Computing with Biologically Inspired Neural Oscillators: Application to Colour Image Segmentation

This paper investigates the computing capabilities and potential applications of neural oscillators, a biologically inspired neuralmodel, to grey scale and colour image segmentation, an importanttask in image understanding and object recognition. A proposedneural system that exploits the synergy between neural oscillators and Kohonen self-organising maps (SOMs) is presented. Itconsists of a two-dimensional grid of neural oscillators which are locally connected through excitatory connections and globallyconnected to a common inhibitor. Each neuron is mapped to a pixel of the input image and existing objects, represented byhomogenous areas, are temporally segmented through synchronis ation of the activity of neural oscillators that are mapped topixels of the same object. Self-organising maps form the basis of a colour reduction system whose output is fed to a 2D grid ofneural oscillators for temporal correlation-based object segmentation. Both chromatic and local spatial features are used. Thesystem is simulated in Matlab and its demonstration on real world colour images shows promising results and the emergence ofa new bioinspired approach for colour image segmentation. The paper concludes with a discussion of the performance of theproposed system and its comparison with traditional image segmentation approaches.