This HTML5 document contains 44 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
dctermshttp://purl.org/dc/terms/
n18http://localhost/temp/predkladatel/
n15http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n10http://linked.opendata.cz/resource/domain/vavai/projekt/
n13http://linked.opendata.cz/ontology/domain/vavai/
n11http://linked.opendata.cz/ontology/domain/vavai/riv/podDruhVysledku/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
rdfshttp://www.w3.org/2000/01/rdf-schema#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n19http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F68407700%3A21230%2F14%3A00218863%21RIV15-MSM-21230___/
n9http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n6http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n17http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n4http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n14http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F68407700%3A21230%2F14%3A00218863%21RIV15-MSM-21230___
rdf:type
n13:Vysledek skos:Concept
rdfs:seeAlso
http://cmp.felk.cvut.cz/~sulcmila/papers/Sulc-TR-2014-12.pdf
dcterms:description
A family of novel texture representations called Ffirst, the Fast Features Invariant to Rotation and Scale of Texture, is introduced. New rotation invariants are proposed, extending the LBP-HF features, improving the recognition accuracy. Using the full set of LBP features, as opposed to uniform only, leads to further improvement. Linear Support Vector Machines with an approximate $chi^2$-kernel map are used for fast and precise classification. Experimental results show that Ffirst exceeds the best reported results in texture classification on three difficult texture datasets KTH-TIPS2a, KTH-TIPS2b and ALOT, achieving 88%, 76% and 96% accuracy respectively. The recognition rates are above 99% on standard texture datasets KTH-TIPS, Brodatz32, UIUCTex, UMD, CUReT. A family of novel texture representations called Ffirst, the Fast Features Invariant to Rotation and Scale of Texture, is introduced. New rotation invariants are proposed, extending the LBP-HF features, improving the recognition accuracy. Using the full set of LBP features, as opposed to uniform only, leads to further improvement. Linear Support Vector Machines with an approximate $chi^2$-kernel map are used for fast and precise classification. Experimental results show that Ffirst exceeds the best reported results in texture classification on three difficult texture datasets KTH-TIPS2a, KTH-TIPS2b and ALOT, achieving 88%, 76% and 96% accuracy respectively. The recognition rates are above 99% on standard texture datasets KTH-TIPS, Brodatz32, UIUCTex, UMD, CUReT.
dcterms:title
Fast Features Invariant to Rotation and Scale of Texture Fast Features Invariant to Rotation and Scale of Texture
skos:prefLabel
Fast Features Invariant to Rotation and Scale of Texture Fast Features Invariant to Rotation and Scale of Texture
skos:notation
RIV/68407700:21230/14:00218863!RIV15-MSM-21230___
n3:aktivita
n4:P n4:S
n3:aktivity
P(GBP103/12/G084), S
n3:dodaniDat
n14:2015
n3:domaciTvurceVysledku
n15:1711326 n15:3455157
n3:druhVysledku
n11:V%2FS
n3:duvernostUdaju
n6:S
n3:entitaPredkladatele
n19:predkladatel
n3:idSjednocenehoVysledku
16501
n3:idVysledku
RIV/68407700:21230/14:00218863
n3:jazykVysledku
n17:eng
n3:klicovaSlova
Computer Vision; Texture; Classification; LBP; LBP-HF; Histogram; SVM; Feature maps; Ffirst
n3:klicoveSlovo
n9:Classification n9:SVM n9:Ffirst n9:LBP n9:Feature%20maps n9:Texture n9:Computer%20Vision n9:Histogram n9:LBP-HF
n3:kontrolniKodProRIV
[4EF75539193F]
n3:mistoVydani
Praha
n3:objednatelVyzkumneZpravy
Center for Machine Perception, K13133 FEE Czech Technical University
n3:obor
n8:JD
n3:pocetDomacichTvurcuVysledku
2
n3:pocetTvurcuVysledku
2
n3:projekt
n10:GBP103%2F12%2FG084
n3:rokUplatneniVysledku
n14:2014
n3:tvurceVysledku
Šulc, Milan Matas, Jiří
s:numberOfPages
20
n18:organizacniJednotka
21230