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

Comparison between immersion-based and toboggan-based watershed image segmentation.

Yung-Chieh Lin1, Yu-Pao Tsai, Yi-Ping Hung

  • 1Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan, ROC. cole@iadea.com

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|March 8, 2006
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

A Multinational, Retrospective, Real-World Study: Treatment Patterns in Patients With HER2-Positive Locally Advanced or Metastatic Gastric or Gastroesophageal Junction Adenocarcinoma Beyond First-line in East Asia (HER2+ GASTA Study).

Cancer research and treatment·2026
Same author

Integrating liquid chromatography-high resolution mass spectrometry based suspect screening with ionization efficiency prediction to expand semi-quantitative coverage in wastewater-based epidemiology: application to environmental chemicals.

Environment international·2026
Same author

Efficacy of neoadjuvant chemoradiotherapy with 5-fluorouracil/cisplatin versus paclitaxel/cisplatin in esophageal squamous cell carcinoma: A single-institute real-world study.

Journal of the Formosan Medical Association = Taiwan yi zhi·2026
Same author

Proinflammatory state and metabolic dysregulation linking delayed feeding progression to extrauterine restricted head growth in extremely preterm infants.

BMC medicine·2025
Same author

Adjuvant chemoradiotherapy for stage III gastric cancer: A differential role in R0 and non-R0 resection.

Journal of the Chinese Medical Association : JCMA·2025
Same author

Functional connectivity as a prognostic biomarker for neurodevelopmental outcomes in preterm infants without severe brain injury.

Brain communications·2025

Two new order-invariant watershed segmentation algorithms achieve identical results using both immersion and toboggan simulation approaches. The toboggan method proves more efficient, especially for large images in computer vision applications.

Area of Science:

  • Computer Vision
  • Image Processing
  • Computational Geometry

Background:

  • Watershed segmentation is a popular image segmentation technique.
  • Two main approaches exist: immersion and toboggan simulation, with differing conceptual directions.
  • Previous research had not definitively established if these approaches yield identical results or which is more efficient.

Purpose of the Study:

  • To develop and compare order-invariant watershed segmentation algorithms based on both immersion and toboggan approaches.
  • To determine if these conceptually opposite methods can produce the same segmentation outcome.
  • To evaluate the efficiency of the developed algorithms, particularly for varying image sizes.

Main Methods:

  • Introduced two novel order-invariant algorithms for watershed segmentation.

Related Experiment Videos

  • One algorithm utilizes the immersion approach (low to high altitude).
  • The other algorithm employs the toboggan approach (high to low altitude), incorporating a special RIDGE label for order-invariance.

    • Main Results:

    • Both developed algorithms successfully achieve identical segmentation results, confirming order-invariance.
    • Both algorithms demonstrate high efficiency, processing images rapidly (e.g., <1/30s for 256x256, <1/5s for 512x512).
    • The toboggan-based algorithm consistently outperformed the immersion-based algorithm in speed, especially for larger images (512x512 and above).

    Conclusions:

    • Order-invariant watershed segmentation is achievable using both immersion and toboggan simulation methods.
    • The toboggan simulation approach offers superior computational efficiency compared to the immersion approach for watershed segmentation, particularly in large-scale image processing.
    • This study provides insights into the efficiency advantages of the toboggan algorithm in computer vision.