An oscillatory network model with controllable synchronization and a neuromorphic dynamical method of information processing
- Authors: Grichuk E.S.1, Kuzmina M.G.2, Manykin E.A.1
-
Affiliations:
- National Research Center Kurchatov Institute
- Keldysh Institute of Applied Mathematics
- Issue: Vol 9, No 4 (2017)
- Pages: 511-520
- Section: Article
- URL: https://journals.rcsi.science/2070-0482/article/view/201855
- DOI: https://doi.org/10.1134/S2070048217040068
- ID: 201855
Cite item
Abstract
A spatially two-dimensional oscillatory neural network model with inhomogeneous modifiable oscillatory coupling is designed and an adaptive dynamical method of brightness image segmentation (image reconstruction) based on self-organized cluster synchronization in the oscillatory network is developed. The method imitates the known phenomenon of dynamical binding via synchronization that is presumably used by a number of the brain neural structures in their work. The oscillatory-network approach demonstrates the following capabilities: (1) high-quality segmentation of real grey-level and color images; (2) selective image segmentation (exclusion of unnecessary information); (3) solution of the simplest problem of object selection in a visual scene—the problem of the successive selection of all spatially separated image fragments of almost equal brightness.
About the authors
E. S. Grichuk
National Research Center Kurchatov Institute
Email: mg.kuzmina@gmail.com
Russian Federation, Moscow
M. G. Kuzmina
Keldysh Institute of Applied Mathematics
Author for correspondence.
Email: mg.kuzmina@gmail.com
Russian Federation, Moscow
E. A. Manykin
National Research Center Kurchatov Institute
Email: mg.kuzmina@gmail.com
Russian Federation, Moscow