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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 04, 1991
Accession Number
ADA243717

Entities

People

  • Ruzena Bajcsy

Organizations

  • Moore School of Electrical Engineering

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence Software
  • Boundaries
  • Computations
  • Computer Vision
  • Computers
  • High Density
  • Image Segmentation
  • Low Density
  • Network Topology
  • Neural Networks
  • Reliability
  • Simulations
  • Simulators
  • Transfer Functions
  • Two Dimensional
  • Visual Cortex

Readers

  • Computational Modeling and Simulation
  • Computer Vision.
  • Neural Network Machine Learning.

Technology Areas

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