Fusion of hidden Markov random field models and its Bayesian estimation

被引：14
|
作者：
Destrempes, Francois
Angers, Jean-Francois
Mignotte, Max
机构：
[1] Univ Montreal, Dept Informat & Rech Operat, Montreal, PQ H3C 3J7, Canada
[2] Univ Montreal, Dept Math & Stat, Montreal, PQ H3C 3J7, Canada
来源：
IEEE TRANSACTIONS ON IMAGE PROCESSING | 2006年 / 15卷 / 10期
关键词：
bayesian estimation; color and texture segmentation; Exploration/Selection algorithm; Exploration/Selection/Estimation procedure; fusion of hidden Markov random field models; Julesz ensembles; Markov Chain Monte Carlo (MCM) algorithm;
D O I：
10.1109/TIP.2006.877522
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
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.
引用
收藏
页码：2920 / 2935
页数：16
相关论文
共 50 条
  • [21] Utilizing Gaussian Markov Random Field Properties of Bayesian Animal Models
    Steinsland, Ingelin
    Jensen, Henrik
    [J]. BIOMETRICS, 2010, 66 (03) : 763 - 771
  • [22] Computational Bayesian analysis of hidden Markov models
    Ryden, T
    Titterington, DM
    [J]. JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 1998, 7 (02) : 194 - 211
  • [23] Crandem systems-conditional random field acoustic models for hidden Markov models
    Fosler-Lussier, Eric
    Morris, Jeremy
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4049 - 4052
  • [24] Approximate Bayesian inference for hierarchical Gaussian Markov random field models
    Rue, Havard
    Martino, Sara
    [J]. JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2007, 137 (10) : 3177 - 3192
  • [25] Asymptotics of the Bayesian estimator of hidden Markov models
    Mevel, L
    Finesso, L
    [J]. 2000 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, PROCEEDINGS, 2000, : 111 - 111
  • [26] Bayesian quantile nonhomogeneous hidden Markov models
    Liu, Hefei
    Song, Xinyuan
    Tang, Yanlin
    Zhang, Baoxue
    [J]. STATISTICAL METHODS IN MEDICAL RESEARCH, 2021, 30 (01) : 112 - 128
  • [27] Bayesian Hidden Markov Models for Financial Data
    Castellano, Rosella
    Scaccia, Luisa
    [J]. DATA ANALYSIS AND CLASSIFICATION, 2010, : 453 - 461
  • [28] Bayesian model selection for Markov, hidden Markov, and multinomial models
    Johansson, Mathias
    Olofsson, Tomas
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2007, 14 (02) : 129 - 132
  • [29] Bayesian nonparametric priors for hidden Markov random fields
    Hongliang Lü
    Julyan Arbel
    Florence Forbes
    [J]. Statistics and Computing, 2020, 30 : 1015 - 1035
  • [30] Bayesian nonparametric priors for hidden Markov random fields
    Lu, Hongliang
    Arbel, Julyan
    Forbes, Florence
    [J]. STATISTICS AND COMPUTING, 2020, 30 (04) : 1015 - 1035
12345