Biologically Inspired Edge Detection

Dermot Kerr, SA Coleman, TM McGinnity, Qingxiang Wu, Marine Clogenson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Inspired by the structure and behaviour of the human visual system, we present an approach to edge detection using spiking neural networks and a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation and then processed using a spiking neural network with hexagonal shaped receptive fields. The performance is compared with receptive fields implemented on standard rectangular images. Results illustrate that, using hexagonal shaped receptive fields, performance is improved over standard rectangular shaped receptive fields.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages802-807
Number of pages1000
DOIs
Publication statusPublished - 3 Jan 2012
Event11th International Conference on Intelligent Systems Design and Applications (ISDA) - Cordoba, Spain
Duration: 3 Jan 2012 → …

Conference

Conference11th International Conference on Intelligent Systems Design and Applications (ISDA)
Period3/01/12 → …

Fingerprint

Edge detection
Pixels
Neural networks

Keywords

  • Edge detection
  • Spiking neural network

Cite this

Kerr, D., Coleman, SA., McGinnity, TM., Wu, Q., & Clogenson, M. (2012). Biologically Inspired Edge Detection. In Unknown Host Publication (pp. 802-807) https://doi.org/10.1109/ISDA.2011.6121755
Kerr, Dermot ; Coleman, SA ; McGinnity, TM ; Wu, Qingxiang ; Clogenson, Marine. / Biologically Inspired Edge Detection. Unknown Host Publication. 2012. pp. 802-807
@inproceedings{57316818eb814c7caded7d47cfefdde9,
title = "Biologically Inspired Edge Detection",
abstract = "Inspired by the structure and behaviour of the human visual system, we present an approach to edge detection using spiking neural networks and a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation and then processed using a spiking neural network with hexagonal shaped receptive fields. The performance is compared with receptive fields implemented on standard rectangular images. Results illustrate that, using hexagonal shaped receptive fields, performance is improved over standard rectangular shaped receptive fields.",
keywords = "Edge detection, Spiking neural network",
author = "Dermot Kerr and SA Coleman and TM McGinnity and Qingxiang Wu and Marine Clogenson",
year = "2012",
month = "1",
day = "3",
doi = "10.1109/ISDA.2011.6121755",
language = "English",
isbn = "978-1-4577-1676-8",
pages = "802--807",
booktitle = "Unknown Host Publication",

}

Kerr, D, Coleman, SA, McGinnity, TM, Wu, Q & Clogenson, M 2012, Biologically Inspired Edge Detection. in Unknown Host Publication. pp. 802-807, 11th International Conference on Intelligent Systems Design and Applications (ISDA), 3/01/12. https://doi.org/10.1109/ISDA.2011.6121755

Biologically Inspired Edge Detection. / Kerr, Dermot; Coleman, SA; McGinnity, TM; Wu, Qingxiang; Clogenson, Marine.

Unknown Host Publication. 2012. p. 802-807.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Biologically Inspired Edge Detection

AU - Kerr, Dermot

AU - Coleman, SA

AU - McGinnity, TM

AU - Wu, Qingxiang

AU - Clogenson, Marine

PY - 2012/1/3

Y1 - 2012/1/3

N2 - Inspired by the structure and behaviour of the human visual system, we present an approach to edge detection using spiking neural networks and a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation and then processed using a spiking neural network with hexagonal shaped receptive fields. The performance is compared with receptive fields implemented on standard rectangular images. Results illustrate that, using hexagonal shaped receptive fields, performance is improved over standard rectangular shaped receptive fields.

AB - Inspired by the structure and behaviour of the human visual system, we present an approach to edge detection using spiking neural networks and a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation and then processed using a spiking neural network with hexagonal shaped receptive fields. The performance is compared with receptive fields implemented on standard rectangular images. Results illustrate that, using hexagonal shaped receptive fields, performance is improved over standard rectangular shaped receptive fields.

KW - Edge detection

KW - Spiking neural network

U2 - 10.1109/ISDA.2011.6121755

DO - 10.1109/ISDA.2011.6121755

M3 - Conference contribution

SN - 978-1-4577-1676-8

SP - 802

EP - 807

BT - Unknown Host Publication

ER -