Show simple item record  

dc.contributor.authorZhang, Edmond Yiwen
dc.contributor.authorMayo, Michael
dc.coverage.spatialConference held at Melbourne, Australiaen_NZ
dc.date.accessioned2009-08-19T23:03:44Z
dc.date.available2009-08-19T23:03:44Z
dc.date.issued2009
dc.identifier.citationZhang, E., Mayo, M. (2009). SIFTing the Relevant from the Irrelevant: Automatically Detecting Objects in Training Images. In Proceedings of 2009 Digital Image Computing: Techniques and Applications, DICTA 2009, 1-3 December 2009, Melbourne, Australia (pp. 317-324). Washington, DC, USA: IEEE.en
dc.identifier.urihttps://hdl.handle.net/10289/2854
dc.description.abstractMany state-of-the-art object recognition systems rely on identifying the location of objects in images, in order to better learn its visual attributes. In this paper, we propose four simple yet powerful hybrid ROI detection methods (combining both local and global features), based on frequently occurring keypoints. We show that our methods demonstrate competitive performance in two different types of datasets, the Caltech101 dataset and the GRAZ-02 dataset, where the pairs of keypoint bounding box method achieved the best accuracies overall.en
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherIEEE Computer Societyen_NZ
dc.rights©2009 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en
dc.subjectImage processingen
dc.subjectSIFT keypointsen
dc.subjectImage recognition and categorizationen
dc.subjectROI detectionen
dc.subjectMachine learning
dc.titleSIFTing the relevant from the irrelevant: Automatically detecting objects in training imagesen
dc.typeConference Contributionen
dc.identifier.doi10.1109/DICTA.2009.59
dc.relation.isPartOfProc 2009 Digital Image Computing: Techniques and Applicationsen_NZ
pubs.begin-page317en_NZ
pubs.elements-id18969
pubs.end-page324en_NZ
pubs.finish-date2009-12-03en_NZ
pubs.start-date2009-12-01en_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record