Loading...
Please wait, while we are loading the content...
Similar Documents
Estimation de paramètres de champs markoviens cachés avec applications à la segmentation d'images et la localisation de formes
| Content Provider | Semantic Scholar |
|---|---|
| Author | Destrempes, François |
| Copyright Year | 2006 |
| Abstract | We propose a new stochastic algorithm for computing useful Bayesian estimators of Hidden Markov Random Field models, that we caïl Exploration/Selection/Estimation procedure. The algorithm is based on an optimization algorithm of O. François, caÏled the Exploration/Selection aÏgorithm. The novelty consists in using the A Posteriori distribution of the HMRF, as exploration distribution in the E/S algorithm. The ESE procedure computes the estimation of the likelihood parameters and the optimal number of region classes according to global constraints, as well as the segmentation of the image. In our formulation, the total number of region classes is fixed, but classes are allowed or disallowed dynamically. This framework replaces the mechanism of split-and-merge of regions, that can be used in the context of image segmentation. The procedure is applied to the estimation of a HMRF coÏor model for images, whose likelihood is based on multivariate distributions, with each component following a |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://papyrus.bib.umontreal.ca/xmlui/bitstream/handle/1866/16708/Destrempes_Francois_2006_these.pdf?isAllowed=y&sequence=1 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
