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

Abstract

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

Electrical Switching in Thin Film Structures Based on Transition Metal Oxides

“…Note that, in the work [100], a MITbased switching devise has been proposed to be used as a quasistatic neuristor synapse model. On the other hand, dynamic oscillation-based models are also widely explored in the field of neuromorphic simulation [146][147][148][149]. Particularly, in the works [148,149], the authors present the realization of coupled and scalable relaxation oscillators utilizing the MIT in metal-insulator-metal transition in VO 2 and demonstrate the potential use of such a system in pattern recognition as one possible computational model based on a non-Boolean neuromorphic computing paradigm.…”