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.
Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6063 |
Date | 01 November 1987 |
Creators | Yuille, Alan |
Source Sets | M.I.T. Theses and Dissertation |
Language | en_US |
Detected Language | English |
Format | 53 p., 3859651 bytes, 1533812 bytes, application/postscript, application/pdf |
Relation | AIM-987 |
Page generated in 0.0013 seconds