Repository logo
 
Publication

Texture features for object salience

2017-11Journal article Open access
Simple item page
dc.contributor.authorTerzic, Kasim
dc.contributor.authorKrishna, Sai
dc.contributor.authordu Buf, J. M. H.
dc.date.accessioned2019-11-20T15:07:14Z
dc.date.available2019-11-20T15:07:14Z
dc.date.issued2017-11
dc.description.abstractAlthough texture is important for many vision-related tasks, it is not used in most salience models. As a consequence, there are images where all existing salience algorithms fail. We introduce a novel set of texture features built on top of a fast model of complex cells in striate cortex, i.e., visual area V1. The texture at each position is characterised by the two-dimensional local power spectrum obtained from Gabor filters which are tuned to many scales and orientations. We then apply a parametric model and describe the local spectrum by the combination of two one-dimensional Gaussian approximations: the scale and orientation distributions. The scale distribution indicates whether the texture has a dominant frequency and what frequency it is. Likewise, the orientation distribution attests the degree of anisotropy. We evaluate the features in combination with the state-of-the-art VOCUS2 salience algorithm. We found that using our novel texture features in addition to colour improves AUC by 3.8% on the PASCAL-S dataset when compared to the colour-only baseline, and by 62% on a novel texture-based dataset. (C) 2017 Elsevier B.V. All rights reserved.
dc.description.sponsorshipEU [ICT-2009.2.1-270247]
dc.identifier.doi10.1016/j.imavis.2017.09.007
dc.identifier.issn0262-8856
dc.identifier.issn1872-8138
dc.identifier.urihttp://hdl.handle.net/10400.1/12937
dc.language.isoeng
dc.peerreviewedyes
dc.publisherElsevier Science Bv
dc.relationA neuro-dynamic framework for cognitive robotics: scene representations, behavioural sequences, and learning.
dc.subjectPrimary visual-cortex
dc.subjectRegion detection
dc.subjectAttention
dc.subjectVision
dc.subjectSegmentation
dc.subjectMechanisms
dc.subjectImages
dc.subjectOvert
dc.subjectModel
dc.subjectV1
dc.titleTexture features for object salience
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleA neuro-dynamic framework for cognitive robotics: scene representations, behavioural sequences, and learning.
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/5876/UID%2FEEA%2F50009%2F2013/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/EXPL%2FEEI-SII%2F1982%2F2013/PT
oaire.awardURIinfo:eu-repo/grantAgreement/EC/FP7/270247/EU
oaire.citation.endPage51
oaire.citation.startPage43
oaire.citation.titleImage and Vision Computing
oaire.citation.volume67
oaire.fundingStream5876
oaire.fundingStream3599-PPCDT
oaire.fundingStreamFP7
person.familyNamedu Buf
person.givenNameHans
person.identifier.orcid0000-0002-4345-1237
person.identifier.ridM-5125-2013
person.identifier.scopus-author-id6604075916
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100008530
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameEuropean Commission
rcaap.rightsopenAccess
rcaap.typearticle
relation.isAuthorOfPublicationcfad5636-2c77-4db0-a3a0-d7eb97ce6bee
relation.isAuthorOfPublication.latestForDiscoverycfad5636-2c77-4db0-a3a0-d7eb97ce6bee
relation.isProjectOfPublication19a727e2-d775-407f-ab10-7d5f19577e08
relation.isProjectOfPublication59235b52-882c-42ae-946a-d0507ff0f489
relation.isProjectOfPublicationef5f67fa-93e7-4d9a-8157-a59c70c4e0d9
relation.isProjectOfPublication.latestForDiscoveryef5f67fa-93e7-4d9a-8157-a59c70c4e0d9

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Terzic_2017_IVC_ObjectSalience_AAM.pdf
Size:
1.72 MB
Format:
Adobe Portable Document Format
Download

Collections

FCT2-Artigos (em revistas ou actas indexadas)