Parallel Distributed Networks for Image Smoothing and Segmentation in Analog VSLI

Abstract

Image smoothing and segmentation algorithms are frequently formulated as optimization problems. Linear and nonlinear (reciprocal) resistive networks have solutions characterized by an extremum principle. Thus, appropriately designed networks can automatically solve certain smoothing and segmentation problems in robot vision. This paper considers switched linear resistive networks and nonlinear resistive networks for such tasks. A new derivation of the latter network type from the former is given via an intermediate stochastic formulation, and a new result relating the solution sets of the two is given for the zero temperature limit. We then present simulation studies of several continuation methods that can be gracefully implemented in analog VLSI and that seem to give 'good' results for these non-convex optimization problems.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1989
Accession Number
ADA216780

Entities

People

  • A. Lumsdaine
  • I. Elfadel
  • J. Wyatt

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Annealing
  • Applied Computer Science
  • Artificial Intelligence
  • Computations
  • Computer Science
  • Computer Vision
  • Computers
  • Electrical Engineering
  • Engineering
  • Equations
  • Heuristic Methods
  • Networks
  • Optimization
  • Resistance
  • Standards
  • Topology

Readers

  • Neural Network Machine Learning.
  • Operations Research
  • Thin Film Deposition Science.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Autonomy