The University of Southampton
University of Southampton Institutional Repository

Evolving content-driven superpixels for accurate image representation

Evolving content-driven superpixels for accurate image representation
Evolving content-driven superpixels for accurate image representation
A novel approach to superpixel generation is presented that aims to reconcile image information with superpixel coverage. It is described as content-driven as the number of superpixels in any given area is dictated by the underlying image properties. By using a combination of well-established computer vision techniques, superpixels are grown and subsequently divided on detecting simple image variation. It is designed to have no direct control over the number of superpixels as this can lead to errors. The algorithm is subject to performance metrics on the Berkeley Segmentation Dataset including: explained variation; mode label analysis, as well as a measure of oversegmentation. The results show that this new algorithm can reduce the superpixel oversegmentation and retain comparable performance in all other metrics. The algorithm is shown to be stable with respect to initialisation, with little variation across performance metrics on a set of random initialisations.
978-3-642-24027-0
192-201
Lowe, Richard
d597842e-560d-44a0-bade-dee08ce57677
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Lowe, Richard
d597842e-560d-44a0-bade-dee08ce57677
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12

Lowe, Richard and Nixon, Mark S. (2011) Evolving content-driven superpixels for accurate image representation. ISVC'11 Proceedings of the 7th International Conference on Advances in Visual Computing - Volume Part I. pp. 192-201 . (doi:10.1007/978-3-642-24028-7_18).

Record type: Conference or Workshop Item (Paper)

Abstract

A novel approach to superpixel generation is presented that aims to reconcile image information with superpixel coverage. It is described as content-driven as the number of superpixels in any given area is dictated by the underlying image properties. By using a combination of well-established computer vision techniques, superpixels are grown and subsequently divided on detecting simple image variation. It is designed to have no direct control over the number of superpixels as this can lead to errors. The algorithm is subject to performance metrics on the Berkeley Segmentation Dataset including: explained variation; mode label analysis, as well as a measure of oversegmentation. The results show that this new algorithm can reduce the superpixel oversegmentation and retain comparable performance in all other metrics. The algorithm is shown to be stable with respect to initialisation, with little variation across performance metrics on a set of random initialisations.

Text
lowe isvc 2011 pdf.pdf - Version of Record
Restricted to Repository staff only
Request a copy

More information

Published date: 2011
Venue - Dates: ISVC'11 Proceedings of the 7th International Conference on Advances in Visual Computing - Volume Part I, 2011-01-01
Organisations: Vision, Learning and Control

Identifiers

Local EPrints ID: 363318
URI: http://eprints.soton.ac.uk/id/eprint/363318
ISBN: 978-3-642-24027-0
PURE UUID: 1f205681-d572-4ccc-a667-8ad73566d2e9
ORCID for Mark S. Nixon: ORCID iD orcid.org/0000-0002-9174-5934

Catalogue record

Date deposited: 20 Mar 2014 17:02
Last modified: 07 Oct 2020 02:39

Export record

Altmetrics

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×