Energy Functions for Early Vision and Analog Networks.

Abstract

Abstract. This paper describes attempts to model the modules of early vision in terms of minimizing energy functions, in particular energy functions allowing discontinuities in the solution. It examines the success of using Hopfield-style analog networks for solving such problems. Finally it discusses the limitations of the energy function approach. Keywords: Surface interpolation; Motion smoothing; Segmentation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1987
Accession Number
ADA190384

Entities

People

  • Alan Yuille

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Computations
  • Computer Graphics
  • Computers
  • Content Addressable Memory
  • Electrical Engineering
  • Equations
  • Heuristic Methods
  • Image Processing
  • Information Systems
  • Lyapunov Functions
  • Mean Field Theory
  • Neural Networks
  • Stratified Fluids
  • Two Dimensional

Readers

  • Computer Vision.
  • Operations Research
  • Plasma Physics / Magnetohydrodynamics