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.
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