Binding and Segmentation of Visual Images by Means of Oscillatory Neurons

Abstract

A neural network based on Wilson-Cowan oscillators is used to perform object recognition in a two-dimensional visual scene. The temporal correlation among groups of oscillating neurons is used as the main criterion to solve the classic binding and segmentation problem. The network uses an original pattern of short range lateral excitations among adjacent neurons to achieve the binding problem, and an external inhibitory global neuron to provide segmentation of multiple objects in the same visual scene. The latter may represent an "attention mechanism" from neurons at a higher hierarchical level. Simulations performed by using multiple idealized figures (up to 4-5) in the presence of noise suggest that the network can satisfactorily recognize objects in most cases. However the threshold and time constant of the attention mechanism depend on the complexity (number of objects and level of noise) of the scene under examination. The present results may be useful to improve our understanding of how distributed activities are integrated in the neural system to form single object perceptions. In perspective the proposed model may find applications in practical algorithms for object recognition.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 25, 2001
Accession Number
ADA410278

Entities

People

  • A. Sarti
  • G. E. La Cara
  • M. Ursino

Organizations

  • University of Bologna

Tags

DTIC Thesaurus Topics

  • Brain
  • Cerebral Cortex
  • Computer Science
  • Computer Vision
  • Computers
  • Couplings
  • Differential Equations
  • Inhibition
  • Neural Networks
  • Neurons
  • Object Recognition
  • Oscillation
  • Oscillators
  • Personal Computers
  • Recognition
  • Separators
  • Simulations

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Control Systems Engineering.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference