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 novel implementation of watershed transform using multi-degree immersion simulation.

Shengcai Peng1, Lixu Gu

  • 1Department of Computer Science, Shanghai Jiaotong University, Shanghai, China.

Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
|February 7, 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

MedSegAgent: A Universal and Scalable Multi-Agent System for Instructive Medical Image Segmentation.

IEEE journal of biomedical and health informatics·2026
Same author

The application of CT-free electromagnetic navigation-guided percutaneous puncture localization of pulmonary nodules.

Surgical endoscopy·2025
Same author

Real-Time 3D Ultrasound Reconstruction Using U2-Net Segmentation for Cardiovascular Interventional Surgery<sup></sup>.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

E-CMCA and LSTM-Enhanced Framework for Cross-Modal MRI-TRUS Registration in Prostate Cancer.

Journal of imaging·2025
Same author

Revisiting model scaling with a U-net benchmark for 3D medical image segmentation.

Scientific reports·2025
Same author

FIND: A Framework for Iterative to Non-Iterative Distillation for Lightweight Deformable Registration.

IEEE journal of biomedical and health informatics·2025

This study introduces a novel multi-degree immersion watershed transform to prevent image over-segmentation. The enhanced method offers more accurate results with lower computational costs compared to traditional approaches.

Area of Science:

  • Image processing
  • Computer vision
  • Algorithm development

Background:

  • The watershed transform is a powerful image segmentation technique.
  • Traditional watershed methods can suffer from over-segmentation.
  • Existing improvements include topographical distance-based implementations.

Purpose of the Study:

  • To present a novel implementation of the watershed transform.
  • To address the over-segmentation problem in image segmentation.
  • To improve the accuracy and efficiency of watershed-based methods.

Main Methods:

  • A multi-degree immersion simulation is proposed, enhancing the traditional watershed algorithm.
  • The simulation involves varying flood steps based on intensity degrees.

Related Experiment Videos

  • Performance is compared against a topographical distance-based implementation.

    • Main Results:

    • The multi-degree immersion watershed transform effectively resists over-segmentation.
    • The proposed method achieves more accurate segmentation results.
    • It demonstrates lower computing time and memory costs.

    Conclusions:

    • The novel multi-degree immersion watershed transform provides superior performance.
    • This implementation offers a more accurate and cost-effective solution for image segmentation.
    • It represents a significant improvement over traditional watershed algorithms.