Nonlinear Analog Networks for Image Smoothing and Segmentation

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 consists switched linear resistive networks and nonlinear resistive networks for such tasks. The latter network type is derived from the former 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 stimulation 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
Jan 01, 1991
Accession Number
ADA241164

Entities

People

  • A. Lumsdaine
  • I. M. Elfadel
  • John Wyatt

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Artificial Intelligence
  • Computer Vision
  • Heuristic Methods
  • Image Processing
  • Image Reconstruction
  • Image Restoration
  • Information Systems
  • Networks
  • Optimization
  • Probability
  • Probability Distributions
  • Random Variables
  • Simulations
  • Topology
  • Two Dimensional

Readers

  • Control Systems Engineering.
  • Neural Network Machine Learning.
  • Operations Research

Technology Areas

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