OcrV1, PascalFrancis, Corpus, bibRecord, 000695

Skew detection and reconstruction of color-printed document images

Identifieur interne : 000695 ( PascalFrancis/Corpus ); précédent : 000694; suivant : 000696

Skew detection and reconstruction of color-printed document images

Auteurs : Y. K. Chen ; J. F. Wang

Source :

IEICE Transactions on Information and Systems [ 0916-8532 ] ; 2001.

RBID : Pascal:02-0026829

Descripteurs français

Pascal (Inist)
- Théorie, Traitement image couleur, Algorithme, Reconnaissance optique caractère, Logiciel, Couleur, Modèle mathématique, Méthode numérique, Reconstruction image.

English descriptors

KwdEn :
- Algorithms, Color, Color image processing, Color printed document image, Color transition count, Computer software, Image reconstruction, Mathematical models, Numerical methods, Optical character recognition, Skew detection, Theory.

Abstract

Large amounts of color-printed documents are published now everyday. Some OCR approaches of color-printed document images are provided, but they cannot normally work if the input images skew. In the past years, many algorithms are provided to detect the skew of monochrome document images but none of them process color-printed document images. All of these methods assume that text is printed in black on a white background and cannot be applied to detect skew in color-printed document images. In this paper, we propose an algorithm to detect the skew angle of a color-printed document image and reconstruct it. Our approach first determines variation of color-transition count at each angle (from -45° to +45°) and the angle of maximal variation is regarded as the skew angle. Then, a scanning-line model reconstructs the image. We test 100 color-printed document images of various kinds and get good results (93 succeed and 7 fail). The average processing time of A4 size image is 2.76 seconds and the reconstruction time is 3.97 seconds on a Pentium III 733 PC.

Notice en format standard (ISO 2709)

Pour connaître la documentation sur le format Inist Standard.

A01	`01`	`1`		`@0 0916-8532`
A02	`01`			`@0 ITISEF`
A03		`1`		`@0 IEICE Trans Inf Syst`
A05				`@2 v E84-D`
A06				`@2 8`
A08	`01`	`1`	`ENG`	`@1 Skew detection and reconstruction of color-printed document images`
A11	`01`	`1`		`@1 CHEN (Y. K.)`
A11	`02`	`1`		`@1 WANG (J. F.)`
A14	`01`			`@1 Institute of Information Engineering National Cheng Kung University @2 Tainan @3 TWN @Z 1 aut.`
A20				`@1 1018-1024`
A21				`@1 2001`
A23	`01`			`@0 ENG`
A43	`01`			`@1 INIST @2 XXXX`
A44				`@0 A100`
A45				`@0 23 Refs.`
A47	`01`	`1`		`@0 02-0026829`
A60				`@1 P`
A61				`@0 A`
A64	`01`	`1`		`@0 IEICE Transactions on Information and Systems`
A66	`01`			`@0 JPN`
C01	`01`		`ENG`	@0 Large amounts of color-printed documents are published now everyday. Some OCR approaches of color-printed document images are provided, but they cannot normally work if the input images skew. In the past years, many algorithms are provided to detect the skew of monochrome document images but none of them process color-printed document images. All of these methods assume that text is printed in black on a white background and cannot be applied to detect skew in color-printed document images. In this paper, we propose an algorithm to detect the skew angle of a color-printed document image and reconstruct it. Our approach first determines variation of color-transition count at each angle (from -45° to +45°) and the angle of maximal variation is regarded as the skew angle. Then, a scanning-line model reconstructs the image. We test 100 color-printed document images of various kinds and get good results (93 succeed and 7 fail). The average processing time of A4 size image is 2.76 seconds and the reconstruction time is 3.97 seconds on a Pentium III 733 PC.
C02	`01`	`X`		`@0 001D02B07B`
C02	`02`	`X`		`@0 001D02B03`
C02	`03`	`X`		`@0 001D02B12`
C02	`04`	`3`		`@0 001B40B`
C02	`05`	`X`		`@0 001A02I01`
C03	`01`	`1`	`ENG`	`@0 Color printed document image @4 INC`
C03	`02`	`1`	`ENG`	`@0 Skew detection @4 INC`
C03	`03`	`1`	`ENG`	`@0 Color transition count @4 INC`
C03	`04`	`1`	`FRE`	`@0 Théorie`
C03	`04`	`1`	`ENG`	`@0 Theory`
C03	`05`	`1`	`FRE`	`@0 Traitement image couleur`
C03	`05`	`1`	`ENG`	`@0 Color image processing`
C03	`06`	`1`	`FRE`	`@0 Algorithme`
C03	`06`	`1`	`ENG`	`@0 Algorithms`
C03	`07`	`1`	`FRE`	`@0 Reconnaissance optique caractère`
C03	`07`	`1`	`ENG`	`@0 Optical character recognition`
C03	`08`	`1`	`FRE`	`@0 Logiciel`
C03	`08`	`1`	`ENG`	`@0 Computer software`
C03	`09`	`1`	`FRE`	`@0 Couleur`
C03	`09`	`1`	`ENG`	`@0 Color`
C03	`10`	`1`	`FRE`	`@0 Modèle mathématique`
C03	`10`	`1`	`ENG`	`@0 Mathematical models`
C03	`11`	`1`	`FRE`	`@0 Méthode numérique`
C03	`11`	`1`	`ENG`	`@0 Numerical methods`
C03	`12`	`1`	`FRE`	`@0 Reconstruction image @3 P`
C03	`12`	`1`	`ENG`	`@0 Image reconstruction @3 P`
N21				`@1 014`

Format Inist (serveur)

NO :	PASCAL 02-0026829 EI
ET :	Skew detection and reconstruction of color-printed document images
AU :	CHEN (Y. K.); WANG (J. F.)
AF :	Institute of Information Engineering National Cheng Kung University/Tainan/Taïwan (1 aut.)
DT :	Publication en série; Niveau analytique
SO :	IEICE Transactions on Information and Systems; ISSN 0916-8532; Coden ITISEF; Japon; Da. 2001; Vol. v E84-D; No. 8; Pp. 1018-1024; Bibl. 23 Refs.
LA :	Anglais
EA :	Large amounts of color-printed documents are published now everyday. Some OCR approaches of color-printed document images are provided, but they cannot normally work if the input images skew. In the past years, many algorithms are provided to detect the skew of monochrome document images but none of them process color-printed document images. All of these methods assume that text is printed in black on a white background and cannot be applied to detect skew in color-printed document images. In this paper, we propose an algorithm to detect the skew angle of a color-printed document image and reconstruct it. Our approach first determines variation of color-transition count at each angle (from -45° to +45°) and the angle of maximal variation is regarded as the skew angle. Then, a scanning-line model reconstructs the image. We test 100 color-printed document images of various kinds and get good results (93 succeed and 7 fail). The average processing time of A4 size image is 2.76 seconds and the reconstruction time is 3.97 seconds on a Pentium III 733 PC.
CC :	001D02B07B; 001D02B03; 001D02B12; 001B40B; 001A02I01
FD :	Théorie; Traitement image couleur; Algorithme; Reconnaissance optique caractère; Logiciel; Couleur; Modèle mathématique; Méthode numérique; Reconstruction image
ED :	Color printed document image; Skew detection; Color transition count; Theory; Color image processing; Algorithms; Optical character recognition; Computer software; Color; Mathematical models; Numerical methods; Image reconstruction
LO :	INIST-XXXX
ID :	02-0026829

Links to Exploration step

Pascal:02-0026829

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Skew detection and reconstruction of color-printed document images</title>
<author><name sortKey="Chen, Y K" sort="Chen, Y K" uniqKey="Chen Y" first="Y. K." last="Chen">Y. K. Chen</name>
<affiliation><inist:fA14 i1="01"><s1>Institute of Information Engineering National Cheng Kung University</s1>
<s2>Tainan</s2>
<s3>TWN</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Wang, J F" sort="Wang, J F" uniqKey="Wang J" first="J. F." last="Wang">J. F. Wang</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">02-0026829</idno>
<date when="2001">2001</date>
<idno type="stanalyst">PASCAL 02-0026829 EI</idno>
<idno type="RBID">Pascal:02-0026829</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000695</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Skew detection and reconstruction of color-printed document images</title>
<author><name sortKey="Chen, Y K" sort="Chen, Y K" uniqKey="Chen Y" first="Y. K." last="Chen">Y. K. Chen</name>
<affiliation><inist:fA14 i1="01"><s1>Institute of Information Engineering National Cheng Kung University</s1>
<s2>Tainan</s2>
<s3>TWN</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author><name sortKey="Wang, J F" sort="Wang, J F" uniqKey="Wang J" first="J. F." last="Wang">J. F. Wang</name>
</author>
</analytic>
<series><title level="j" type="main">IEICE Transactions on Information and Systems</title>
<title level="j" type="abbreviated">IEICE Trans Inf Syst</title>
<idno type="ISSN">0916-8532</idno>
<imprint><date when="2001">2001</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">IEICE Transactions on Information and Systems</title>
<title level="j" type="abbreviated">IEICE Trans Inf Syst</title>
<idno type="ISSN">0916-8532</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term>
<term>Color</term>
<term>Color image processing</term>
<term>Color printed document image</term>
<term>Color transition count</term>
<term>Computer software</term>
<term>Image reconstruction</term>
<term>Mathematical models</term>
<term>Numerical methods</term>
<term>Optical character recognition</term>
<term>Skew detection</term>
<term>Theory</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Théorie</term>
<term>Traitement image couleur</term>
<term>Algorithme</term>
<term>Reconnaissance optique caractère</term>
<term>Logiciel</term>
<term>Couleur</term>
<term>Modèle mathématique</term>
<term>Méthode numérique</term>
<term>Reconstruction image</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Large amounts of color-printed documents are published now everyday.  Some OCR approaches of color-printed document images are provided, but they cannot normally work if the input images skew. In the past years, many algorithms are provided to detect the skew of monochrome document images but none of them process color-printed document images. All of these methods assume that text is printed in black on a white background and cannot be applied to detect skew in color-printed document images. In this paper, we propose an algorithm to detect the skew angle of a color-printed document image and reconstruct it. Our approach first determines variation of color-transition count at each angle (from -45° to +45°) and the angle of maximal variation is regarded as the skew angle. Then, a scanning-line model reconstructs the image. We test 100 color-printed document images of various kinds and get good results (93 succeed and 7 fail). The average processing time of A4 size image is 2.76 seconds and the reconstruction time is 3.97 seconds on a Pentium III 733 PC.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0916-8532</s0>
</fA01>
<fA02 i1="01"><s0>ITISEF</s0>
</fA02>
<fA03 i2="1"><s0>IEICE Trans Inf Syst</s0>
</fA03>
<fA05><s2>v E84-D</s2>
</fA05>
<fA06><s2>8</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>Skew detection and reconstruction of color-printed document images</s1>
</fA08>
<fA11 i1="01" i2="1"><s1>CHEN (Y. K.)</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>WANG (J. F.)</s1>
</fA11>
<fA14 i1="01"><s1>Institute of Information Engineering National Cheng Kung University</s1>
<s2>Tainan</s2>
<s3>TWN</s3>
<sZ>1 aut.</sZ>
</fA14>
<fA20><s1>1018-1024</s1>
</fA20>
<fA21><s1>2001</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>XXXX</s2>
</fA43>
<fA44><s0>A100</s0>
</fA44>
<fA45><s0>23 Refs.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>02-0026829</s0>
</fA47>
<fA60><s1>P</s1>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>IEICE Transactions on Information and Systems</s0>
</fA64>
<fA66 i1="01"><s0>JPN</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>Large amounts of color-printed documents are published now everyday.  Some OCR approaches of color-printed document images are provided, but they cannot normally work if the input images skew. In the past years, many algorithms are provided to detect the skew of monochrome document images but none of them process color-printed document images. All of these methods assume that text is printed in black on a white background and cannot be applied to detect skew in color-printed document images. In this paper, we propose an algorithm to detect the skew angle of a color-printed document image and reconstruct it. Our approach first determines variation of color-transition count at each angle (from -45° to +45°) and the angle of maximal variation is regarded as the skew angle. Then, a scanning-line model reconstructs the image. We test 100 color-printed document images of various kinds and get good results (93 succeed and 7 fail). The average processing time of A4 size image is 2.76 seconds and the reconstruction time is 3.97 seconds on a Pentium III 733 PC.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D02B07B</s0>
</fC02>
<fC02 i1="02" i2="X"><s0>001D02B03</s0>
</fC02>
<fC02 i1="03" i2="X"><s0>001D02B12</s0>
</fC02>
<fC02 i1="04" i2="3"><s0>001B40B</s0>
</fC02>
<fC02 i1="05" i2="X"><s0>001A02I01</s0>
</fC02>
<fC03 i1="01" i2="1" l="ENG"><s0>Color printed document image</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="02" i2="1" l="ENG"><s0>Skew detection</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="03" i2="1" l="ENG"><s0>Color transition count</s0>
<s4>INC</s4>
</fC03>
<fC03 i1="04" i2="1" l="FRE"><s0>Théorie</s0>
</fC03>
<fC03 i1="04" i2="1" l="ENG"><s0>Theory</s0>
</fC03>
<fC03 i1="05" i2="1" l="FRE"><s0>Traitement image couleur</s0>
</fC03>
<fC03 i1="05" i2="1" l="ENG"><s0>Color image processing</s0>
</fC03>
<fC03 i1="06" i2="1" l="FRE"><s0>Algorithme</s0>
</fC03>
<fC03 i1="06" i2="1" l="ENG"><s0>Algorithms</s0>
</fC03>
<fC03 i1="07" i2="1" l="FRE"><s0>Reconnaissance optique caractère</s0>
</fC03>
<fC03 i1="07" i2="1" l="ENG"><s0>Optical character recognition</s0>
</fC03>
<fC03 i1="08" i2="1" l="FRE"><s0>Logiciel</s0>
</fC03>
<fC03 i1="08" i2="1" l="ENG"><s0>Computer software</s0>
</fC03>
<fC03 i1="09" i2="1" l="FRE"><s0>Couleur</s0>
</fC03>
<fC03 i1="09" i2="1" l="ENG"><s0>Color</s0>
</fC03>
<fC03 i1="10" i2="1" l="FRE"><s0>Modèle mathématique</s0>
</fC03>
<fC03 i1="10" i2="1" l="ENG"><s0>Mathematical models</s0>
</fC03>
<fC03 i1="11" i2="1" l="FRE"><s0>Méthode numérique</s0>
</fC03>
<fC03 i1="11" i2="1" l="ENG"><s0>Numerical methods</s0>
</fC03>
<fC03 i1="12" i2="1" l="FRE"><s0>Reconstruction image</s0>
<s3>P</s3>
</fC03>
<fC03 i1="12" i2="1" l="ENG"><s0>Image reconstruction</s0>
<s3>P</s3>
</fC03>
<fN21><s1>014</s1>
</fN21>
</pA>
</standard>
<server><NO>PASCAL 02-0026829 EI</NO>
<ET>Skew detection and reconstruction of color-printed document images</ET>
<AU>CHEN (Y. K.); WANG (J. F.)</AU>
<AF>Institute of Information Engineering National Cheng Kung University/Tainan/Taïwan (1 aut.)</AF>
<DT>Publication en série; Niveau analytique</DT>
<SO>IEICE Transactions on Information and Systems; ISSN 0916-8532; Coden ITISEF; Japon; Da. 2001; Vol. v E84-D; No. 8; Pp. 1018-1024; Bibl. 23 Refs.</SO>
<LA>Anglais</LA>
<EA>Large amounts of color-printed documents are published now everyday. Some OCR approaches of color-printed document images are provided, but they cannot normally work if the input images skew. In the past years, many algorithms are provided to detect the skew of monochrome document images but none of them process color-printed document images. All of these methods assume that text is printed in black on a white background and cannot be applied to detect skew in color-printed document images. In this paper, we propose an algorithm to detect the skew angle of a color-printed document image and reconstruct it. Our approach first determines variation of color-transition count at each angle (from -45° to +45°) and the angle of maximal variation is regarded as the skew angle. Then, a scanning-line model reconstructs the image. We test 100 color-printed document images of various kinds and get good results (93 succeed and 7 fail). The average processing time of A4 size image is 2.76 seconds and the reconstruction time is 3.97 seconds on a Pentium III 733 PC.</EA>
<CC>001D02B07B; 001D02B03; 001D02B12; 001B40B; 001A02I01</CC>
<FD>Théorie; Traitement image couleur; Algorithme; Reconnaissance optique caractère; Logiciel; Couleur; Modèle mathématique; Méthode numérique; Reconstruction image</FD>
<ED>Color printed document image; Skew detection; Color transition count; Theory; Color image processing; Algorithms; Optical character recognition; Computer software; Color; Mathematical models; Numerical methods; Image reconstruction</ED>
<LO>INIST-XXXX</LO>
<ID>02-0026829</ID>
</server>
</inist>
</record>

Pour manipuler ce document sous Unix (Dilib)

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

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000695 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000695 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Ticri/CIDE
   |area=    OcrV1
   |flux=    PascalFrancis
   |étape=   Corpus
   |type=    RBID
   |clé=     Pascal:02-0026829
   |texte=   Skew detection and reconstruction of color-printed document 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

Skew detection and reconstruction of color-printed document images

Skew detection and reconstruction of color-printed document images

Source :

Descripteurs français

English descriptors

Abstract

Notice en format standard (ISO 2709)

Format Inist (serveur)

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