A biologically inspired spiking model of visual processing for image feature detection

Kerr, D, McGinnity, TM ORCID: https://orcid.org/0000-0002-9897-4748, Coleman, S and Clogenson, M, 2015. A biologically inspired spiking model of visual processing for image feature detection. Neurocomputing, 158, pp. 268-280. ISSN 0925-2312

Preview

Text 2409_McGinnity.pdf - Pre-print Download (1MB) | Preview

Abstract

To enable fast reliable feature matching or tracking in scenes, features need to be discrete and meaningful, and hence edge or corner features, commonly called interest points are often used for this purpose. Experimental research has illustrated that biological vision systems use neuronal circuits to extract particular features such as edges or corners from visual scenes. Inspired by this biological behaviour, this paper proposes a biologically inspired spiking neural network for the purpose of image feature extraction. Standard digital images are processed and converted to spikes in a manner similar to the processing that transforms light into spikes in the retina. Using a hierarchical spiking network, various types of biologically inspired receptive fields are used to extract progressively complex image features. The performance of the network is assessed by examining the repeatability of extracted features with visual results presented using both synthetic and real images.

Item Type:	Journal article
Publication Title:	Neurocomputing
Creators:	Kerr, D., McGinnity, T.M., Coleman, S. and Clogenson, M.
Publisher:	Elsevier
Place of Publication:	Amsterdam, Netherlands
Date:	2015
Volume:	158
ISSN:	0925-2312
Identifiers:	Number Type 10.1016/j.neucom.2015.01.011 DOI
Divisions:	Schools > School of Science and Technology
Record created by:	EPrints Services
Date Added:	09 Oct 2015 10:35
Last Modified:	09 Jun 2017 13:34
URI:	https://irep.ntu.ac.uk/id/eprint/15302

Actions (login required)

Edit View

Statistics

Views

Downloads