SPIKING HIERARCHICAL NEURAL NETWORK FOR CORNER DETECTION

Dermot Kerr, Martin McGinnity, Sonya Coleman, Qingxiang Wu, Marine Clogenson

2011

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.

Paper Citation

in Harvard Style

Kerr D., McGinnity M., Coleman S., Wu Q. and Clogenson M. (2011). SPIKING HIERARCHICAL NEURAL NETWORK FOR CORNER DETECTION . In Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011) ISBN 978-989-8425-84-3, pages 230-235. DOI: 10.5220/0003682402300235

in Bibtex Style

@conference{ncta11,
author={Dermot Kerr and Martin McGinnity and Sonya Coleman and Qingxiang Wu and Marine Clogenson},
title={SPIKING HIERARCHICAL NEURAL NETWORK FOR CORNER DETECTION},
booktitle={Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011)},
year={2011},
pages={230-235},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003682402300235},
isbn={978-989-8425-84-3},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011)
TI - SPIKING HIERARCHICAL NEURAL NETWORK FOR CORNER DETECTION
SN - 978-989-8425-84-3
AU - Kerr D.
AU - McGinnity M.
AU - Coleman S.
AU - Wu Q.
AU - Clogenson M.
PY - 2011
SP - 230
EP - 235
DO - 10.5220/0003682402300235