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

Anti-geometric diffusion for adaptive thresholding and fast segmentation.

Siddharth Manay1, Anthony Yezzi

  • 1Sch. of Electr. and Comput. Eng., Georgia Inst. of Technol., Atlanta, GA 30332, USA. smanay.ece98@gtalumni.org

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 5, 2008
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

Applications of Artificial Intelligence, Deep Learning, and Machine Learning to Support the Analysis of Microscopic Images of Cells and Tissues.

Journal of imaging·2025
Same author

Artificial Intelligence for Classifying the Relationship between Impacted Third Molar and Mandibular Canal on Panoramic Radiographs.

Life (Basel, Switzerland)·2023
Same author

An Overview of In Vitro Assays of <sup>64</sup>Cu-, <sup>68</sup>Ga-, <sup>125</sup>I-, and <sup>99m</sup>Tc-Labelled Radiopharmaceuticals Using Radiometric Counters in the Era of Radiotheranostics.

Diagnostics (Basel, Switzerland)·2023
Same author

Anti-Arthritic and Anti-Cancer Activities of Polyphenols: A Review of the Most Recent In Vitro Assays.

Life (Basel, Switzerland)·2023
Same author

Radar-Based Shape and Reflectivity Reconstruction Using Active Surfaces and the Level Set Method.

IEEE transactions on pattern analysis and machine intelligence·2022
Same author

Clinically viable myocardial CCTA segmentation for measuring vessel-specific myocardial blood flow from dynamic PET/CCTA hybrid fusion.

European journal of hybrid imaging·2022
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
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
See all related articles

This study introduces an anti-geometric heat flow model for adaptive image thresholding and segmentation. This novel anisotropic diffusion approach effectively segments greyscale images by smearing edges, simplifying region detection.

Area of Science:

  • Computer Vision
  • Image Processing
  • Computational Imaging

Background:

  • Anisotropic diffusion is a common image processing technique.
  • Existing methods often struggle with determining when diffusion should stop.
  • Edge preservation is a typical goal, but can hinder region discrimination.

Purpose of the Study:

  • To introduce a novel anisotropic diffusion model, the anti-geometric heat flow.
  • To apply this model for adaptive thresholding of bimodal images.
  • To develop a general framework for greyscale image segmentation.

Main Methods:

  • Utilizing an anisotropic diffusion model that smears edges instead of preserving them.
  • Implementing a region splitting procedure based on the diffusion process.

Related Experiment Videos

  • Combining region splitting with energy-based region merging for segmentation.

    • Main Results:

    • The anti-geometric heat flow model rapidly detects and discriminates image regions separated by edges.
    • Edge detection occurs during diffusion, avoiding the 'when to stop' problem.
    • The framework demonstrates effectiveness in segmenting diverse imagery.

    Conclusions:

    • The anti-geometric heat flow offers an effective approach for adaptive thresholding and image segmentation.
    • This method provides a robust solution to the stopping criteria problem in diffusion-based techniques.
    • The proposed segmentation framework is versatile and applicable to various image types.