Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/76410
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorCarneiro, G.en
dc.date.issued2010en
dc.identifier.citationICPR 2010: 20th International Conference on Pattern Recognition, Istanbul, Turkey, 23-26 August 2010: pp.3356-3359en
dc.identifier.isbn9781424475421en
dc.identifier.issn1051-4651en
dc.identifier.urihttp://hdl.handle.net/2440/76410-
dc.description.abstractThe use of an ensemble of feature spaces trained with distance metric learning methods has been empirically shown to be useful for the task of automatically designing local image descriptors. In this paper, we present a quantitative analysis which shows that in general, nonlinear distance metric learning methods provide better results than linear methods for automatically designing local image descriptors. In addition, we show that the learned feature spaces present better results than state of- the-art hand designed features in benchmark quantitative comparisons. We discuss the results and suggest relevant problems for further investigation.en
dc.description.statementofresponsibilityGustavo Carneiroen
dc.language.isoenen
dc.publisherIEEE computer societyen
dc.rights© 2010 IEEEen
dc.titleA comparative study on the use of an ensemble of feature extractors for the automatic design of local image descriptorsen
dc.typeConference paperen
dc.identifier.rmid0020114360en
dc.contributor.conferenceInternational Conference on Pattern Recognition (20th : 2010 : Istanbul, Turkey)en
dc.identifier.doi10.1109/ICPR.2010.819en
dc.publisher.placeOnlineen
dc.identifier.pubid27018-
pubs.library.collectionComputer Science publicationsen
pubs.verification-statusVerifieden
pubs.publication-statusPublisheden
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]en
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.