OcrV1, Main, Exploration, bibRecord, 000767

Skew detection in document images based on rectangular active contour

Identifieur interne : 000767 ( Main/Exploration ); précédent : 000766; suivant : 000768

Skew detection in document images based on rectangular active contour

Auteurs : HUIJIE FAN [République populaire de Chine] ; LINLIN ZHU [République populaire de Chine] ; YANDONG TANG [République populaire de Chine]

Source :

International journal on document analysis and recognition : (Print) [ 1433-2833 ] ; 2010.

RBID : Pascal:11-0227816

Descripteurs français

Pascal (Inist)
- Détecteur image, Détection contour, Vision ordinateur, Reconnaissance optique caractère, Reconnaissance caractère, Analyse documentaire, Analyse image, Traitement image, Angle rotation, Forme rectangulaire, Courbe niveau, Type document, Structure tableau, Analyse automatique, Modélisation, Robustesse, ., Segmentation image.

English descriptors

KwdEn :
- Automatic analysis, Character recognition, Computer vision, Contour line, Document analysis, Document types, Edge detection, Image analysis, Image processing, Image segmentation, Image sensor, Modeling, Optical character recognition, Rectangular shape, Robustness, Rotation angle, Table layout.

Abstract

The digitalization processes of documents produce frequently images with small rotation angles. The skew angles in document images degrade the performance of optical character recognition (OCR) tools. Therefore, skew detection of document images plays an important role in automatic document analysis systems. In this paper, we propose a Rectangular Active Contour Model (RAC Model) for content region detection and skew angle calculation by imposing a rectangular shape constraint on the zero-level set in Chan-Vese Model (C-V Model) according to the rectangular feature of content regions in document images. Our algorithm differs from other skew detection methods in that it does not rely on local image features. Instead, it uses global image features and shape constraint to obtain a strong robustness in detecting skew angles of document images. We experimented on different types of document images. Comparing the results with other skew detection algorithms, our algorithm is more accurate in detecting the skews of the complex document images with different fonts, tables, illustrations, and layouts. We do not need to pre-process the original image, even if it is noisy, and at the same time the rectangular content region of a document image is also detected.

Affiliations:

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

to stream PascalFrancis, to step Corpus: 000142
to stream PascalFrancis, to step Curation: 000631
to stream PascalFrancis, to step Checkpoint: 000141
to stream Main, to step Merge: 000772
to stream Main, to step Curation: 000767

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Skew detection in document images based on rectangular active contour</title>
<author><name sortKey="Huijie Fan" sort="Huijie Fan" uniqKey="Huijie Fan" last="Huijie Fan">HUIJIE FAN</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Science</s1>
<s2>110016 Shenyang</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>110016 Shenyang</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Graduate University of the Chinese Academy of Science</s1>
<s2>100049 Beijing</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<placeName><settlement type="city">Pékin</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Linlin Zhu" sort="Linlin Zhu" uniqKey="Linlin Zhu" last="Linlin Zhu">LINLIN ZHU</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Science</s1>
<s2>110016 Shenyang</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>110016 Shenyang</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Graduate University of the Chinese Academy of Science</s1>
<s2>100049 Beijing</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<placeName><settlement type="city">Pékin</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Yandong Tang" sort="Yandong Tang" uniqKey="Yandong Tang" last="Yandong Tang">YANDONG TANG</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Science</s1>
<s2>110016 Shenyang</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>110016 Shenyang</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">11-0227816</idno>
<date when="2010">2010</date>
<idno type="stanalyst">PASCAL 11-0227816 INIST</idno>
<idno type="RBID">Pascal:11-0227816</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000142</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000631</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000141</idno>
<idno type="wicri:doubleKey">1433-2833:2010:Huijie Fan:skew:detection:in</idno>
<idno type="wicri:Area/Main/Merge">000772</idno>
<idno type="wicri:Area/Main/Curation">000767</idno>
<idno type="wicri:Area/Main/Exploration">000767</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Skew detection in document images based on rectangular active contour</title>
<author><name sortKey="Huijie Fan" sort="Huijie Fan" uniqKey="Huijie Fan" last="Huijie Fan">HUIJIE FAN</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Science</s1>
<s2>110016 Shenyang</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>110016 Shenyang</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Graduate University of the Chinese Academy of Science</s1>
<s2>100049 Beijing</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<placeName><settlement type="city">Pékin</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Linlin Zhu" sort="Linlin Zhu" uniqKey="Linlin Zhu" last="Linlin Zhu">LINLIN ZHU</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Science</s1>
<s2>110016 Shenyang</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>110016 Shenyang</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Graduate University of the Chinese Academy of Science</s1>
<s2>100049 Beijing</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<placeName><settlement type="city">Pékin</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Yandong Tang" sort="Yandong Tang" uniqKey="Yandong Tang" last="Yandong Tang">YANDONG TANG</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Science</s1>
<s2>110016 Shenyang</s2>
<s3>CHN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>République populaire de Chine</country>
<wicri:noRegion>110016 Shenyang</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">International journal on document analysis and recognition : (Print)</title>
<title level="j" type="abbreviated">Int. j. doc. anal. recognit. : (Print)</title>
<idno type="ISSN">1433-2833</idno>
<imprint><date when="2010">2010</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">International journal on document analysis and recognition : (Print)</title>
<title level="j" type="abbreviated">Int. j. doc. anal. recognit. : (Print)</title>
<idno type="ISSN">1433-2833</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Automatic analysis</term>
<term>Character recognition</term>
<term>Computer vision</term>
<term>Contour line</term>
<term>Document analysis</term>
<term>Document types</term>
<term>Edge detection</term>
<term>Image analysis</term>
<term>Image processing</term>
<term>Image segmentation</term>
<term>Image sensor</term>
<term>Modeling</term>
<term>Optical character recognition</term>
<term>Rectangular shape</term>
<term>Robustness</term>
<term>Rotation angle</term>
<term>Table layout</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Détecteur image</term>
<term>Détection contour</term>
<term>Vision ordinateur</term>
<term>Reconnaissance optique caractère</term>
<term>Reconnaissance caractère</term>
<term>Analyse documentaire</term>
<term>Analyse image</term>
<term>Traitement image</term>
<term>Angle rotation</term>
<term>Forme rectangulaire</term>
<term>Courbe niveau</term>
<term>Type document</term>
<term>Structure tableau</term>
<term>Analyse automatique</term>
<term>Modélisation</term>
<term>Robustesse</term>
<term>.</term>
<term>Segmentation image</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">The digitalization processes of documents produce frequently images with small rotation angles. The skew angles in document images degrade the performance of optical character recognition (OCR) tools. Therefore, skew detection of document images plays an important role in automatic document analysis systems. In this paper, we propose a Rectangular Active Contour Model (RAC Model) for content region detection and skew angle calculation by imposing a rectangular shape constraint on the zero-level set in Chan-Vese Model (C-V Model) according to the rectangular feature of content regions in document images. Our algorithm differs from other skew detection methods in that it does not rely on local image features. Instead, it uses global image features and shape constraint to obtain a strong robustness in detecting skew angles of document images. We experimented on different types of document images. Comparing the results with other skew detection algorithms, our algorithm is more accurate in detecting the skews of the complex document images with different fonts, tables, illustrations, and layouts. We do not need to pre-process the original image, even if it is noisy, and at the same time the rectangular content region of a document image is also detected.</div>
</front>
</TEI>
<affiliations><list><country><li>République populaire de Chine</li>
</country>
<settlement><li>Pékin</li>
</settlement>
</list>
<tree><country name="République populaire de Chine"><noRegion><name sortKey="Huijie Fan" sort="Huijie Fan" uniqKey="Huijie Fan" last="Huijie Fan">HUIJIE FAN</name>
</noRegion>
<name sortKey="Huijie Fan" sort="Huijie Fan" uniqKey="Huijie Fan" last="Huijie Fan">HUIJIE FAN</name>
<name sortKey="Linlin Zhu" sort="Linlin Zhu" uniqKey="Linlin Zhu" last="Linlin Zhu">LINLIN ZHU</name>
<name sortKey="Linlin Zhu" sort="Linlin Zhu" uniqKey="Linlin Zhu" last="Linlin Zhu">LINLIN ZHU</name>
<name sortKey="Yandong Tang" sort="Yandong Tang" uniqKey="Yandong Tang" last="Yandong Tang">YANDONG TANG</name>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000767 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000767 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Ticri/CIDE
   |area=    OcrV1
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     Pascal:11-0227816
   |texte=   Skew detection in document images based on rectangular active contour
}}

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 in document images based on rectangular active contour

Skew detection in document images based on rectangular active contour

Source :

Descripteurs français

English descriptors

Abstract

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

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri