A saliency-based hierarchy for local symmetries

Shape representation is fundamental to many areas of computer vision. Local symmetries provide a tool on which to base flexible representations of complex shapes, however, 'multiple participation' symmetries such as SLS generate many more symmetries, than required. This clutters the repres...

Full description

Bibliographic Details
Main Authors: Jenkinson, M, Brady, M
Format: Journal article
Language:English
Published: 2002
_version_ 1826268525739638784
author Jenkinson, M
Brady, M
author_facet Jenkinson, M
Brady, M
author_sort Jenkinson, M
collection OXFORD
description Shape representation is fundamental to many areas of computer vision. Local symmetries provide a tool on which to base flexible representations of complex shapes, however, 'multiple participation' symmetries such as SLS generate many more symmetries, than required. This clutters the representation with mostly irrelevant symmetries, hiding perceptually salient information. In this paper, a salience hierarchy is proposed that allows compact, perceptually pleasing representations to be extracted from the highly redundant full SLS. Both individual and competitive saliency is used to create the hierarchy which partitions the set of symmetries into subsets, each of which is an independent shape representation. © 2002 Elsevier Science B.V. All rights reserved.
first_indexed 2024-03-06T21:11:02Z
format Journal article
id oxford-uuid:3e289348-e251-4578-92a8-a991d019317b
institution University of Oxford
language English
last_indexed 2024-03-06T21:11:02Z
publishDate 2002
record_format dspace
spelling oxford-uuid:3e289348-e251-4578-92a8-a991d019317b2022-03-26T14:23:59ZA saliency-based hierarchy for local symmetriesJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:3e289348-e251-4578-92a8-a991d019317bEnglishSymplectic Elements at Oxford2002Jenkinson, MBrady, MShape representation is fundamental to many areas of computer vision. Local symmetries provide a tool on which to base flexible representations of complex shapes, however, 'multiple participation' symmetries such as SLS generate many more symmetries, than required. This clutters the representation with mostly irrelevant symmetries, hiding perceptually salient information. In this paper, a salience hierarchy is proposed that allows compact, perceptually pleasing representations to be extracted from the highly redundant full SLS. Both individual and competitive saliency is used to create the hierarchy which partitions the set of symmetries into subsets, each of which is an independent shape representation. © 2002 Elsevier Science B.V. All rights reserved.
spellingShingle Jenkinson, M
Brady, M
A saliency-based hierarchy for local symmetries
title A saliency-based hierarchy for local symmetries
title_full A saliency-based hierarchy for local symmetries
title_fullStr A saliency-based hierarchy for local symmetries
title_full_unstemmed A saliency-based hierarchy for local symmetries
title_short A saliency-based hierarchy for local symmetries
title_sort saliency based hierarchy for local symmetries
work_keys_str_mv AT jenkinsonm asaliencybasedhierarchyforlocalsymmetries
AT bradym asaliencybasedhierarchyforlocalsymmetries
AT jenkinsonm saliencybasedhierarchyforlocalsymmetries
AT bradym saliencybasedhierarchyforlocalsymmetries