Spiking Hierarchical Neural Network for Corner Detection

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

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

5 Citations (Scopus)

Abstract

To enable fast reliable feature matching or tracking in scenes, features need to be discrete and meaningful, and hence corner detection is often used for this purpose. We present a new approach to corner detection inspired by the structure and behaviour of the human visual system, which uses spiking neural networks. Standard digital images are processed and converted to spikes in a manner similar to the processing that is performed in the retina. The spiking neural network performs edge and corner detection using receptive fields that are able to detect edges and corners of various orientations. The locations where neurons emit a spike indicate the positions of detected features. Results are presented using synthetic and real images.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages230-235
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

Neural networks
Neurons
Processing

Keywords

  • Spiking neural network
  • Corner detection

Cite this

Kerr, D ; McGinnity, TM ; Coleman, SA ; Wu, Qingxiang ; Clogenson, M. / Spiking Hierarchical Neural Network for Corner Detection. Unknown Host Publication. 2011. pp. 230-235
@inproceedings{63e02fdd9dff4c8abefff668eba3293d,
title = "Spiking Hierarchical Neural Network for Corner Detection",
abstract = "To enable fast reliable feature matching or tracking in scenes, features need to be discrete and meaningful, and hence corner detection is often used for this purpose. We present a new approach to corner detection inspired by the structure and behaviour of the human visual system, which uses spiking neural networks. Standard digital images are processed and converted to spikes in a manner similar to the processing that is performed in the retina. The spiking neural network performs edge and corner detection using receptive fields that are able to detect edges and corners of various orientations. The locations where neurons emit a spike indicate the positions of detected features. Results are presented using synthetic and real images.",
keywords = "Spiking neural network, Corner detection",
author = "D Kerr and TM McGinnity and SA Coleman and Qingxiang Wu and M Clogenson",
year = "2011",
doi = "10.5220/0003682402300235",
language = "English",
pages = "230--235",
booktitle = "Unknown Host Publication",

}

Kerr, D, McGinnity, TM, Coleman, SA, Wu, Q & Clogenson, M 2011, Spiking Hierarchical Neural Network for Corner Detection. in Unknown Host Publication. pp. 230-235, International Conference on Neural Computation Theory and Applications, 1/01/11. https://doi.org/10.5220/0003682402300235

Spiking Hierarchical Neural Network for Corner Detection. / Kerr, D; McGinnity, TM; Coleman, SA; Wu, Qingxiang; Clogenson, M.

Unknown Host Publication. 2011. p. 230-235.

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

TY - GEN

T1 - Spiking Hierarchical Neural Network for Corner Detection

AU - Kerr, D

AU - McGinnity, TM

AU - Coleman, SA

AU - Wu, Qingxiang

AU - Clogenson, M

PY - 2011

Y1 - 2011

N2 - To enable fast reliable feature matching or tracking in scenes, features need to be discrete and meaningful, and hence corner detection is often used for this purpose. We present a new approach to corner detection inspired by the structure and behaviour of the human visual system, which uses spiking neural networks. Standard digital images are processed and converted to spikes in a manner similar to the processing that is performed in the retina. The spiking neural network performs edge and corner detection using receptive fields that are able to detect edges and corners of various orientations. The locations where neurons emit a spike indicate the positions of detected features. Results are presented using synthetic and real images.

AB - To enable fast reliable feature matching or tracking in scenes, features need to be discrete and meaningful, and hence corner detection is often used for this purpose. We present a new approach to corner detection inspired by the structure and behaviour of the human visual system, which uses spiking neural networks. Standard digital images are processed and converted to spikes in a manner similar to the processing that is performed in the retina. The spiking neural network performs edge and corner detection using receptive fields that are able to detect edges and corners of various orientations. The locations where neurons emit a spike indicate the positions of detected features. Results are presented using synthetic and real images.

KW - Spiking neural network

KW - Corner detection

U2 - 10.5220/0003682402300235

DO - 10.5220/0003682402300235

M3 - Conference contribution

SP - 230

EP - 235

BT - Unknown Host Publication

ER -