons. Each image neuron corresponds to a pixel in the image. Between each image neuron is an edge neuron, one corresponding to every possible edge location for the desired orientation. The goal of the vertical network is to find the prospective vertical edges in the horizontal direction.

AB - Summary form only given. It was shown that the feature map obtained by multiple descent cost competitive self-organization can be used for the transformation of images combined with the supervision of an outside intelligence. The example of the change of emotional expression of a face was considered. The task of the first module was to locate the prospective edges. Basically, two orthogonally oriented preliminary networks (horizontal and vertical) are sufficient. This is true because a homogeneous region can be outlined using only vertical and horizontal edges. A prospective edge selection (preliminary) network consists of two types of neurons: image neurons and edge neurons. Each image neuron corresponds to a pixel in the image. Between each image neuron is an edge neuron, one corresponding to every possible edge location for the desired orientation. The goal of the vertical network is to find the prospective vertical edges in the horizontal direction.

UR - http://www.scopus.com/inward/record.url?scp=0026624562&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026624562&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780301641

SP - 936

BT - Proceedings. IJCNN - International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -