Solving the binding problem with feature integration theory

Hiroshi Kume, Yuko Osana, Masafumi Hagiwara

研究成果: Conference contribution

抄録

In this paper, we propose a neural network model of visual system based on the feature integration theory. The proposed model has a structure based on the hierarchical structure of visual system and selectiveness of information by visual attention. The proposed model consists of two stages: the feature recognition stage and the feature integration stage. In the feature recognition stage, there are two modules: the form recognition module and the color recognition module. In these modules, information of form and color is separately processed in parallel. The form recognition module is constructed of the neocognitron, and the color recognition module is constructed of the LVQ neural network. The feature integration stage is based on the feature integration theory, which is a representative theory for explaining all phenomena occurring in visual system as a consistent process. We carried out computer simulations and confirmed that the proposed model can recognize plural objects which have some features in vision and solve the binding problem.

元の言語English
ホスト出版物のタイトルProceedings of the International Joint Conference on Neural Networks
出版者IEEE
ページ200-205
ページ数6
1
出版物ステータスPublished - 1999
イベントInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
継続期間: 1999 7 101999 7 16

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'99)
Washington, DC, USA
期間99/7/1099/7/16

Fingerprint

Color
Neural networks
Computer simulation

ASJC Scopus subject areas

  • Software

これを引用

Kume, H., Osana, Y., & Hagiwara, M. (1999). Solving the binding problem with feature integration theory. : Proceedings of the International Joint Conference on Neural Networks (巻 1, pp. 200-205). IEEE.

Solving the binding problem with feature integration theory. / Kume, Hiroshi; Osana, Yuko; Hagiwara, Masafumi.

Proceedings of the International Joint Conference on Neural Networks. 巻 1 IEEE, 1999. p. 200-205.

研究成果: Conference contribution

Kume, H, Osana, Y & Hagiwara, M 1999, Solving the binding problem with feature integration theory. : Proceedings of the International Joint Conference on Neural Networks. 巻. 1, IEEE, pp. 200-205, International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, 99/7/10.
Kume H, Osana Y, Hagiwara M. Solving the binding problem with feature integration theory. : Proceedings of the International Joint Conference on Neural Networks. 巻 1. IEEE. 1999. p. 200-205
Kume, Hiroshi ; Osana, Yuko ; Hagiwara, Masafumi. / Solving the binding problem with feature integration theory. Proceedings of the International Joint Conference on Neural Networks. 巻 1 IEEE, 1999. pp. 200-205
@inproceedings{76345db1d1f34cdf85a31df083035415,
title = "Solving the binding problem with feature integration theory",
abstract = "In this paper, we propose a neural network model of visual system based on the feature integration theory. The proposed model has a structure based on the hierarchical structure of visual system and selectiveness of information by visual attention. The proposed model consists of two stages: the feature recognition stage and the feature integration stage. In the feature recognition stage, there are two modules: the form recognition module and the color recognition module. In these modules, information of form and color is separately processed in parallel. The form recognition module is constructed of the neocognitron, and the color recognition module is constructed of the LVQ neural network. The feature integration stage is based on the feature integration theory, which is a representative theory for explaining all phenomena occurring in visual system as a consistent process. We carried out computer simulations and confirmed that the proposed model can recognize plural objects which have some features in vision and solve the binding problem.",
author = "Hiroshi Kume and Yuko Osana and Masafumi Hagiwara",
year = "1999",
language = "English",
volume = "1",
pages = "200--205",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "IEEE",

}

TY - GEN

T1 - Solving the binding problem with feature integration theory

AU - Kume, Hiroshi

AU - Osana, Yuko

AU - Hagiwara, Masafumi

PY - 1999

Y1 - 1999

N2 - In this paper, we propose a neural network model of visual system based on the feature integration theory. The proposed model has a structure based on the hierarchical structure of visual system and selectiveness of information by visual attention. The proposed model consists of two stages: the feature recognition stage and the feature integration stage. In the feature recognition stage, there are two modules: the form recognition module and the color recognition module. In these modules, information of form and color is separately processed in parallel. The form recognition module is constructed of the neocognitron, and the color recognition module is constructed of the LVQ neural network. The feature integration stage is based on the feature integration theory, which is a representative theory for explaining all phenomena occurring in visual system as a consistent process. We carried out computer simulations and confirmed that the proposed model can recognize plural objects which have some features in vision and solve the binding problem.

AB - In this paper, we propose a neural network model of visual system based on the feature integration theory. The proposed model has a structure based on the hierarchical structure of visual system and selectiveness of information by visual attention. The proposed model consists of two stages: the feature recognition stage and the feature integration stage. In the feature recognition stage, there are two modules: the form recognition module and the color recognition module. In these modules, information of form and color is separately processed in parallel. The form recognition module is constructed of the neocognitron, and the color recognition module is constructed of the LVQ neural network. The feature integration stage is based on the feature integration theory, which is a representative theory for explaining all phenomena occurring in visual system as a consistent process. We carried out computer simulations and confirmed that the proposed model can recognize plural objects which have some features in vision and solve the binding problem.

UR - http://www.scopus.com/inward/record.url?scp=0033348739&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033348739&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0033348739

VL - 1

SP - 200

EP - 205

BT - Proceedings of the International Joint Conference on Neural Networks

PB - IEEE

ER -