Solving the binding problem with feature integration theory

Hiroshi Kume, Yuko Osana, Masafumi Hagiwara

Research output: Contribution to conferencePaper

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.

Original languageEnglish
Pages200-205
Number of pages6
Publication statusPublished - 1999 Dec 1
EventInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
Duration: 1999 Jul 101999 Jul 16

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'99)
CityWashington, DC, USA
Period99/7/1099/7/16

    Fingerprint

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Kume, H., Osana, Y., & Hagiwara, M. (1999). Solving the binding problem with feature integration theory. 200-205. Paper presented at International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, .