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

The patchwork engine: image segmentation from shape symmetries.

G J van Tonder1, Y Ejima

  • 1Laboratory of Cognitive Science, Graduate School for Human and Environmental Studies, Kyoto University, Kyoto City, Kyoto Prefecture, Japan. gert@cv.jinkan.kyoto-u.ac.jp

Neural Networks : the Official Journal of the International Neural Network Society
|August 11, 2000
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

Bicarbonate in Arteries Measured Preoperatively for Cadaveric Single-lung Transplantation is Related to Intraoperative Extra-Corporeal Membrane Oxygenation Use: A Retrospective Preliminary Study.

International journal of organ transplantation medicine·2022
Same author

Heterotopic pregnancy diagnosed before the onset of severe symptoms: case report.

Clinical and experimental obstetrics & gynecology·2013
Same author

Comparison of actual tidal volume in neonatal lung model volume control ventilation using three ventilators.

Anaesthesia and intensive care·2011
Same author

Cesarean section and primary pulmonary hypertension: the role of intravenous dexmedetomidine.

International journal of obstetric anesthesia·2009
Same author

Experimental derivation of relative biological effectiveness of A-bomb neutrons in Hiroshima and Nagasaki and implications for risk assessment.

Radiation research·2008
Same author

Flexible computation of shape symmetries within the maximal disk paradigm.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a novel blind image segmentation method using local symmetries to divide images into shape-relevant patches. This approach enhances contour detection and figure-ground segmentation in early vision.

Area of Science:

  • Computer Vision
  • Image Processing
  • Computational Neuroscience

Background:

  • Traditional watershed segmentation methods struggle with contour detection and gap closure in images.
  • Existing contour interpolation methods do not fully address the complexities of early visual processing for shape perception.

Purpose of the Study:

  • To develop a novel blind image segmentation technique for identifying shape-relevant patches.
  • To leverage local symmetries in shape boundary contours for improved image segmentation.
  • To enhance figure-ground segregation and the formation of complex shape hypotheses in early vision.

Main Methods:

  • Assigning lateral weights between boundary contour points, analogous to Euclidean distance maps.
  • Extracting local maxima in symmetries, linking these maxima within enclosed contours, and reconstructing contours using symmetry maxima as seeds.

Related Experiment Videos

  • Proposing primitive operations of patch comparison and merging to reveal global shape contours.

    • Main Results:

    • The proposed method successfully segments images into shape-relevant patches, outperforming existing contour interpolation and related segmentation methods.
    • The model effectively closes gaps in solid image contours, a known weakness of watershed segmentation.
    • Symmetry-based segmentation contributes to figure-ground segregation and provides primitive operations for complex shape hypothesis generation.

    Conclusions:

    • Local symmetries are crucial for blind image segmentation and can be effectively computed from shape boundary contours.
    • The proposed method offers a robust alternative to watershed segmentation, particularly for handling incomplete contours.
    • Symmetry plays a fundamental role in early vision, aiding in shape perception and the construction of complex visual representations.