DYNAMICAL PROPERTY OF PERIODIC OSCILLATIONS OBSERVED IN A COUPLED NEURAL OSCILLATOR NETWORK FOR IMAGE SEGMENTATION

Tetsuya Yoshinaga, Ken’ichi Fujimoto

2008

Abstract

We consider image segmentation using the LEGION (Locally-Excitatory Globally-Inhibitory Oscillator Net-work), and investigate dynamical properties of a modified LEGION, described by noise-free or deterministic continuous ordinary differential equations. We clarify a phenomenon of image segmentation corresponds to the appearance of a synchronized periodic solution, and the ability of segmentation depends on its symmetric properties. We study bifurcations of periodic solutions by using a computational method based on the qualitative dynamical system theory.

Paper Citation

in Harvard Style

Yoshinaga T. and Fujimoto K. (2008). DYNAMICAL PROPERTY OF PERIODIC OSCILLATIONS OBSERVED IN A COUPLED NEURAL OSCILLATOR NETWORK FOR IMAGE SEGMENTATION . In Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008) ISBN 978-989-8111-18-0, pages 141-146. DOI: 10.5220/0001062101410146

in Bibtex Style

@conference{biosignals08,
author={Tetsuya Yoshinaga and Ken’ichi Fujimoto},
title={DYNAMICAL PROPERTY OF PERIODIC OSCILLATIONS OBSERVED IN A COUPLED NEURAL OSCILLATOR NETWORK FOR IMAGE SEGMENTATION},
booktitle={Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)},
year={2008},
pages={141-146},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001062101410146},
isbn={978-989-8111-18-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)
TI - DYNAMICAL PROPERTY OF PERIODIC OSCILLATIONS OBSERVED IN A COUPLED NEURAL OSCILLATOR NETWORK FOR IMAGE SEGMENTATION
SN - 978-989-8111-18-0
AU - Yoshinaga T.
AU - Fujimoto K.
PY - 2008
SP - 141
EP - 146
DO - 10.5220/0001062101410146