Visual word spatial arrangement for image retrieval and classification
Identifieur interne : 000011 ( Main/Exploration ); précédent : 000010; suivant : 000012Visual word spatial arrangement for image retrieval and classification
Auteurs : RBID : Pascal:13-0366125Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
We present word spatial arrangement (WSA), an approach to represent the spatial arrangement of visual words under the bag-of-visual-words model. It lies in a simple idea which encodes the relative position of visual words by splitting the image space into quadrants using each detected point as origin. WSA generates compact feature vectors and is flexible for being used for image retrieval and classification, for working with hard or soft assignment, requiring no pre/post processing for spatial verification. Experiments in the retrieval scenario show the superiority of WSA in relation to Spatial Pyramids. Experiments in the classification scenario show a reasonable compromise between those methods, with Spatial Pyramids generating larger feature vectors, while WSA provides adequate performance with much more compact features. As WSA encodes only the spatial information of visual words and not their frequency of occurrence, the results indicate the importance of such information for visual categorization.
Links toward previous steps (curation, corpus...)
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Visual word spatial arrangement for image retrieval and classification</title><author><name sortKey="Penatti, Ot Vio A B" uniqKey="Penatti O">Ot Vio A. B. Penatti</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>RECOD Lab, Institute of Computing (IC), University of Campinas (Unicamp) - Av. Albert Einstein, 1251</s1><s2>Campinas 13083-852, SP</s2><s3>BRA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>5 aut.</sZ></inist:fA14><country>Brésil</country><placeName><region type="state">État de São Paulo</region></placeName></affiliation></author><author><name sortKey="Silva, Fernanda B" uniqKey="Silva F">Fernanda B. Silva</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>RECOD Lab, Institute of Computing (IC), University of Campinas (Unicamp) - Av. Albert Einstein, 1251</s1><s2>Campinas 13083-852, SP</s2><s3>BRA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>5 aut.</sZ></inist:fA14><country>Brésil</country><placeName><region type="state">État de São Paulo</region></placeName></affiliation></author><author><name sortKey="Valle, Eduardo" uniqKey="Valle E">Eduardo Valle</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>RECOD Lab, Institute of Computing (IC), University of Campinas (Unicamp) - Av. Albert Einstein, 1251</s1><s2>Campinas 13083-852, SP</s2><s3>BRA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>5 aut.</sZ></inist:fA14><country>Brésil</country><placeName><region type="state">État de São Paulo</region></placeName></affiliation><affiliation wicri:level="2"><inist:fA14 i1="02"><s1>Department of Computer Engineering and Industrial Automation (DCA), School of Electrical and Computer Engineering (FEEC), University of Campinas (Unicamp) - Av. Albert Einstein, 400</s1><s2>Campinas 13083-852, SP</s2><s3>BRA</s3><sZ>3 aut.</sZ></inist:fA14><country>Brésil</country><placeName><region type="state">État de São Paulo</region></placeName></affiliation></author><author><name sortKey="Gouet Brunet, Valerie" uniqKey="Gouet Brunet V">Valerie Gouet-Brunet</name><affiliation wicri:level="3"><inist:fA14 i1="03"><s1>Paris-Est University, IGN/SR, MATIS Lab, 73 avenue de Paris</s1><s2>94160 Saint-Mandé</s2><s3>FRA</s3><sZ>4 aut.</sZ></inist:fA14><country>France</country><placeName><region type="region" nuts="2">Île-de-France</region><settlement type="city">Saint-Mandé</settlement></placeName></affiliation><affiliation wicri:level="3"><inist:fA14 i1="04"><s1>CNAM, CEDRIC Lab, 292 rue Saint-Martin</s1><s2>75141 Paris</s2><s3>FRA</s3><sZ>4 aut.</sZ></inist:fA14><country>France</country><placeName><region type="region" nuts="2">Île-de-France</region><settlement type="city">Paris</settlement></placeName></affiliation></author><author><name sortKey="Da S Torres, Ricardo" uniqKey="Da S Torres R">Ricardo Da S. Torres</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>RECOD Lab, Institute of Computing (IC), University of Campinas (Unicamp) - Av. Albert Einstein, 1251</s1><s2>Campinas 13083-852, SP</s2><s3>BRA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>5 aut.</sZ></inist:fA14><country>Brésil</country><placeName><region type="state">État de São Paulo</region></placeName></affiliation></author></titleStmt><publicationStmt><idno type="inist">13-0366125</idno><date when="2014">2014</date><idno type="stanalyst">PASCAL 13-0366125 INIST</idno><idno type="RBID">Pascal:13-0366125</idno><idno type="wicri:Area/Main/Corpus">000398</idno><idno type="wicri:Area/Main/Curation">002474</idno><idno type="wicri:Area/Main/Exploration">000011</idno></publicationStmt><seriesStmt><idno type="ISSN">0031-3203</idno><title level="j" type="abbreviated">Pattern recogn.</title><title level="j" type="main">Pattern recognition</title></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Categorization</term><term>Image classification</term><term>Image retrieval</term><term>Occurrence frequency</term><term>Performance evaluation</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Recherche image</term><term>Classification image</term><term>Evaluation performance</term><term>Fréquence apparition</term><term>Catégorisation</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">We present word spatial arrangement (WSA), an approach to represent the spatial arrangement of visual words under the bag-of-visual-words model. It lies in a simple idea which encodes the relative position of visual words by splitting the image space into quadrants using each detected point as origin. WSA generates compact feature vectors and is flexible for being used for image retrieval and classification, for working with hard or soft assignment, requiring no pre/post processing for spatial verification. Experiments in the retrieval scenario show the superiority of WSA in relation to Spatial Pyramids. Experiments in the classification scenario show a reasonable compromise between those methods, with Spatial Pyramids generating larger feature vectors, while WSA provides adequate performance with much more compact features. As WSA encodes only the spatial information of visual words and not their frequency of occurrence, the results indicate the importance of such information for visual categorization.</div></front></TEI><inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0031-3203</s0></fA01><fA02 i1="01"><s0>PTNRA8</s0></fA02><fA03 i2="1"><s0>Pattern recogn.</s0></fA03><fA05><s2>47</s2></fA05><fA06><s2>2</s2></fA06><fA08 i1="01" i2="1" l="ENG"><s1>Visual word spatial arrangement for image retrieval and classification</s1></fA08><fA11 i1="01" i2="1"><s1>PENATTI (Otávio A. B.)</s1></fA11><fA11 i1="02" i2="1"><s1>SILVA (Fernanda B.)</s1></fA11><fA11 i1="03" i2="1"><s1>VALLE (Eduardo)</s1></fA11><fA11 i1="04" i2="1"><s1>GOUET-BRUNET (Valerie)</s1></fA11><fA11 i1="05" i2="1"><s1>DA S. TORRES (Ricardo)</s1></fA11><fA14 i1="01"><s1>RECOD Lab, Institute of Computing (IC), University of Campinas (Unicamp) - Av. Albert Einstein, 1251</s1><s2>Campinas 13083-852, SP</s2><s3>BRA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>5 aut.</sZ></fA14><fA14 i1="02"><s1>Department of Computer Engineering and Industrial Automation (DCA), School of Electrical and Computer Engineering (FEEC), University of Campinas (Unicamp) - Av. Albert Einstein, 400</s1><s2>Campinas 13083-852, SP</s2><s3>BRA</s3><sZ>3 aut.</sZ></fA14><fA14 i1="03"><s1>Paris-Est University, IGN/SR, MATIS Lab, 73 avenue de Paris</s1><s2>94160 Saint-Mandé</s2><s3>FRA</s3><sZ>4 aut.</sZ></fA14><fA14 i1="04"><s1>CNAM, CEDRIC Lab, 292 rue Saint-Martin</s1><s2>75141 Paris</s2><s3>FRA</s3><sZ>4 aut.</sZ></fA14><fA20><s1>705-720</s1></fA20><fA21><s1>2014</s1></fA21><fA23 i1="01"><s0>ENG</s0></fA23><fA43 i1="01"><s1>INIST</s1><s2>15220</s2><s5>354000501094390190</s5></fA43><fA44><s0>0000</s0><s1>© 2013 INIST-CNRS. All rights reserved.</s1></fA44><fA45><s0>36 ref.</s0></fA45><fA47 i1="01" i2="1"><s0>13-0366125</s0></fA47><fA60><s1>P</s1></fA60><fA61><s0>A</s0></fA61><fA64 i1="01" i2="1"><s0>Pattern recognition</s0></fA64><fA66 i1="01"><s0>GBR</s0></fA66><fC01 i1="01" l="ENG"><s0>We present word spatial arrangement (WSA), an approach to represent the spatial arrangement of visual words under the bag-of-visual-words model. It lies in a simple idea which encodes the relative position of visual words by splitting the image space into quadrants using each detected point as origin. WSA generates compact feature vectors and is flexible for being used for image retrieval and classification, for working with hard or soft assignment, requiring no pre/post processing for spatial verification. Experiments in the retrieval scenario show the superiority of WSA in relation to Spatial Pyramids. Experiments in the classification scenario show a reasonable compromise between those methods, with Spatial Pyramids generating larger feature vectors, while WSA provides adequate performance with much more compact features. As WSA encodes only the spatial information of visual words and not their frequency of occurrence, the results indicate the importance of such information for visual categorization.</s0></fC01><fC02 i1="01" i2="X"><s0>001D04A05C</s0></fC02><fC02 i1="02" i2="X"><s0>001D04A04A1</s0></fC02><fC02 i1="03" i2="X"><s0>001D04A03</s0></fC02><fC03 i1="01" i2="3" l="FRE"><s0>Recherche image</s0><s5>01</s5></fC03><fC03 i1="01" i2="3" l="ENG"><s0>Image retrieval</s0><s5>01</s5></fC03><fC03 i1="02" i2="3" l="FRE"><s0>Classification image</s0><s5>02</s5></fC03><fC03 i1="02" i2="3" l="ENG"><s0>Image classification</s0><s5>02</s5></fC03><fC03 i1="03" i2="X" l="FRE"><s0>Evaluation performance</s0><s5>03</s5></fC03><fC03 i1="03" i2="X" l="ENG"><s0>Performance evaluation</s0><s5>03</s5></fC03><fC03 i1="03" i2="X" l="SPA"><s0>Evaluación prestación</s0><s5>03</s5></fC03><fC03 i1="04" i2="X" l="FRE"><s0>Fréquence apparition</s0><s5>04</s5></fC03><fC03 i1="04" i2="X" l="ENG"><s0>Occurrence frequency</s0><s5>04</s5></fC03><fC03 i1="04" i2="X" l="SPA"><s0>Frecuencia aparición</s0><s5>04</s5></fC03><fC03 i1="05" i2="X" l="FRE"><s0>Catégorisation</s0><s5>05</s5></fC03><fC03 i1="05" i2="X" l="ENG"><s0>Categorization</s0><s5>05</s5></fC03><fC03 i1="05" i2="X" l="SPA"><s0>Categorización</s0><s5>05</s5></fC03><fC07 i1="01" i2="X" l="FRE"><s0>Recherche information</s0><s5>06</s5></fC07><fC07 i1="01" i2="X" l="ENG"><s0>Information retrieval</s0><s5>06</s5></fC07><fC07 i1="01" i2="X" l="SPA"><s0>Búsqueda información</s0><s5>06</s5></fC07><fC07 i1="02" i2="X" l="FRE"><s0>Traitement image</s0><s5>07</s5></fC07><fC07 i1="02" i2="X" l="ENG"><s0>Image processing</s0><s5>07</s5></fC07><fC07 i1="02" i2="X" l="SPA"><s0>Procesamiento imagen</s0><s5>07</s5></fC07><fN21><s1>343</s1></fN21><fN44 i1="01"><s1>OTO</s1></fN44><fN82><s1>OTO</s1></fN82></pA></standard></inist></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=FranceBresilV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000011 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000011 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= *** parameter Area/wikiCode missing ***
|area= FranceBresilV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= Pascal:13-0366125
|texte= Visual word spatial arrangement for image retrieval and classification
}}
| This area was generated with Dilib version V0.6.01. |  |