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 segmentation model using compound Markov random fields based on a boundary model.

Jue Wu1, Albert C S Chung

  • 1Lo Kwee-Seong Medical Image Analysis Laboratory, Department of Computer Science and Engineering, and Bioengineering Program, School of Engineering, The Hong Kong University of Science and Technology. johnwoo@ust.hk

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 8, 2007
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

Relationship Between Sleep-Related Worry, Compassion Fatigue, and Retention Intention Among Nurses: A Multicenter Cross-Sectional Study.

Journal of nursing management·2026
Same author

Fueling Ambition: Graduate Degree Aspirations Among Women of Color in STEM.

CBE life sciences education·2026
Same author

Career Pathways and Skill Preparedness among Biology PhDs: A Social Cognitive Career Theory Perspective.

CBE life sciences education·2026
Same author

Self-purifying chloride-mediated sequential nitrate reduction-oxidation enabled by a Co-oxygen vacancy tandem photoelectrocatalyst.

Dalton transactions (Cambridge, England : 2003)·2026
Same author

Relationship between compassion fatigue, medical narrative ability, and retention intention among nurses: a cross-sectional multi-center study.

Frontiers in health services·2026
Same author

The influence of ceramic tile characteristics on visual comfort and cognitive performance in workplace environments: a study based on VR and EEG.

Frontiers in psychology·2026
Same journal

Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

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

Semantic Frame Interpolation.

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

Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

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

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

This study introduces a novel compound Markov random field (MRF) model for image segmentation. The new model improves accuracy and boundary preservation, especially in noisy medical images.

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Markov random field (MRF) theory is a standard approach for image segmentation.
  • Existing MRF models face challenges with complex boundaries and noise sensitivity.

Purpose of the Study:

  • To propose a new non-texture segmentation model using compound MRFs.
  • To improve segmentation performance by coupling a label MRF with a novel boundary MRF.
  • To enhance boundary preservation and noise robustness in image segmentation.

Main Methods:

  • Developed a compound MRF model integrating a label MRF and a general boundary MRF.
  • The boundary MRF incorporates prior information on edge configurations within a 3x3 neighborhood.
  • The model features a compact interaction between label and boundary MRFs without prior boundary pattern training.

Related Experiment Videos

Main Results:

  • The proposed model successfully segments objects with complex boundaries.
  • Demonstrated effectiveness in segmenting images corrupted by noise.
  • Achieved more accurate segmentation and preserved delicate boundaries on synthetic and real clinical datasets.

Conclusions:

  • The compound MRF model offers superior image segmentation performance compared to existing methods.
  • The model exhibits enhanced robustness to noise across varying signal-to-noise ratios.
  • This approach is particularly promising for medical image segmentation applications.