Show simple item record



dc.contributor.authorChum, Ondřej
dc.contributor.authorMatas, Jiří
dc.date.accessioned2012-06-07T13:15:00Z
dc.date.available2012-06-07T13:15:00Z
dc.date.issued2006-06
dc.identifier.citationOndrej Chum and Jirí Matas. Geometric hashing with local affine frames. In Andrew Fitzgibbon, Camillo Taylor, and Yan LeCun, editors, Proc. of Conference on Computer Vision and Pattern Recognition (CVPR), volume 1, pages 879-884, Los Alamitos, USA, June 2006. IEEE Computer Society.cze
dc.identifier.urihttp://hdl.handle.net/10467/9499
dc.description.abstractWe propose a novel representation of local image structure and a matching scheme that are insensitive to a wide range of appearance changes. The representation is a collection of local affine frames that are constructed on outer boundaries of maximally stable extremal regions (MSERS) in an affine-covariant way. Each local affine frame is described by a relative location of other local affine frames in its neighborhood. The image is thus represented by quantities that depend only on the location of the boundaries of MSERs. Inter-image correspondences between local affine frames are formed in constant time by geometric hashing. Direct detection of local afine frames removes the requirement of a point-based hashing to establish reference frames in a combinatorial way, which has in the case of affine transform complexily that is cubic in the number of points. Local affine frames, which are also the quantities represented in the hash table, occupy a 6 0 space and hence data collisions are less likely compared with 2 0 point hashing. Experimentally, the robustness of the method and its insensitiviq to photometric changes is demonstrated on images from different spectral bands of satellite sensor; on images of a transparent object and on images of an object taken during day and night.eng
dc.language.isocescze
dc.publisherIEEEcze
dc.rights© 2006 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.titleGeometric Hashing with Local Af ne Framescze
dc.typepříspěvek z konference - elektronickýcze
dc.identifier.doi10.1109/CVPR.2006.125


Files in this item



This item appears in the following Collection(s)

Show simple item record