Biologically Inspired Edge Detection using Spiking Neural Networks and Hexagonal Images

M Clogenson, D Kerr, TM McGinnity, SA Coleman, Qingxiang Wu

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

1 Citation (Scopus)

Abstract

Inspired by the structure and behaviour of the human visual system, we extend existing work using spiking neural networks for edge detection with a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation before being processed with a spiking neural network with scalable hexagonally shaped receptive fields. The performance is compared with different sized receptive fields implemented on standard rectangular images. Results illustrate that using hexagonal-shaped receptive fields provides improved performance over a range of scales compared with standard rectangular shaped receptive fields and images.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages381-384
Number of pages1000
DOIs
Publication statusPublished - 2011
EventInternational Conference on Neural Computation Theory and Applications - Paris, France
Duration: 1 Jan 2011 → …

Conference

ConferenceInternational Conference on Neural Computation Theory and Applications
Period1/01/11 → …

Fingerprint

Edge detection
Neural networks
Pixels

Keywords

  • Spiking neural network
  • Edge detection
  • Multi-scale hexagonal receptive fields

Cite this

@inproceedings{e32e4cc38c5644c3949965188d4ee5fc,
title = "Biologically Inspired Edge Detection using Spiking Neural Networks and Hexagonal Images",
abstract = "Inspired by the structure and behaviour of the human visual system, we extend existing work using spiking neural networks for edge detection with a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation before being processed with a spiking neural network with scalable hexagonally shaped receptive fields. The performance is compared with different sized receptive fields implemented on standard rectangular images. Results illustrate that using hexagonal-shaped receptive fields provides improved performance over a range of scales compared with standard rectangular shaped receptive fields and images.",
keywords = "Spiking neural network, Edge detection, Multi-scale hexagonal receptive fields",
author = "M Clogenson and D Kerr and TM McGinnity and SA Coleman and Qingxiang Wu",
year = "2011",
doi = "10.5220/0003682103810384",
language = "English",
pages = "381--384",
booktitle = "Unknown Host Publication",

}

Clogenson, M, Kerr, D, McGinnity, TM, Coleman, SA & Wu, Q 2011, Biologically Inspired Edge Detection using Spiking Neural Networks and Hexagonal Images. in Unknown Host Publication. pp. 381-384, International Conference on Neural Computation Theory and Applications, 1/01/11. https://doi.org/10.5220/0003682103810384

Biologically Inspired Edge Detection using Spiking Neural Networks and Hexagonal Images. / Clogenson, M; Kerr, D; McGinnity, TM; Coleman, SA; Wu, Qingxiang.

Unknown Host Publication. 2011. p. 381-384.

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

TY - GEN

T1 - Biologically Inspired Edge Detection using Spiking Neural Networks and Hexagonal Images

AU - Clogenson, M

AU - Kerr, D

AU - McGinnity, TM

AU - Coleman, SA

AU - Wu, Qingxiang

PY - 2011

Y1 - 2011

N2 - Inspired by the structure and behaviour of the human visual system, we extend existing work using spiking neural networks for edge detection with a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation before being processed with a spiking neural network with scalable hexagonally shaped receptive fields. The performance is compared with different sized receptive fields implemented on standard rectangular images. Results illustrate that using hexagonal-shaped receptive fields provides improved performance over a range of scales compared with standard rectangular shaped receptive fields and images.

AB - Inspired by the structure and behaviour of the human visual system, we extend existing work using spiking neural networks for edge detection with a biologically plausible hexagonal pixel arrangement. Standard digital images are converted into a hexagonal pixel representation before being processed with a spiking neural network with scalable hexagonally shaped receptive fields. The performance is compared with different sized receptive fields implemented on standard rectangular images. Results illustrate that using hexagonal-shaped receptive fields provides improved performance over a range of scales compared with standard rectangular shaped receptive fields and images.

KW - Spiking neural network

KW - Edge detection

KW - Multi-scale hexagonal receptive fields

U2 - 10.5220/0003682103810384

DO - 10.5220/0003682103810384

M3 - Conference contribution

SP - 381

EP - 384

BT - Unknown Host Publication

ER -