OcrV1, PascalFrancis, Curation, bibRecord, 000447

Semantic classification of business images

Identifieur interne : 000447 ( PascalFrancis/Curation ); précédent : 000446; suivant : 000448

Semantic classification of business images

Auteurs : Berna Erol [États-Unis] ; Jonathan J. Hull [États-Unis]

Source :

Proceedings of SPIE, the International Society for Optical Engineering

RBID : Pascal:07-0373903

Descripteurs français

Pascal (Inist)
- Multimédia, Analyse sémantique, Classification image, Caractère manuscrit, Reconnaissance optique caractère, Machine vecteur support, Classification automatique, Précision, Traitement image, 4230V, 4230S.
Wicri :
- topic : Multimédia.

English descriptors

KwdEn :
- Accuracy, Automatic classification, Image classification, Image processing, Manuscript character, Multimedia, Optical character recognition, Semantic analysis, Support vector machine.

Abstract

Digital cameras are becoming increasingly common for capturing information in business settings. In this paper, we describe a novel method for classifying images into the following semantic classes: document, whiteboard, business card, slide, and regular images. Our method is based on combining low-level image features, such as text color, layout, and handwriting features with high-level OCR output analysis. Several Support Vector Machine Classifiers are combined for multi-class classification of input images. The system yields 95% accuracy in classification.

A05				`@2 6073`
A08	`01`	`1`	`ENG`	`@1 Semantic classification of business images`
A09	`01`	`1`	`ENG`	`@1 Multimedia content analysis, management, and retrieval 2006 : 17-19 January 2006, San Jose, California, USA`
A11	`01`	`1`		`@1 EROL (Berna)`
A11	`02`	`1`		`@1 HULL (Jonathan J.)`
A12	`01`	`1`		`@1 CHANG (Edward Y.) @9 ed.`
A12	`02`	`1`		`@1 HANJALIC (Alan) @9 ed.`
A12	`03`	`1`		`@1 SEBE (Nicu) @9 ed.`
A14	`01`			`@1 Ricoh California Research Center 2882 Sand Hill Rd. Suite 115 @2 Menlo Park, California @3 USA @Z 1 aut. @Z 2 aut.`
A18	`01`	`1`		`@1 IS&T--The Society for Imaging Science and Technology @3 USA @9 org-cong.`
A18	`02`	`1`		`@1 Society of photo-optical instrumentation engineers @3 USA @9 org-cong.`
A20				`@2 60730G.1-60730G.8`
A21				`@1 2006`
A23	`01`			`@0 ENG`
A26	`01`			`@0 0-8194-6113-X`
A43	`01`			`@1 INIST @2 21760 @5 354000153561090150`
A44				`@0 0000 @1 © 2007 INIST-CNRS. All rights reserved.`
A45				`@0 14 ref.`
A47	`01`	`1`		`@0 07-0373903`
A60				`@1 P @2 C`
A61				`@0 A`
A64	`01`	`2`		`@0 Proceedings of SPIE, the International Society for Optical Engineering`
A66	`01`			`@0 USA`
C01	`01`		`ENG`	@0 Digital cameras are becoming increasingly common for capturing information in business settings. In this paper, we describe a novel method for classifying images into the following semantic classes: document, whiteboard, business card, slide, and regular images. Our method is based on combining low-level image features, such as text color, layout, and handwriting features with high-level OCR output analysis. Several Support Vector Machine Classifiers are combined for multi-class classification of input images. The system yields 95% accuracy in classification.
C02	`01`	`X`		`@0 001D04A04A1`
C02	`02`	`X`		`@0 001D04A05A`
C02	`03`	`X`		`@0 001D04A05C`
C02	`04`	`3`		`@0 001B40B30V`
C03	`01`	`X`	`FRE`	`@0 Multimédia @5 61`
C03	`01`	`X`	`ENG`	`@0 Multimedia @5 61`
C03	`01`	`X`	`SPA`	`@0 Multimedia @5 61`
C03	`02`	`X`	`FRE`	`@0 Analyse sémantique @5 62`
C03	`02`	`X`	`ENG`	`@0 Semantic analysis @5 62`
C03	`02`	`X`	`SPA`	`@0 Análisis semántico @5 62`
C03	`03`	`3`	`FRE`	`@0 Classification image @5 63`
C03	`03`	`3`	`ENG`	`@0 Image classification @5 63`
C03	`04`	`X`	`FRE`	`@0 Caractère manuscrit @5 64`
C03	`04`	`X`	`ENG`	`@0 Manuscript character @5 64`
C03	`04`	`X`	`SPA`	`@0 Carácter manuscrito @5 64`
C03	`05`	`X`	`FRE`	`@0 Reconnaissance optique caractère @5 65`
C03	`05`	`X`	`ENG`	`@0 Optical character recognition @5 65`
C03	`05`	`X`	`SPA`	`@0 Reconocimento óptico de caracteres @5 65`
C03	`06`	`X`	`FRE`	`@0 Machine vecteur support @5 66`
C03	`06`	`X`	`ENG`	`@0 Support vector machine @5 66`
C03	`06`	`X`	`SPA`	`@0 Máquina vector soporte @5 66`
C03	`07`	`X`	`FRE`	`@0 Classification automatique @5 67`
C03	`07`	`X`	`ENG`	`@0 Automatic classification @5 67`
C03	`07`	`X`	`SPA`	`@0 Clasificación automática @5 67`
C03	`08`	`X`	`FRE`	`@0 Précision @5 68`
C03	`08`	`X`	`ENG`	`@0 Accuracy @5 68`
C03	`08`	`X`	`SPA`	`@0 Precisión @5 68`
C03	`09`	`X`	`FRE`	`@0 Traitement image @5 69`
C03	`09`	`X`	`ENG`	`@0 Image processing @5 69`
C03	`09`	`X`	`SPA`	`@0 Procesamiento imagen @5 69`
C03	`10`	`X`	`FRE`	`@0 4230V @4 INC @5 91`
C03	`11`	`X`	`FRE`	`@0 4230S @4 INC @5 92`
N21				`@1 239`
N44	`01`			`@1 OTO`
N82				`@1 OTO`

A30	`01`	`1`	`ENG`	`@1 Multimedia content analysis, management, and retrieval @3 USA @4 2006`

Links toward previous steps (curation, corpus...)

to stream PascalFrancis, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000339

Links to Exploration step

Pascal:07-0373903

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Semantic classification of business images</title>
<author><name sortKey="Erol, Berna" sort="Erol, Berna" uniqKey="Erol B" first="Berna" last="Erol">Berna Erol</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Ricoh California Research Center 2882 Sand Hill Rd. Suite 115</s1>
<s2>Menlo Park, California</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Hull, Jonathan J" sort="Hull, Jonathan J" uniqKey="Hull J" first="Jonathan J." last="Hull">Jonathan J. Hull</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Ricoh California Research Center 2882 Sand Hill Rd. Suite 115</s1>
<s2>Menlo Park, California</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">07-0373903</idno>
<date when="2006">2006</date>
<idno type="stanalyst">PASCAL 07-0373903 INIST</idno>
<idno type="RBID">Pascal:07-0373903</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000339</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000447</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Semantic classification of business images</title>
<author><name sortKey="Erol, Berna" sort="Erol, Berna" uniqKey="Erol B" first="Berna" last="Erol">Berna Erol</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Ricoh California Research Center 2882 Sand Hill Rd. Suite 115</s1>
<s2>Menlo Park, California</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
</affiliation>
</author>
<author><name sortKey="Hull, Jonathan J" sort="Hull, Jonathan J" uniqKey="Hull J" first="Jonathan J." last="Hull">Jonathan J. Hull</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Ricoh California Research Center 2882 Sand Hill Rd. Suite 115</s1>
<s2>Menlo Park, California</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Proceedings of SPIE, the International Society for Optical Engineering</title>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Proceedings of SPIE, the International Society for Optical Engineering</title>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Accuracy</term>
<term>Automatic classification</term>
<term>Image classification</term>
<term>Image processing</term>
<term>Manuscript character</term>
<term>Multimedia</term>
<term>Optical character recognition</term>
<term>Semantic analysis</term>
<term>Support vector machine</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Multimédia</term>
<term>Analyse sémantique</term>
<term>Classification image</term>
<term>Caractère manuscrit</term>
<term>Reconnaissance optique caractère</term>
<term>Machine vecteur support</term>
<term>Classification automatique</term>
<term>Précision</term>
<term>Traitement image</term>
<term>4230V</term>
<term>4230S</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Multimédia</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Digital cameras are becoming increasingly common for capturing information in business settings. In this paper, we describe a novel method for classifying images into the following semantic classes: document, whiteboard, business card, slide, and regular images. Our method is based on combining low-level image features, such as text color, layout, and handwriting features with high-level OCR output analysis. Several Support Vector Machine Classifiers are combined for multi-class classification of input images. The system yields 95% accuracy in classification.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA05><s2>6073</s2>
</fA05>
<fA08 i1="01" i2="1" l="ENG"><s1>Semantic classification of business images</s1>
</fA08>
<fA09 i1="01" i2="1" l="ENG"><s1>Multimedia content analysis, management, and retrieval 2006 : 17-19 January 2006, San Jose, California, USA</s1>
</fA09>
<fA11 i1="01" i2="1"><s1>EROL (Berna)</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>HULL (Jonathan J.)</s1>
</fA11>
<fA12 i1="01" i2="1"><s1>CHANG (Edward Y.)</s1>
<s9>ed.</s9>
</fA12>
<fA12 i1="02" i2="1"><s1>HANJALIC (Alan)</s1>
<s9>ed.</s9>
</fA12>
<fA12 i1="03" i2="1"><s1>SEBE (Nicu)</s1>
<s9>ed.</s9>
</fA12>
<fA14 i1="01"><s1>Ricoh California Research Center 2882 Sand Hill Rd. Suite 115</s1>
<s2>Menlo Park, California</s2>
<s3>USA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</fA14>
<fA18 i1="01" i2="1"><s1>IS&T--The Society for Imaging Science and Technology</s1>
<s3>USA</s3>
<s9>org-cong.</s9>
</fA18>
<fA18 i1="02" i2="1"><s1>Society of photo-optical instrumentation engineers</s1>
<s3>USA</s3>
<s9>org-cong.</s9>
</fA18>
<fA20><s2>60730G.1-60730G.8</s2>
</fA20>
<fA21><s1>2006</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA26 i1="01"><s0>0-8194-6113-X</s0>
</fA26>
<fA43 i1="01"><s1>INIST</s1>
<s2>21760</s2>
<s5>354000153561090150</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2007 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>14 ref.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>07-0373903</s0>
</fA47>
<fA60><s1>P</s1>
<s2>C</s2>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="2"><s0>Proceedings of SPIE, the International Society for Optical Engineering</s0>
</fA64>
<fA66 i1="01"><s0>USA</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>Digital cameras are becoming increasingly common for capturing information in business settings. In this paper, we describe a novel method for classifying images into the following semantic classes: document, whiteboard, business card, slide, and regular images. Our method is based on combining low-level image features, such as text color, layout, and handwriting features with high-level OCR output analysis. Several Support Vector Machine Classifiers are combined for multi-class classification of input images. The system yields 95% accuracy in classification.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D04A04A1</s0>
</fC02>
<fC02 i1="02" i2="X"><s0>001D04A05A</s0>
</fC02>
<fC02 i1="03" i2="X"><s0>001D04A05C</s0>
</fC02>
<fC02 i1="04" i2="3"><s0>001B40B30V</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Multimédia</s0>
<s5>61</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Multimedia</s0>
<s5>61</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Multimedia</s0>
<s5>61</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Analyse sémantique</s0>
<s5>62</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Semantic analysis</s0>
<s5>62</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Análisis semántico</s0>
<s5>62</s5>
</fC03>
<fC03 i1="03" i2="3" l="FRE"><s0>Classification image</s0>
<s5>63</s5>
</fC03>
<fC03 i1="03" i2="3" l="ENG"><s0>Image classification</s0>
<s5>63</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Caractère manuscrit</s0>
<s5>64</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Manuscript character</s0>
<s5>64</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Carácter manuscrito</s0>
<s5>64</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Reconnaissance optique caractère</s0>
<s5>65</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Optical character recognition</s0>
<s5>65</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Reconocimento óptico de caracteres</s0>
<s5>65</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Machine vecteur support</s0>
<s5>66</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Support vector machine</s0>
<s5>66</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Máquina vector soporte</s0>
<s5>66</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Classification automatique</s0>
<s5>67</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Automatic classification</s0>
<s5>67</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA"><s0>Clasificación automática</s0>
<s5>67</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>Précision</s0>
<s5>68</s5>
</fC03>
<fC03 i1="08" i2="X" l="ENG"><s0>Accuracy</s0>
<s5>68</s5>
</fC03>
<fC03 i1="08" i2="X" l="SPA"><s0>Precisión</s0>
<s5>68</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE"><s0>Traitement image</s0>
<s5>69</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG"><s0>Image processing</s0>
<s5>69</s5>
</fC03>
<fC03 i1="09" i2="X" l="SPA"><s0>Procesamiento imagen</s0>
<s5>69</s5>
</fC03>
<fC03 i1="10" i2="X" l="FRE"><s0>4230V</s0>
<s4>INC</s4>
<s5>91</s5>
</fC03>
<fC03 i1="11" i2="X" l="FRE"><s0>4230S</s0>
<s4>INC</s4>
<s5>92</s5>
</fC03>
<fN21><s1>239</s1>
</fN21>
<fN44 i1="01"><s1>OTO</s1>
</fN44>
<fN82><s1>OTO</s1>
</fN82>
</pA>
<pR><fA30 i1="01" i2="1" l="ENG"><s1>Multimedia content analysis, management, and retrieval</s1>
<s3>USA</s3>
<s4>2006</s4>
</fA30>
</pR>
</standard>
</inist>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PascalFrancis/Curation

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000447 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Curation/biblio.hfd -nk 000447 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Ticri/CIDE
   |area=    OcrV1
   |flux=    PascalFrancis
   |étape=   Curation
   |type=    RBID
   |clé=     Pascal:07-0373903
   |texte=   Semantic classification of business images
}}

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024

	Serveur d'exploration sur l'OCR
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur l'OCR

Semantic classification of business images

Semantic classification of business images

Source :

Descripteurs français

English descriptors

Abstract

Links toward previous steps (curation, corpus...)

Links to Exploration step

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri