Gray-Level Object Segmentation with a Network of FitzHugh-Nagumo Oscillators

Abstract. In this paper we adopt a temporal coding approach to neuronal modeling of the visual cortex, using oscillations. We propose a hierarchy of three processing modules corresponding to dierent levels of representation. The rst layer encodes the input image (stimulus) into an array of units, while the second layer consists of a network of FitzHugh-Nagumo oscillators. The dynamical behaviour of the coupled oscillators is rigorously investigated and a stimulus-driven synchronization theorem is derived. However, this module reveals itself insucient to correctly encode and segregate dierent objects when they have similar gray{levels in the input image. Therefore, a third layer connected in a feedback loop with the oscillators is added. This ensures synchronization (resp. desynchronization) of neuron ensembles representing the same (resp. a dierent) object. Simulation results are presented using synthetic as well as real and noisy gray{level images.

• Type: Conference
• Year: 1997
• Where: IWANN
• Authors: Abderrahim Labbi, Ruggero Milanese, Holger Bosch
• Keywords: Di Erent Objects, Input Image, IWANN 1997, Neural Networks, Temporal Coding Approach