OcrV1, Main, Exploration, bibRecord, 000791

Complex documents images segmentation based on steerable pyramid features

Identifieur interne : 000791 ( Main/Exploration ); précédent : 000790; suivant : 000792

Complex documents images segmentation based on steerable pyramid features

Auteurs : Mohamed Benjelil [France] ; Slim Kanoun [Tunisie] ; Rémy Mullot [France] ; Adel M. Alimi [Tunisie]

Source :

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

RBID : Pascal:11-0227897

Descripteurs français

Pascal (Inist)
- Traitement document, Traitement image, Classification, Analyse documentaire, Reconnaissance caractère, Reconnaissance optique caractère, Système complexe, Texte, Caractère manuscrit, Représentation graphique, Image multiple, Banque image, Présentation document, Décomposition sous bande, Multilinguisme, Structure document, Document officiel, Extraction forme, Invariant, Analyse multirésolution, Segmentation image.
Wicri :
- topic : Classification, Multilinguisme, Document officiel.

English descriptors

KwdEn :
- Character recognition, Classification, Complex system, Document analysis, Document layout, Document processing, Document structure, Graphics, Image databank, Image processing, Image segmentation, Invariant, Manuscript character, Multilingualism, Multiple image, Multiresolution analysis, Official document, Optical character recognition, Pattern extraction, Subband decomposition, Text.

Abstract

Page segmentation and classification is very important in document layout analysis system before it is presented to an OCR system or for any other subsequent processing steps. In this paper, we propose an accurate and suitably designed system for complex documents segmentation. This system is based on steerable pyramid transform. The features extracted from pyramid sub-bands serve to locate and classify regions into text (either machine-printed or handwritten) and non-text (images, graphics, drawings or paintings) in some noise-infected, deformed, multilingual, multi-script document images. These documents contain tabular structures, logos, stamps, handwritten script blocks, photographs, etc. The encouraging and promising results obtained on 1,000 official complex document images data set are presented in this research paper. We compared our results with those from existing state-of-the-art methods. This comparison shows that the proposed method performs consistently well on large sets of complex document images.

Affiliations:

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

to stream PascalFrancis, to step Corpus: 000140
to stream PascalFrancis, to step Curation: 000633
to stream PascalFrancis, to step Checkpoint: 000165
to stream Main, to step Merge: 000796
to stream Main, to step Curation: 000791

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Complex documents images segmentation based on steerable pyramid features</title>
<author><name sortKey="Benjelil, Mohamed" sort="Benjelil, Mohamed" uniqKey="Benjelil M" first="Mohamed" last="Benjelil">Mohamed Benjelil</name>
<affiliation wicri:level="3"><inist:fA14 i1="02"><s1>L3I, University of La Rochelle, Avenue Michel Crépeau</s1>
<s2>17042 La Rochelle</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Aquitaine-Limousin-Poitou-Charentes</region>
<region type="old region" nuts="2">Poitou-Charentes</region>
<settlement type="city">La Rochelle</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Kanoun, Slim" sort="Kanoun, Slim" uniqKey="Kanoun S" first="Slim" last="Kanoun">Slim Kanoun</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>REGIM-ENIS, B.P 1173</s1>
<s2>3038 Sfax</s2>
<s3>TUN</s3>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Tunisie</country>
<wicri:noRegion>3038 Sfax</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Mullot, Remy" sort="Mullot, Remy" uniqKey="Mullot R" first="Rémy" last="Mullot">Rémy Mullot</name>
<affiliation wicri:level="3"><inist:fA14 i1="02"><s1>L3I, University of La Rochelle, Avenue Michel Crépeau</s1>
<s2>17042 La Rochelle</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Aquitaine-Limousin-Poitou-Charentes</region>
<region type="old region" nuts="2">Poitou-Charentes</region>
<settlement type="city">La Rochelle</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Alimi, Adel M" sort="Alimi, Adel M" uniqKey="Alimi A" first="Adel M." last="Alimi">Adel M. Alimi</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>REGIM-ENIS, B.P 1173</s1>
<s2>3038 Sfax</s2>
<s3>TUN</s3>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Tunisie</country>
<wicri:noRegion>3038 Sfax</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">11-0227897</idno>
<date when="2010">2010</date>
<idno type="stanalyst">PASCAL 11-0227897 INIST</idno>
<idno type="RBID">Pascal:11-0227897</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000140</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000633</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000165</idno>
<idno type="wicri:doubleKey">1433-2833:2010:Benjelil M:complex:documents:images</idno>
<idno type="wicri:Area/Main/Merge">000796</idno>
<idno type="wicri:Area/Main/Curation">000791</idno>
<idno type="wicri:Area/Main/Exploration">000791</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Complex documents images segmentation based on steerable pyramid features</title>
<author><name sortKey="Benjelil, Mohamed" sort="Benjelil, Mohamed" uniqKey="Benjelil M" first="Mohamed" last="Benjelil">Mohamed Benjelil</name>
<affiliation wicri:level="3"><inist:fA14 i1="02"><s1>L3I, University of La Rochelle, Avenue Michel Crépeau</s1>
<s2>17042 La Rochelle</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Aquitaine-Limousin-Poitou-Charentes</region>
<region type="old region" nuts="2">Poitou-Charentes</region>
<settlement type="city">La Rochelle</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Kanoun, Slim" sort="Kanoun, Slim" uniqKey="Kanoun S" first="Slim" last="Kanoun">Slim Kanoun</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>REGIM-ENIS, B.P 1173</s1>
<s2>3038 Sfax</s2>
<s3>TUN</s3>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Tunisie</country>
<wicri:noRegion>3038 Sfax</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Mullot, Remy" sort="Mullot, Remy" uniqKey="Mullot R" first="Rémy" last="Mullot">Rémy Mullot</name>
<affiliation wicri:level="3"><inist:fA14 i1="02"><s1>L3I, University of La Rochelle, Avenue Michel Crépeau</s1>
<s2>17042 La Rochelle</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><region type="region" nuts="2">Aquitaine-Limousin-Poitou-Charentes</region>
<region type="old region" nuts="2">Poitou-Charentes</region>
<settlement type="city">La Rochelle</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Alimi, Adel M" sort="Alimi, Adel M" uniqKey="Alimi A" first="Adel M." last="Alimi">Adel M. Alimi</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>REGIM-ENIS, B.P 1173</s1>
<s2>3038 Sfax</s2>
<s3>TUN</s3>
<sZ>2 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Tunisie</country>
<wicri:noRegion>3038 Sfax</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>Character recognition</term>
<term>Classification</term>
<term>Complex system</term>
<term>Document analysis</term>
<term>Document layout</term>
<term>Document processing</term>
<term>Document structure</term>
<term>Graphics</term>
<term>Image databank</term>
<term>Image processing</term>
<term>Image segmentation</term>
<term>Invariant</term>
<term>Manuscript character</term>
<term>Multilingualism</term>
<term>Multiple image</term>
<term>Multiresolution analysis</term>
<term>Official document</term>
<term>Optical character recognition</term>
<term>Pattern extraction</term>
<term>Subband decomposition</term>
<term>Text</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Traitement document</term>
<term>Traitement image</term>
<term>Classification</term>
<term>Analyse documentaire</term>
<term>Reconnaissance caractère</term>
<term>Reconnaissance optique caractère</term>
<term>Système complexe</term>
<term>Texte</term>
<term>Caractère manuscrit</term>
<term>Représentation graphique</term>
<term>Image multiple</term>
<term>Banque image</term>
<term>Présentation document</term>
<term>Décomposition sous bande</term>
<term>Multilinguisme</term>
<term>Structure document</term>
<term>Document officiel</term>
<term>Extraction forme</term>
<term>Invariant</term>
<term>Analyse multirésolution</term>
<term>Segmentation image</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Classification</term>
<term>Multilinguisme</term>
<term>Document officiel</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Page segmentation and classification is very important in document layout analysis system before it is presented to an OCR system or for any other subsequent processing steps. In this paper, we propose an accurate and suitably designed system for complex documents segmentation. This system is based on steerable pyramid transform. The features extracted from pyramid sub-bands serve to locate and classify regions into text (either machine-printed or handwritten) and non-text (images, graphics, drawings or paintings) in some noise-infected, deformed, multilingual, multi-script document images. These documents contain tabular structures, logos, stamps, handwritten script blocks, photographs, etc. The encouraging and promising results obtained on 1,000 official complex document images data set are presented in this research paper. We compared our results with those from existing state-of-the-art methods. This comparison shows that the proposed method performs consistently well on large sets of complex document images.</div>
</front>
</TEI>
<affiliations><list><country><li>France</li>
<li>Tunisie</li>
</country>
<region><li>Aquitaine-Limousin-Poitou-Charentes</li>
<li>Poitou-Charentes</li>
</region>
<settlement><li>La Rochelle</li>
</settlement>
</list>
<tree><country name="France"><region name="Aquitaine-Limousin-Poitou-Charentes"><name sortKey="Benjelil, Mohamed" sort="Benjelil, Mohamed" uniqKey="Benjelil M" first="Mohamed" last="Benjelil">Mohamed Benjelil</name>
</region>
<name sortKey="Mullot, Remy" sort="Mullot, Remy" uniqKey="Mullot R" first="Rémy" last="Mullot">Rémy Mullot</name>
</country>
<country name="Tunisie"><noRegion><name sortKey="Kanoun, Slim" sort="Kanoun, Slim" uniqKey="Kanoun S" first="Slim" last="Kanoun">Slim Kanoun</name>
</noRegion>
<name sortKey="Alimi, Adel M" sort="Alimi, Adel M" uniqKey="Alimi A" first="Adel M." last="Alimi">Adel M. Alimi</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 000791 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000791 | 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:11-0227897
   |texte=   Complex documents images segmentation based on steerable pyramid features
}}

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

Complex documents images segmentation based on steerable pyramid features

Complex documents images segmentation based on steerable pyramid features

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