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

Image segmentation based on oscillatory correlation

D Wang1, D Terman

  • 1Department of Computer and Information Science, Ohio State University, Columbus 43210, USA.

Neural Computation
|May 15, 1997
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

Calcium regulation of HCN channels supports persistent activity in a multiscale model of neocortex.

Neuroscience·2016
Same author

Irregular activity arises as a natural consequence of synaptic inhibition.

Chaos (Woodbury, N.Y.)·2014
Same author

Local circuit input to the medullary reticular formation from the rostral nucleus of the solitary tract.

American journal of physiology. Regulatory, integrative and comparative physiology·2008
Same author

Activity patterns in a model for the subthalamopallidal network of the basal ganglia.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2002
Same author

Localized bumps of activity sustained by inhibition in a two-layer thalamic network.

Journal of computational neuroscience·2001
Same author

Analysis of clustered firing patterns in synaptically coupled networks of oscillators.

Journal of mathematical biology·2001
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

Locally Excitatory, Globally Inhibitory Oscillator Networks (LEGION) effectively segment images by using oscillator phases to bind pixels. This novel framework suppresses noise, enhancing image segmentation and figure-ground segregation.

Area of Science:

  • Computational Neuroscience
  • Computer Vision
  • Image Processing

Background:

  • Image segmentation is crucial for understanding visual information.
  • Existing methods may struggle with noisy regions and complex image structures.
  • Oscillator network models offer a biologically inspired approach to visual processing.

Purpose of the Study:

  • To introduce a novel image segmentation framework using LEGION.
  • To develop a method for noise suppression within the LEGION model.
  • To evaluate the effectiveness of LEGION for image segmentation and figure-ground segregation.

Main Methods:

  • Utilizing the phase dynamics of coupled oscillators to represent pixel relationships.
  • Introducing a lateral potential mechanism to modulate oscillator activity based on neighborhood connections.

Related Experiment Videos

  • Developing an algorithm based on lateral potential to suppress noisy regions.
  • Computer simulations to analyze network properties and performance.

    • Main Results:

    • The LEGION network successfully segments images into distinct regions and a noise-based background.
    • The proposed lateral potential effectively suppresses oscillators in noisy areas without impacting major image regions.
    • Computer simulations demonstrate the network's capacity for natural image segmentation.
    • The developed algorithm shows successful application to real gray-level images.

    Conclusions:

    • LEGION provides a novel and effective framework for image segmentation.
    • The model demonstrates robust performance in separating images and segregating figures from the ground.
    • The approach offers insights into biologically plausible mechanisms for visual perception and image processing.