This HTML5 document contains 55 embedded RDF statements represented using HTML+Microdata notation.

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

Namespace Prefixes

PrefixIRI
n14http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n20http://purl.org/net/nknouf/ns/bibtex#
n17http://localhost/temp/predkladatel/
n16http://linked.opendata.cz/resource/domain/vavai/projekt/
n8http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n9http://linked.opendata.cz/resource/domain/vavai/subjekt/
n6http://linked.opendata.cz/ontology/domain/vavai/
n18https://schema.org/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n22http://bibframe.org/vocab/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n11http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F68407700%3A21230%2F13%3A00211343%21RIV14-MSM-21230___/
n5http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n21http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n15http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n13http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n23http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n4http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n12http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F68407700%3A21230%2F13%3A00211343%21RIV14-MSM-21230___
rdf:type
n6:Vysledek skos:Concept
dcterms:description
An unconstrained end-to-end text localization and recognition method is presented. The method introduces a novel approach for character detection and recognition which combines the advantages of sliding-window and connected component methods. Characters are detected and recognized as image regions which contain strokes of specific orientations in a specific relative position, where the strokes are efficiently detected by convolving the image gradient field with a set of oriented bar filters. Additionally, a novel character representation efficiently calculated from the values obtained in the stroke detection phase is introduced. The representation is robust to shift at the stroke level, which makes it less sensitive to intra-class variations and the noise induced by normalizing character size and positioning. The effectiveness of the representation is demonstrated by the results achieved in the classification of real-world characters using an euclidian nearest-neighbor classifier trained on synthetic data in a plain form. The method was evaluated on a standard dataset, where it achieves state-of-the-art results in both text localization and recognition. An unconstrained end-to-end text localization and recognition method is presented. The method introduces a novel approach for character detection and recognition which combines the advantages of sliding-window and connected component methods. Characters are detected and recognized as image regions which contain strokes of specific orientations in a specific relative position, where the strokes are efficiently detected by convolving the image gradient field with a set of oriented bar filters. Additionally, a novel character representation efficiently calculated from the values obtained in the stroke detection phase is introduced. The representation is robust to shift at the stroke level, which makes it less sensitive to intra-class variations and the noise induced by normalizing character size and positioning. The effectiveness of the representation is demonstrated by the results achieved in the classification of real-world characters using an euclidian nearest-neighbor classifier trained on synthetic data in a plain form. The method was evaluated on a standard dataset, where it achieves state-of-the-art results in both text localization and recognition.
dcterms:title
Scene Text Localization and Recognition with Oriented Stroke Detection Scene Text Localization and Recognition with Oriented Stroke Detection
skos:prefLabel
Scene Text Localization and Recognition with Oriented Stroke Detection Scene Text Localization and Recognition with Oriented Stroke Detection
skos:notation
RIV/68407700:21230/13:00211343!RIV14-MSM-21230___
n6:predkladatel
n9:orjk%3A21230
n3:aktivita
n15:S n15:P
n3:aktivity
P(7E13016), P(TE01020415), S
n3:dodaniDat
n12:2014
n3:domaciTvurceVysledku
n8:1711326 n8:9115161
n3:druhVysledku
n4:D
n3:duvernostUdaju
n21:S
n3:entitaPredkladatele
n11:predkladatel
n3:idSjednocenehoVysledku
104058
n3:idVysledku
RIV/68407700:21230/13:00211343
n3:jazykVysledku
n13:eng
n3:klicovaSlova
Character recognition; Context; Detectors; Image segmentation; Robustness; Standards; Text recognition; photo OCR; scene text localization; scene text recognition; text-in-the-wild; unconstrained end-to-end text recognition
n3:klicoveSlovo
n5:Detectors n5:Robustness n5:Character%20recognition n5:unconstrained%20end-to-end%20text%20recognition n5:Context n5:photo%20OCR n5:Standards n5:Text%20recognition n5:scene%20text%20localization n5:scene%20text%20recognition n5:text-in-the-wild n5:Image%20segmentation
n3:kontrolniKodProRIV
[719F47496F1B]
n3:mistoKonaniAkce
Sydney
n3:mistoVydani
Piscataway
n3:nazevZdroje
IEEE International Conference on Computer Vision (ICCV 2013)
n3:obor
n23:JD
n3:pocetDomacichTvurcuVysledku
2
n3:pocetTvurcuVysledku
2
n3:projekt
n16:7E13016 n16:TE01020415
n3:rokUplatneniVysledku
n12:2013
n3:tvurceVysledku
Neumann, Lukáš Matas, Jiří
n3:typAkce
n14:WRD
n3:zahajeniAkce
2013-12-01+01:00
s:issn
1550-5499
s:numberOfPages
8
n22:doi
10.1109/ICCV.2013.19
n20:hasPublisher
IEEE
n18:isbn
978-1-4799-2839-2
n17:organizacniJednotka
21230