Neural Network Model of Visual System based on Feature Integration Theory

17 References
  • KUME Hiroshi
    Department of Electrical Engineering, Faculty of Science and Technology, Keio University
  • OSANA Yuko
    Department of Electrical Engineering, Faculty of Science and Technology, Keio University
  • HAGIWARA Masafumi
    Department of Electrical Engineering, Faculty of Science and Technology, Keio University

Bibliographic Information

Other Title
  • 特徴統合理論に基づく視覚ニューラルネットワークモデル

Search this article

Description

In this report, we propose a neural network model of visual system based on feature integration theory. It can solve the binding problem and recognize plural objects which have some features in the vision. The proposed model has feature recognition stage and feature integration stage. In the feature recognition stage, there are two modules; the form recognition module and the color recognition module. In these modules, form and color are processed in parallel. The form recognition module is constructed of neocognitron and the color recognition module is constructed of LVQ (Learning Vector Quantization) neural network. The feature integration stage is based on the feature integration theory, which is a representative theory for explaining all phenomena occurring invisual system as a consistent process. We carried out a series of computer simulations and confirmed that the proposed model can recognize plural objects which have some features in the vision.

Journal

References(17)*help

See more

Keywords

Details 詳細情報について

  • CRID
    1570572702517214720
  • NII Article ID
    110003233539
  • NII Book ID
    AN10091178
  • Text Lang
    ja
  • Data Source
    • CiNii Articles

Report a problem

Back to top