Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A stochastic method for Bayesian estimation of hidden Markov random field models with application to a color model.

François Destrempes1, Max Mignotte, Jean-François Angers

  • 1Département d'Informatique et de Recherche Opérationnelle, Université de Montréal, Montréal, H3C 3J7 QC Canada.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|August 27, 2005
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Comparison of four attenuation-compensation methods for backscatter coefficient estimation and characterization of focal liver lesions.

Physics in medicine and biology·2026
Same author

Theoretical Foundations of the Echo Envelope Statistical Modeling: A Tutorial.

IEEE transactions on ultrasonics, ferroelectrics, and frequency control·2025
Same author

Thoracolumbar Fascia Microstructure and Low Back Pain: Insights From Quantitative Ultrasound Homodyned K-Distribution Statistical Modeling.

Ultrasound in medicine & biology·2025
Same author

Enhancing Liver Nodule Visibility and Diagnostic Classification Using Ultrasound Local Attenuation Coefficient Slope Imaging.

Ultrasound in medicine & biology·2025
Same author

A Phantom-Free Approach for Estimating the Backscatter Coefficient of Aggregated Red Blood Cells Applied to COVID-19 Patients.

IEEE transactions on ultrasonics, ferroelectrics, and frequency control·2024
Same author

Effect of rt-PA on Shear Wave Mechanical Assessment and Quantitative Ultrasound Properties of Blood Clot Kinetics In Vitro.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2024
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

GoP-based Quality Enhancement on Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Multi-Branch Tree-based Fusion Neural Architecture Search with Zero-Cost Screen for Multi-Modal Classification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

We introduce a new Exploration/Selection/Estimation (ESE) algorithm for Bayesian estimation in hidden Markov random field (HMRF) models. This method enhances image segmentation by dynamically adjusting region classes and estimating model parameters.

Area of Science:

  • Computer Vision
  • Statistical Modeling
  • Image Processing

Background:

  • Hidden Markov Random Field (HMRF) models are crucial for image analysis and segmentation.
  • Existing methods for HMRF model parameter estimation and segmentation can be computationally intensive or lack flexibility.
  • Accurate estimation of likelihood parameters and optimal number of region classes is essential for effective image segmentation.

Purpose of the Study:

  • To propose a novel stochastic algorithm, the Exploration/Selection/Estimation (ESE) procedure, for Bayesian estimation of HMRF models.
  • To compute likelihood parameters, optimal number of region classes, and image segmentation using the ESE procedure.
  • To introduce a flexible framework that dynamically allows or disallows region classes, replacing traditional split-and-merge mechanisms.

Related Experiment Videos

Main Methods:

  • The ESE procedure is based on the Exploration/Selection (E/S) algorithm, utilizing the HMRF's a posteriori distribution as the exploration distribution.
  • The method estimates likelihood parameters and the optimal number of region classes under global constraints.
  • A specific application involves estimating an HMRF color model for images with multivariate Beta distributions, including a method for maximum likelihood estimation of Beta distributions.

Main Results:

  • The ESE procedure successfully computes Bayesian estimators for HMRF models, including parameter estimation and image segmentation.
  • Experimental results on 100 natural images demonstrate the effectiveness of the proposed method.
  • A proof of convergence for the underlying E/S algorithm is provided for nonsymmetric exploration graphs.

Conclusions:

  • The ESE procedure offers a robust and flexible approach for Bayesian estimation and image segmentation using HMRF models.
  • The dynamic class management framework provides an alternative to conventional region merging techniques.
  • The method is effective for HMRF color models with Beta distribution likelihoods, showing promise for complex image analysis tasks.