Fusion of Hidden Markov Random Field models and its Bayesian estimation. Export

@article{citeulike:890304, abstract = {In this paper, we present a Hidden Markov Random Field (HMRF) data-fusion model. The proposed model is applied to the segmentation of natural images based on the fusion of colors and textons into Julesz ensembles. The corresponding Exploration/ Selection/Estimation (ESE) procedure for the estimation of the parameters is presented. This method achieves the estimation of the parameters of the Gaussian kernels, the mixture proportions, the region labels, the number of regions, and the Markov hyper-parameter. Meanwhile, we present a new proof of the asymptotic convergence of the ESE procedure, based on original finite time bounds for the rate of convergence.}, address = {D\'{e}partement d'Informatique et de Recherche Op\'{e}rationnelle, Universit\'{e} de Montr\'{e}al, Pavilion Andr\'{e}-Aisenstadt, Canada. destremp@iro.umontreal.ca}, author = {Destrempes, F. and Angers, J. F. and Mignotte, M.}, citeulike-article-id = {890304}, citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/17022259}, citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=17022259}, issn = {1057-7149}, journal = {IEEE Trans Image Process}, keywords = {mrf, partition\_function, spatial}, month = {October}, number = {10}, pages = {2920--2935}, posted-at = {2006-10-09 18:16:34}, priority = {2}, title = {Fusion of Hidden Markov Random Field models and its Bayesian estimation.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/17022259}, volume = {15}, year = {2006} }

TY - JOUR ID - citeulike:890304 L3 - citeulike-article-id:890304 N2 - In this paper, we present a Hidden Markov Random Field (HMRF) data-fusion model. The proposed model is applied to the segmentation of natural images based on the fusion of colors and textons into Julesz ensembles. The corresponding Exploration/ Selection/Estimation (ESE) procedure for the estimation of the parameters is presented. This method achieves the estimation of the parameters of the Gaussian kernels, the mixture proportions, the region labels, the number of regions, and the Markov hyper-parameter. Meanwhile, we present a new proof of the asymptotic convergence of the ESE procedure, based on original finite time bounds for the rate of convergence. IS - 10 JF - IEEE Trans Image Process SN - 1057-7149 AD - Département d'Informatique et de Recherche Opérationnelle, Université de Montréal, Pavilion André-Aisenstadt, Canada. destremp@iro.umontreal.ca EP - 2935 TI - Fusion of Hidden Markov Random Field models and its Bayesian estimation. VL - 15 SP - 2920 KW - mrf KW - partition_function KW - spatial AU - Destrempes, F AU - Angers, JF AU - Mignotte, M PY - 2006/10// UR - http://view.ncbi.nlm.nih.gov/pubmed/17022259 ER -