Response of an Excitatory-Inhibitory Neural Network to External Stimulation: An Application to Image Segmentation

TL;DR

This paper investigates how simple excitatory-inhibitory neural pairs respond to external stimuli and demonstrates their application in image segmentation by coupling these pairs in a network.

Contribution

It introduces a neural network model based on excitatory-inhibitory pairs for image segmentation and analyzes its dynamic response to external stimulation.

Findings

Network dynamics vary with stimulus magnitude

Coupled pairs effectively segment images into object and background

Successful application to both synthetic and real images

Abstract

Neural network models comprising elements which have exclusively excitatory or inhibitory synapses are capable of a wide range of dynamic behavior, including chaos. In this paper, a simple excitatory-inhibitory neural pair, which forms the building block of larger networks, is subjected to external stimulation. The response shows transition between various types of dynamics, depending upon the magnitude of the stimulus. Coupling such pairs over a local neighborhood in a two-dimensional plane, the resultant network can achieve a satisfactory segmentation of an image into ``object'' and ``background''. Results for synthetic and and ``real-life'' images are given.