Energy functions for early vision and analog networks
- 1 June 1989
- journal article
- research article
- Published by Springer Nature in Biological Cybernetics
- Vol. 61 (2) , 115-123
- https://doi.org/10.1007/bf00204595
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.This publication has 27 references indexed in Scilit:
- Probabilistic Solution of Ill-Posed Problems in Computational VisionJournal of the American Statistical Association, 1987
- Computational vision and regularization theoryNature, 1985
- Apparent Motion of Subjective SurfacesPerception, 1985
- Optimization by Simulated AnnealingScience, 1983
- Numerical shape from shading and occluding boundariesArtificial Intelligence, 1981
- Determining optical flowArtificial Intelligence, 1981
- A computational theory of human stereo visionProceedings of the Royal Society of London. B. Biological Sciences, 1979
- Azaarenes in Recent Marine SedimentsScience, 1977
- Multi-level adaptive solutions to boundary-value problemsMathematics of Computation, 1977
- Cooperative Computation of Stereo DisparityScience, 1976