Computing with biologically inspired neural oscillators: Application to colour image segmentation

Arfan Ghani, Ammar Belatreche, Liam Maguire, Martin McGinnity, Liam McDaid

Research output: Contribution to journalArticle

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.
Original languageEnglish
Number of pages21
JournalAdvances in Artificial Intelligence
DOIs
Publication statusPublished - 2010

Fingerprint

Image segmentation
Color
Self organizing maps
Pixels
Image understanding
Object recognition
Neurons
Synchronization
Demonstrations

Cite this

Computing with biologically inspired neural oscillators : Application to colour image segmentation. / Ghani, Arfan; Belatreche, Ammar; Maguire, Liam; McGinnity, Martin; McDaid, Liam.

In: Advances in Artificial Intelligence, 2010.

Research output: Contribution to journalArticle

Ghani, Arfan ; Belatreche, Ammar ; Maguire, Liam ; McGinnity, Martin ; McDaid, Liam. / Computing with biologically inspired neural oscillators : Application to colour image segmentation. In: Advances in Artificial Intelligence. 2010.
@article{aa5fd2f6d679482a9da4bc2ade92471a,
title = "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.",
author = "Arfan Ghani and Ammar Belatreche and Liam Maguire and Martin McGinnity and Liam McDaid",
year = "2010",
doi = "10.1155/2010/405073",
language = "English",
journal = "Advances in Artificial Intelligence",
issn = "1687-7470",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Computing with biologically inspired neural oscillators

T2 - Application to colour image segmentation

AU - Ghani, Arfan

AU - Belatreche, Ammar

AU - Maguire, Liam

AU - McGinnity, Martin

AU - McDaid, Liam

PY - 2010

Y1 - 2010

N2 - 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.

AB - 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.

U2 - 10.1155/2010/405073

DO - 10.1155/2010/405073

M3 - Article

JO - Advances in Artificial Intelligence

JF - Advances in Artificial Intelligence

SN - 1687-7470

ER -