A Neural Network Model of Object Segmentation and Feature Binding in Visual Cortex

Abstract

We present neural network simulations of how the visual cortex may segment objects and bind attributes based on depth-from-occlusion. We briefly discuss one particular subprocess in our occlusion-based model most relevant to segmentation and binding: determination of the direction of figure. We propose that our model allows us to address a central issue in object recognition: how the visual system defines an object. In addition, we test our model on 'illusory' stimuli, with the network's response indicating the existence of robust psychophysical properties in the system.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1990
Accession Number
ADA248100

Entities

People

  • Leif H. Finkel
  • Paul Sajda

Organizations

  • University of Pennsylvania

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Cognitive Neuroscience
  • Cognitive Science
  • Computer Vision
  • Feature Extraction
  • Firing Rate
  • Identification
  • Military Research
  • Nervous System
  • Neural Networks
  • Neurosciences
  • Perception
  • Simulations
  • Simulators
  • Surface Properties
  • Two Dimensional
  • Vascular System Injuries
  • Visual Cortex

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Immunology
  • Vision Science/Vision Psychology/Cognitive Neuroscience.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks