This HTML5 document contains 42 embedded RDF statements represented using HTML+Microdata notation.

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

Namespace Prefixes

PrefixIRI
n21http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n22http://localhost/temp/predkladatel/
n13http://purl.org/net/nknouf/ns/bibtex#
n6http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n12http://linked.opendata.cz/ontology/domain/vavai/
n8https://schema.org/
shttp://schema.org/
n4http://linked.opendata.cz/ontology/domain/vavai/riv/
skoshttp://www.w3.org/2004/02/skos/core#
rdfshttp://www.w3.org/2000/01/rdf-schema#
n11http://bibframe.org/vocab/
n15http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F61989100%3A27240%2F14%3A86093011%21RIV15-MSM-27240___/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n14http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n20http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n19http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n16http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n10http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n7http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n5http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F61989100%3A27240%2F14%3A86093011%21RIV15-MSM-27240___
rdf:type
n12:Vysledek skos:Concept
rdfs:seeAlso
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?reload=true&arnumber=7001946
dcterms:description
Many feature-based object detectors have shown that the use of gradient image information can be a very efficient way to describe the appearance of objects. Especially, the gradient sizes, directions and histograms are commonly used. In this area, the histogram of oriented gradients (HOG) is considered as the state-of-the-art method. The histograms and gradient orientations are used to encode the gradient information in HOG. Nevertheless, many works have proved that the feature vector dimensionality of HOG can be reduced; particularly, the information of the gradient directions is redundant and it can be reduced. This was the motivation to encode the gradient information with the least possible redundant information. In this paper, we propose the method in which the discrete cosine transform (DCT) is used to effectively encode the gradient information; using DCT, the gradient information can be encoded with a relatively small set of DCT coefficients in which the most important gradient information is preserved. We show the properties of presented method for the case of solving the problem of face and pedestrian detection. Many feature-based object detectors have shown that the use of gradient image information can be a very efficient way to describe the appearance of objects. Especially, the gradient sizes, directions and histograms are commonly used. In this area, the histogram of oriented gradients (HOG) is considered as the state-of-the-art method. The histograms and gradient orientations are used to encode the gradient information in HOG. Nevertheless, many works have proved that the feature vector dimensionality of HOG can be reduced; particularly, the information of the gradient directions is redundant and it can be reduced. This was the motivation to encode the gradient information with the least possible redundant information. In this paper, we propose the method in which the discrete cosine transform (DCT) is used to effectively encode the gradient information; using DCT, the gradient information can be encoded with a relatively small set of DCT coefficients in which the most important gradient information is preserved. We show the properties of presented method for the case of solving the problem of face and pedestrian detection.
dcterms:title
Gradient-DCT (G-DCT) descriptors Gradient-DCT (G-DCT) descriptors
skos:prefLabel
Gradient-DCT (G-DCT) descriptors Gradient-DCT (G-DCT) descriptors
skos:notation
RIV/61989100:27240/14:86093011!RIV15-MSM-27240___
n4:aktivita
n19:S
n4:aktivity
S
n4:dodaniDat
n5:2015
n4:domaciTvurceVysledku
n6:4899423 n6:9112995
n4:druhVysledku
n10:D
n4:duvernostUdaju
n20:S
n4:entitaPredkladatele
n15:predkladatel
n4:idSjednocenehoVysledku
18525
n4:idVysledku
RIV/61989100:27240/14:86093011
n4:jazykVysledku
n16:eng
n4:klicovaSlova
object description; image features; feature extraction
n4:klicoveSlovo
n14:feature%20extraction n14:image%20features n14:object%20description
n4:kontrolniKodProRIV
[35527B9C12B0]
n4:mistoKonaniAkce
Paříž
n4:mistoVydani
New York
n4:nazevZdroje
2014 4th International Conference on Image Processing Theory, Tools and Applications, IPTA 2014
n4:obor
n7:IN
n4:pocetDomacichTvurcuVysledku
2
n4:pocetTvurcuVysledku
2
n4:rokUplatneniVysledku
n5:2014
n4:tvurceVysledku
Fusek, Radovan Sojka, Eduard
n4:typAkce
n21:WRD
n4:zahajeniAkce
2014-10-14+02:00
s:numberOfPages
6
n11:doi
10.1109/IPTA.2014.7001946
n13:hasPublisher
Institute of Electrical and Electronics Engineers
n8:isbn
978-1-4799-6461-1
n22:organizacniJednotka
27240