Computational and Neural Network Models for the Analysis of Visual Texture
Abstract
The detailed and biological realistic neural model of architectures that utilize Gabor filters for vision computations continues to be the focus of research. Additionally, some further testing of a three layer back propagation learning network for computing slat tilt was undertaken. A model has been developed which simulates the process of texture segmentation in the visual cortex according to the computational model of M.R. Turner et.al. using the McGregor high fidelity neural simulator. This system attempts to faithfully simulate the transfer functions of neurons using various numerical simulation methods.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 04, 1991
- Accession Number
- ADA243717
Entities
People
- Ruzena Bajcsy
Organizations
- Moore School of Electrical Engineering