Please use this identifier to cite or link to this item:
Title: The infinite hidden Markov random field model
Authors: Tsechpenakis, Gabriel 
Chatzis, Sotirios P. 
Major Field of Science: Engineering and Technology
Field Category: Electrical Engineering - Electronic Engineering - Information Engineering
Keywords: Bayesian inference;FDirichlet process;Hidden Markov random field;Nonparametric models
Issue Date: Jun-2010
Source: IEEE transactions on neural networks, 2010, vol. 21, no. 6, pp. 1004-1014
Volume: 21
Issue: 6
Start page: 1004
End page: 1014
Journal: IEEE Transactions on Neural Networks 
Abstract: Hidden Markov random field (HMRF) models are widely used for image segmentation, as they appear naturally in problems where a spatially constrained clustering scheme is asked for. A major limitation of HMRF models concerns the automatic selection of the proper number of their states, i.e., the number of region clusters derived by the image segmentation procedure. Existing methods, including likelihood- or entropy-based criteria, and reversible Markov chain Monte Carlo methods, usually tend to yield noisy model size estimates while imposing heavy computational requirements. Recently, Dirichlet process (DP, infinite) mixture models have emerged in the cornerstone of nonparametric Bayesian statistics as promising candidates for clustering applications where the number of clusters is unknown a priori; infinite mixture models based on the original DP or spatially constrained variants of it have been applied in unsupervised image segmentation applications showing promising results. Under this motivation, to resolve the aforementioned issues of HMRF models, in this paper, we introduce a nonparametric Bayesian formulation for the HMRF model, the infinite HMRF model, formulated on the basis of a joint Dirichlet process mixture (DPM) and Markov random field (MRF) construction. We derive an efficient variational Bayesian inference algorithm for the proposed model, and we experimentally demonstrate its advantages over competing methodologies
ISSN: 1045-9227
DOI: 10.1109/TNN.2010.2046910
Rights: © IEEE
Type: Article
Affiliation : University of Miami 
Cyprus University of Technology 
Appears in Collections:Άρθρα/Articles

CORE Recommender
Show full item record

Citations 5

checked on Aug 31, 2020


Last Week
Last month
checked on Oct 26, 2020

Page view(s) 20

Last Week
Last month
checked on Oct 31, 2020

Google ScholarTM



Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.