An analog Hopfield network to overcome excessive smoothing in shape from shading

DOI10.1016/0016-0032(94)90038-8zbMath0834.68120OpenAlexW2086387237WikidataQ128039933 ScholiaQ128039933MaRDI QIDQ1898164

S. Ravindranath, Uday B. Desai

Publication date: 18 March 1996

Published in: Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0016-0032(94)90038-8

zbMATH Keywords

simulated annealingshape from shadingBoltzmann machine

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05)

Cites Work

• Optimization by Simulated Annealing
• Numerical shape from shading and occluding boundaries
• Direct analytical methods for solving Poisson equations in computer vision problems
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• The variational approach to shape from shading
• A method for enforcing integrability in shape from shading algorithms
• Neurons with graded response have collective computational properties like those of two-state neurons.
• Unnamed Item

This page was built for publication: An analog Hopfield network to overcome excessive smoothing in shape from shading