dc.contributor.author | Zhou, Jun | |
dc.contributor.author | Fu, Zhouyu | |
dc.contributor.author | Robles-Kelly, Antonio | |
dc.contributor.editor | Shi, H | |
dc.contributor.editor | Zhang, YC | |
dc.contributor.editor | Bottema, MJ | |
dc.contributor.editor | Lovell, BC | |
dc.contributor.editor | Maeder, AJ | |
dc.date.accessioned | 2017-05-03T16:11:47Z | |
dc.date.available | 2017-05-03T16:11:47Z | |
dc.date.issued | 2009 | |
dc.date.modified | 2013-06-20T04:26:27Z | |
dc.identifier.isbn | 978-1-4244-5297-2 | |
dc.identifier.doi | 10.1109/DICTA.2009.28 | |
dc.identifier.uri | http://hdl.handle.net/10072/51724 | |
dc.description.abstract | In this paper, we address the problem of recovering an optimal salient image descriptor transformation for image classification. Our method involves two steps. Firstly, a binary salient map is generated to specify the regions of interest for subsequent image feature extraction. To this end, an optimal cut-off value is recovered by maximising Fisher's linear discriminant separability measure so as to separate the salient regions from the background of the scene. Next, image descriptors are extracted in the foreground region in order to be optimally transformed. The descriptor optimisation problem is cast in a regularised risk minimisation setting, in which the aim of computation is to recover the optimal transformation up to a cost function. The cost function is convex and can be solved using quadratic programming. The results on unsegmented Oxford Flowers database show that the proposed method can achieve classification performance that are comparable to those provided by alternatives elsewhere in the literature which employ pre-segmented images. | |
dc.description.peerreviewed | Yes | |
dc.description.publicationstatus | Yes | |
dc.format.extent | 254188 bytes | |
dc.format.mimetype | application/pdf | |
dc.language | English | |
dc.publisher | IEEE | |
dc.publisher.place | United States | |
dc.relation.ispartofstudentpublication | N | |
dc.relation.ispartofconferencename | 11th Conference on Digital Image Computing: Techniques and Applications | |
dc.relation.ispartofconferencetitle | 2009 DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA 2009) | |
dc.relation.ispartofdatefrom | 2009-12-01 | |
dc.relation.ispartofdateto | 2009-12-03 | |
dc.relation.ispartoflocation | Melbourne, AUSTRALIA | |
dc.relation.ispartofpagefrom | 125 | |
dc.relation.ispartofpageto | + | |
dc.rights.retention | Y | |
dc.subject.fieldofresearch | Computer vision | |
dc.subject.fieldofresearch | Image processing | |
dc.subject.fieldofresearchcode | 460304 | |
dc.subject.fieldofresearchcode | 460306 | |
dc.title | Learning the Optimal Transformation of Salient Features for Image Classification | |
dc.type | Conference output | |
dc.type.description | E1 - Conferences | |
dc.type.code | E - Conference Publications | |
gro.rights.copyright | © 2009 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |
gro.date.issued | 2009 | |
gro.hasfulltext | Full Text | |
gro.griffith.author | Zhou, Jun | |