A comparative study on the use of an ensemble of feature extractors for the automatic design of local image descriptors

Simple item page
dc.contributor.authorCarneiro, G.
dc.contributor.conferenceInternational Conference on Pattern Recognition (20th : 2010 : Istanbul, Turkey)
dc.date.issued2010
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.
dc.description.statementofresponsibilityGustavo Carneiro
dc.identifier.citationICPR 2010: 20th International Conference on Pattern Recognition, Istanbul, Turkey, 23-26 August 2010: pp.3356-3359
dc.identifier.doi10.1109/ICPR.2010.819
dc.identifier.isbn9781424475421
dc.identifier.issn1051-4651
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]
dc.identifier.urihttp://hdl.handle.net/2440/76410
dc.language.isoen
dc.publisherIEEE computer society
dc.publisher.placeOnline
dc.rights© 2010 IEEE
dc.source.urihttps://doi.org/10.1109/icpr.2010.819
dc.titleA comparative study on the use of an ensemble of feature extractors for the automatic design of local image descriptors
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications