About: Improving SIFT for Fast Tree Matching by Optimal Linear Projection     Goto   Sponge   NotDistinct   Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

AttributesValues
rdf:type
Description
  • We propose to transform an image descriptor so that nearest neighbor (NN) search for correspondences becomes the optimal matching strategy under the assumption that inter-image deviations of corresponding descriptors have Gaussian distribution. The Euclidean NN in the transformed domain corresponds to the NN according to a truncated Mahalanobis metric in the original descriptor space. We provide theoretical justification for the proposed approach and show experimentally that the transformation allows a significant dimensionality reduction and improves matching performance of a state-of-the art SIFT descriptor. We observe consistent improvement in precision-recall and speed of fast matching in tree structures at the expense of little overhead for projecting the descriptors into transformed space. In the context of SIFT vs. transformed MSIFT comparison, tree search structures are evaluated according to different criteria and query types. All search tree experiments confirm that transform
  • We propose to transform an image descriptor so that nearest neighbor (NN) search for correspondences becomes the optimal matching strategy under the assumption that inter-image deviations of corresponding descriptors have Gaussian distribution. The Euclidean NN in the transformed domain corresponds to the NN according to a truncated Mahalanobis metric in the original descriptor space. We provide theoretical justification for the proposed approach and show experimentally that the transformation allows a significant dimensionality reduction and improves matching performance of a state-of-the art SIFT descriptor. We observe consistent improvement in precision-recall and speed of fast matching in tree structures at the expense of little overhead for projecting the descriptors into transformed space. In the context of SIFT vs. transformed MSIFT comparison, tree search structures are evaluated according to different criteria and query types. All search tree experiments confirm that transform (en)
  • We propose to transform an image descriptor so that nearest neighbor (NN) search for correspondences becomes the optimal matching strategy under the assumption that inter-image deviations of corresponding descriptors have Gaussian distribution. The Euclidean NN in the transformed domain corresponds to the NN according to a truncated Mahalanobis metric in the original descriptor space. We provide theoretical justification for the proposed approach and show experimentally that the transformation allows a significant dimensionality reduction and improves matching performance of a state-of-the art SIFT descriptor. We observe consistent improvement in precision-recall and speed of fast matching in tree structures at the expense of little overhead for projecting the descriptors into transformed space. In the context of SIFT vs. transformed MSIFT comparison, tree search structures are evaluated according to different criteria and query types. All search tree experiments confirm that transform (cs)
Title
  • Improving SIFT for Fast Tree Matching by Optimal Linear Projection
  • Improving SIFT for Fast Tree Matching by Optimal Linear Projection (en)
  • Improving SIFT for Fast Tree Matching by Optimal Linear Projection (cs)
skos:prefLabel
  • Improving SIFT for Fast Tree Matching by Optimal Linear Projection
  • Improving SIFT for Fast Tree Matching by Optimal Linear Projection (en)
  • Improving SIFT for Fast Tree Matching by Optimal Linear Projection (cs)
skos:notation
  • RIV/68407700:21230/07:03135492!RIV08-GA0-21230___
http://linked.open.../vavai/riv/strany
  • Nečíslováno
http://linked.open...avai/riv/aktivita
http://linked.open...avai/riv/aktivity
  • P(GA102/07/1317)
http://linked.open...vai/riv/dodaniDat
http://linked.open...aciTvurceVysledku
http://linked.open.../riv/druhVysledku
http://linked.open...iv/duvernostUdaju
http://linked.open...titaPredkladatele
http://linked.open...dnocenehoVysledku
  • 425798
http://linked.open...ai/riv/idVysledku
  • RIV/68407700:21230/07:03135492
http://linked.open...riv/jazykVysledku
http://linked.open.../riv/klicovaSlova
  • SIFT; metric treesr; retrieval (en)
http://linked.open.../riv/klicoveSlovo
http://linked.open...ontrolniKodProRIV
  • [C289B2DE5C6F]
http://linked.open...v/mistoKonaniAkce
  • Rio de Janeiro
http://linked.open...i/riv/mistoVydani
  • Madison
http://linked.open...i/riv/nazevZdroje
  • ICCV 2007: Proceedings of Eleventh IEEE International Conference on Computer Vision
http://linked.open...in/vavai/riv/obor
http://linked.open...ichTvurcuVysledku
http://linked.open...cetTvurcuVysledku
http://linked.open...vavai/riv/projekt
http://linked.open...UplatneniVysledku
http://linked.open...iv/tvurceVysledku
  • Matas, Jiří
  • Mikolajczyk, K.
http://linked.open...vavai/riv/typAkce
http://linked.open.../riv/zahajeniAkce
number of pages
http://purl.org/ne...btex#hasPublisher
  • Omnipress
https://schema.org/isbn
  • 978-1-4244-1630-1
http://localhost/t...ganizacniJednotka
  • 21230
Faceted Search & Find service v1.16.118 as of Jun 21 2024


Alternative Linked Data Documents: ODE     Content Formats:   [cxml] [csv]     RDF   [text] [turtle] [ld+json] [rdf+json] [rdf+xml]     ODATA   [atom+xml] [odata+json]     Microdata   [microdata+json] [html]    About   
This material is Open Knowledge   W3C Semantic Web Technology [RDF Data] Valid XHTML + RDFa
OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software