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 dynamically coupled neural oscillator network for image segmentation.

Ke Chen1, DeLiang Wang

  • 1School of Computer Science, The University of Birmingham, Edgbaston, UK. k.chen@cs.bham.ac.uk

Neural Networks : the Official Journal of the International Neural Network Society
|July 20, 2002
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 speech prediction model based on codec modeling and transformer decoding.

Computer speech & language·2026
Same author

A Molecular Trimming Strategy for Hypoxia-Tolerant Photosensitizers With Enhanced cGAS-STING Activation.

Angewandte Chemie (International ed. in English)·2026
Same author

Towards decoupling frontend enhancement and backend recognition in monaural robust ASR.

Computer speech & language·2026
Same author

Efficacy of SWIM technology combined with direct aspiration first pass technique for large vessel occlusion in acute ischemic stroke.

American journal of translational research·2026
Same author

Manipulating RTP properties of the same organic molecule by polymorphic engineering.

Chemical communications (Cambridge, England)·2025
Same author

Confined Growth of 2D Covalent Organic Framework Nanosheets with Controlled Thickness for Osmotic Energy Conversion.

Small (Weinheim an der Bergstrasse, Germany)·2025
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

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

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

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

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

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

Aggregating global-scale pixel-wise forgery cues within a graph.

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

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

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

This study introduces a novel neural oscillator network for robust image segmentation. The method uses dynamical coupling for effective grouping, outperforming traditional algorithms without iterative noise removal.

Area of Science:

  • Computer Vision
  • Computational Neuroscience
  • Artificial Intelligence

Background:

  • Traditional image segmentation methods often struggle with noise and require iterative processing.
  • Existing neural network approaches may lack robustness or efficiency in handling complex image data.

Purpose of the Study:

  • To develop a dynamically coupled neural oscillator network for enhanced image segmentation.
  • To improve robustness to noise and eliminate the need for iterative noise removal operations.

Main Methods:

  • Proposed a neural oscillator network with ensemble coupling in local regions, moving beyond pair-wise connections.
  • Introduced neighborhood-based dynamical coupling structures for oscillators.
  • Developed two grouping rules considering homogeneous regions and region boundaries based on proximity and similarity.

Related Experiment Videos

Main Results:

  • The dynamically coupled network demonstrated robustness to image noise.
  • A fast segmentation algorithm abstracted from oscillatory dynamics was successfully applied.
  • Effective segmentation was achieved on both synthetic and real-world images.

Conclusions:

  • The proposed neural oscillator network offers an effective and robust solution for image segmentation.
  • The dynamical coupling approach provides advantages over traditional iterative methods.
  • The method shows promise for various image analysis applications.