In recent years many researchers have investigated the use of Markov random fields (MRFs) for computer vision. The computational complexity of the implementation has been a drawback of MRFs. In this paper we derive deterministic approximations to MRFs models. All the theoretical results are obtained in the framework of the mean field theory from statistical mechanics. Because we use MRFs models the mean field equations lead to parallel and iterative algorithms. One of the considered models for image reconstruction is shown to give in a natural way the graduate non-convexity algorithm proposed by Blake and Zisserman.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6025 |
| Date | 01 May 1989 |
| Creators | Geiger, Davi, Girosi, Federico |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 37 p., 3090418 bytes, 2411062 bytes, application/postscript, application/pdf |
| Relation | AIM-1114 |
Page generated in 0.0019 seconds