Show simple item record



dc.contributor.authorPerd’och, Michal
dc.contributor.authorChum, Ondřej
dc.contributor.authorMatas, Jiří
dc.date.accessioned2012-06-12T11:59:00Z
dc.date.available2012-06-12T11:59:00Z
dc.date.issued2009-06
dc.identifier.citationJirí Matas Michal Perdoch, Ondrej Chum. Efficient representation of local geometry for large scale object retrieval. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 9-16, Madison, WI, USA, June 2009. Omnipress.cze
dc.identifier.urihttp://hdl.handle.net/10467/9548
dc.description.abstractState of the art methods for image and object retrieval exploit both appearance (via visual words) and local geometry (spatial extent, relative pose). In large scale problems, memory becomes a limiting factor - local geometry is stored for each feature detected in each image and requires storage larger than the inverted file and term frequency and inverted document frequency weights together. We propose a novel method for learning discretized local geometry representation based on minimization of average reprojection error in the space of ellipses. The representation requires only 24 bits per feature without drop in performance. Additionally, we show that if the gravity vector assumption is used consistently from the feature description to spatial verification, it improves retrieval performance and decreases the memory footprint. The proposed method outperforms state of the art retrieval algorithms in a standard image retrieval benchmark.eng
dc.language.isocescze
dc.publisherIEEEcze
dc.rights© 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.eng
dc.titleEfficient Representation of Local Geometry for Large Scale Object Retrievalcze
dc.typepříspěvek z konference - elektronickýcze
dc.identifier.doi10.1109/CVPR.2009.5206529


Files in this item



This item appears in the following Collection(s)

Show simple item record