A Neural Network Model of Object Segmentation and Feature Binding in Visual Cortex
PENNSYLVANIA UNIV PHILADELPHIA DEPT OF BIOENGINEERING
Pagination or Media Count:
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 networks response indicating the existence of robust psychophysical properties in the system.
- Anatomy and Physiology