Corpus
PascalFrancis
Racine
Corpus
Checkpoint
PascalFrancis
Racine
PascalFrancis
Exploration
Accueil
Racine
Racine

Serveur d'exploration sur la recherche en informatique en Lorraine

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.

A general approach for multi-oriented text line extraction of handwritten documents

Identifieur interne : 000090 ( PascalFrancis/Corpus ); précédent : 000089; suivant : 000091

A general approach for multi-oriented text line extraction of handwritten documents

Auteurs : Nazih Ouwayed ; Abdel Belaïd

Source :

RBID : Pascal:13-0072755

Descripteurs français

English descriptors

Abstract

The multi-orientation occurs frequently in ancient handwritten documents, where the writers try to update a document by adding some annotations in the margins. Due to the margin narrowness, this gives rise to lines in different directions and orientations. Document recognition needs to find the lines everywhere they are written whatever their orientation. This is why we propose in this paper a new approach allowing us to extract the multi-oriented lines in scanned documents. Because of the multi-orientation of lines and their dispersion in the page, we use an image meshing allowing us to progressively and locally determine the lines. Once the meshing is established, the orientation is determined using the Wigner-Ville distribution on the projection histogram profile. This local orientation is then enlarged to limit the orientation in the neighborhood. Afterward, the text lines are extracted locally in each zone basing on the follow-up of the orientation lines and the proximity of connected components. Finally, the connected components that overlap and touch in adjacent lines are separated. The morphology analysis of the terminal letters of Arabic words is here considered. The proposed approach has been experimented on 100 documents reaching an accuracy of about 98.6%.

Notice en format standard (ISO 2709)

Pour connaître la documentation sur le format Inist Standard.

pA  
A01 01  1    @0 1433-2833
A03   1    @0 Int. j. doc. anal. recognit. : (Print)
A05       @2 15
A06       @2 4
A08 01  1  ENG  @1 A general approach for multi-oriented text line extraction of handwritten documents
A11 01  1    @1 OUWAYED (Nazih)
A11 02  1    @1 BELAÏD (Abdel)
A14 01      @1 LORIA, University Nancy 2 @2 Vandoeuvre-Les-Nancy @3 FRA @Z 1 aut. @Z 2 aut.
A20       @1 297-314
A21       @1 2012
A23 01      @0 ENG
A43 01      @1 INIST @2 26790 @5 354000505430660020
A44       @0 0000 @1 © 2013 INIST-CNRS. All rights reserved.
A45       @0 48 ref.
A47 01  1    @0 13-0072755
A60       @1 P
A61       @0 A
A64 01  1    @0 International journal on document analysis and recognition : (Print)
A66 01      @0 DEU
C01 01    ENG  @0 The multi-orientation occurs frequently in ancient handwritten documents, where the writers try to update a document by adding some annotations in the margins. Due to the margin narrowness, this gives rise to lines in different directions and orientations. Document recognition needs to find the lines everywhere they are written whatever their orientation. This is why we propose in this paper a new approach allowing us to extract the multi-oriented lines in scanned documents. Because of the multi-orientation of lines and their dispersion in the page, we use an image meshing allowing us to progressively and locally determine the lines. Once the meshing is established, the orientation is determined using the Wigner-Ville distribution on the projection histogram profile. This local orientation is then enlarged to limit the orientation in the neighborhood. Afterward, the text lines are extracted locally in each zone basing on the follow-up of the orientation lines and the proximity of connected components. Finally, the connected components that overlap and touch in adjacent lines are separated. The morphology analysis of the terminal letters of Arabic words is here considered. The proposed approach has been experimented on 100 documents reaching an accuracy of about 98.6%.
C02 01  X    @0 001D02C03
C03 01  X  FRE  @0 Extraction information @5 06
C03 01  X  ENG  @0 Information extraction @5 06
C03 01  X  SPA  @0 Extracción información @5 06
C03 02  X  FRE  @0 Texte @5 07
C03 02  X  ENG  @0 Text @5 07
C03 02  X  SPA  @0 Texto @5 07
C03 03  X  FRE  @0 Caractère manuscrit @5 08
C03 03  X  ENG  @0 Manuscript character @5 08
C03 03  X  SPA  @0 Carácter manuscrito @5 08
C03 04  X  FRE  @0 Mise à jour @5 09
C03 04  X  ENG  @0 Updating @5 09
C03 04  X  SPA  @0 Actualización @5 09
C03 05  X  FRE  @0 Analyse documentaire @5 10
C03 05  X  ENG  @0 Document analysis @5 10
C03 05  X  SPA  @0 Análisis documental @5 10
C03 06  X  FRE  @0 Histogramme @5 11
C03 06  X  ENG  @0 Histogram @5 11
C03 06  X  SPA  @0 Histograma @5 11
C03 07  X  FRE  @0 Traitement document @5 12
C03 07  X  ENG  @0 Document processing @5 12
C03 07  X  SPA  @0 Tratamiento documento @5 12
C03 08  X  FRE  @0 Document manuscrit @5 18
C03 08  X  ENG  @0 Manuscript document @5 18
C03 08  X  SPA  @0 Documento manuscrito @5 18
C03 09  X  FRE  @0 Annotation @5 19
C03 09  X  ENG  @0 Annotation @5 19
C03 09  X  SPA  @0 Anotación @5 19
C03 10  X  FRE  @0 Morphologie @5 20
C03 10  X  ENG  @0 Morphology @5 20
C03 10  X  SPA  @0 Morfología @5 20
C03 11  X  FRE  @0 Terminal @5 21
C03 11  X  ENG  @0 Terminal @5 21
C03 11  X  SPA  @0 Terminal @5 21
C03 12  X  FRE  @0 Arabe @5 22
C03 12  X  ENG  @0 Arabic @5 22
C03 12  X  SPA  @0 Árabe @5 22
C03 13  X  FRE  @0 Extraction forme @5 23
C03 13  X  ENG  @0 Pattern extraction @5 23
C03 13  X  SPA  @0 Extracción forma @5 23
C03 14  X  FRE  @0 Proximité @5 24
C03 14  X  ENG  @0 Proximity @5 24
C03 14  X  SPA  @0 Proximidad @5 24
C03 15  X  FRE  @0 Recouvrement @5 25
C03 15  X  ENG  @0 Overlay @5 25
C03 15  X  SPA  @0 Recubrimiento @5 25
C03 16  X  FRE  @0 . @4 INC @5 82
C03 17  X  FRE  @0 Traitement image document @4 CD @5 96
C03 17  X  ENG  @0 Document image processing @4 CD @5 96
C03 17  X  SPA  @0 Tratamiento de imágenes de documentos @4 CD @5 96
C03 18  X  FRE  @0 Segmentation image @4 CD @5 97
C03 18  X  ENG  @0 Image segmentation @4 CD @5 97
C03 18  X  SPA  @0 Segmentación de imágenes @4 CD @5 97
N21       @1 042
N44 01      @1 OTO
N82       @1 OTO

Format Inist (serveur)

NO : PASCAL 13-0072755 INIST
ET : A general approach for multi-oriented text line extraction of handwritten documents
AU : OUWAYED (Nazih); BELAÏD (Abdel)
AF : LORIA, University Nancy 2/Vandoeuvre-Les-Nancy/France (1 aut., 2 aut.)
DT : Publication en série; Niveau analytique
SO : International journal on document analysis and recognition : (Print); ISSN 1433-2833; Allemagne; Da. 2012; Vol. 15; No. 4; Pp. 297-314; Bibl. 48 ref.
LA : Anglais
EA : The multi-orientation occurs frequently in ancient handwritten documents, where the writers try to update a document by adding some annotations in the margins. Due to the margin narrowness, this gives rise to lines in different directions and orientations. Document recognition needs to find the lines everywhere they are written whatever their orientation. This is why we propose in this paper a new approach allowing us to extract the multi-oriented lines in scanned documents. Because of the multi-orientation of lines and their dispersion in the page, we use an image meshing allowing us to progressively and locally determine the lines. Once the meshing is established, the orientation is determined using the Wigner-Ville distribution on the projection histogram profile. This local orientation is then enlarged to limit the orientation in the neighborhood. Afterward, the text lines are extracted locally in each zone basing on the follow-up of the orientation lines and the proximity of connected components. Finally, the connected components that overlap and touch in adjacent lines are separated. The morphology analysis of the terminal letters of Arabic words is here considered. The proposed approach has been experimented on 100 documents reaching an accuracy of about 98.6%.
CC : 001D02C03
FD : Extraction information; Texte; Caractère manuscrit; Mise à jour; Analyse documentaire; Histogramme; Traitement document; Document manuscrit; Annotation; Morphologie; Terminal; Arabe; Extraction forme; Proximité; Recouvrement; .; Traitement image document; Segmentation image
ED : Information extraction; Text; Manuscript character; Updating; Document analysis; Histogram; Document processing; Manuscript document; Annotation; Morphology; Terminal; Arabic; Pattern extraction; Proximity; Overlay; Document image processing; Image segmentation
SD : Extracción información; Texto; Carácter manuscrito; Actualización; Análisis documental; Histograma; Tratamiento documento; Documento manuscrito; Anotación; Morfología; Terminal; Árabe; Extracción forma; Proximidad; Recubrimiento; Tratamiento de imágenes de documentos; Segmentación de imágenes
LO : INIST-26790.354000505430660020
ID : 13-0072755

Links to Exploration step

Pascal:13-0072755

Le document en format XML

<record>
<TEI>
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="en" level="a">A general approach for multi-oriented text line extraction of handwritten documents</title>
<author>
<name sortKey="Ouwayed, Nazih" sort="Ouwayed, Nazih" uniqKey="Ouwayed N" first="Nazih" last="Ouwayed">Nazih Ouwayed</name>
<affiliation>
<inist:fA14 i1="01">
<s1>LORIA, University Nancy 2</s1>
<s2>Vandoeuvre-Les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author>
<name sortKey="Belaid, Abdel" sort="Belaid, Abdel" uniqKey="Belaid A" first="Abdel" last="Belaïd">Abdel Belaïd</name>
<affiliation>
<inist:fA14 i1="01">
<s1>LORIA, University Nancy 2</s1>
<s2>Vandoeuvre-Les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt>
<idno type="wicri:source">INIST</idno>
<idno type="inist">13-0072755</idno>
<date when="2012">2012</date>
<idno type="stanalyst">PASCAL 13-0072755 INIST</idno>
<idno type="RBID">Pascal:13-0072755</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000090</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title xml:lang="en" level="a">A general approach for multi-oriented text line extraction of handwritten documents</title>
<author>
<name sortKey="Ouwayed, Nazih" sort="Ouwayed, Nazih" uniqKey="Ouwayed N" first="Nazih" last="Ouwayed">Nazih Ouwayed</name>
<affiliation>
<inist:fA14 i1="01">
<s1>LORIA, University Nancy 2</s1>
<s2>Vandoeuvre-Les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
<author>
<name sortKey="Belaid, Abdel" sort="Belaid, Abdel" uniqKey="Belaid A" first="Abdel" last="Belaïd">Abdel Belaïd</name>
<affiliation>
<inist:fA14 i1="01">
<s1>LORIA, University Nancy 2</s1>
<s2>Vandoeuvre-Les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
</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="2012">2012</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>Annotation</term>
<term>Arabic</term>
<term>Document analysis</term>
<term>Document image processing</term>
<term>Document processing</term>
<term>Histogram</term>
<term>Image segmentation</term>
<term>Information extraction</term>
<term>Manuscript character</term>
<term>Manuscript document</term>
<term>Morphology</term>
<term>Overlay</term>
<term>Pattern extraction</term>
<term>Proximity</term>
<term>Terminal</term>
<term>Text</term>
<term>Updating</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr">
<term>Extraction information</term>
<term>Texte</term>
<term>Caractère manuscrit</term>
<term>Mise à jour</term>
<term>Analyse documentaire</term>
<term>Histogramme</term>
<term>Traitement document</term>
<term>Document manuscrit</term>
<term>Annotation</term>
<term>Morphologie</term>
<term>Terminal</term>
<term>Arabe</term>
<term>Extraction forme</term>
<term>Proximité</term>
<term>Recouvrement</term>
<term>.</term>
<term>Traitement image document</term>
<term>Segmentation image</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en">The multi-orientation occurs frequently in ancient handwritten documents, where the writers try to update a document by adding some annotations in the margins. Due to the margin narrowness, this gives rise to lines in different directions and orientations. Document recognition needs to find the lines everywhere they are written whatever their orientation. This is why we propose in this paper a new approach allowing us to extract the multi-oriented lines in scanned documents. Because of the multi-orientation of lines and their dispersion in the page, we use an image meshing allowing us to progressively and locally determine the lines. Once the meshing is established, the orientation is determined using the Wigner-Ville distribution on the projection histogram profile. This local orientation is then enlarged to limit the orientation in the neighborhood. Afterward, the text lines are extracted locally in each zone basing on the follow-up of the orientation lines and the proximity of connected components. Finally, the connected components that overlap and touch in adjacent lines are separated. The morphology analysis of the terminal letters of Arabic words is here considered. The proposed approach has been experimented on 100 documents reaching an accuracy of about 98.6%.</div>
</front>
</TEI>
<inist>
<standard h6="B">
<pA>
<fA01 i1="01" i2="1">
<s0>1433-2833</s0>
</fA01>
<fA03 i2="1">
<s0>Int. j. doc. anal. recognit. : (Print)</s0>
</fA03>
<fA05>
<s2>15</s2>
</fA05>
<fA06>
<s2>4</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG">
<s1>A general approach for multi-oriented text line extraction of handwritten documents</s1>
</fA08>
<fA11 i1="01" i2="1">
<s1>OUWAYED (Nazih)</s1>
</fA11>
<fA11 i1="02" i2="1">
<s1>BELAÏD (Abdel)</s1>
</fA11>
<fA14 i1="01">
<s1>LORIA, University Nancy 2</s1>
<s2>Vandoeuvre-Les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</fA14>
<fA20>
<s1>297-314</s1>
</fA20>
<fA21>
<s1>2012</s1>
</fA21>
<fA23 i1="01">
<s0>ENG</s0>
</fA23>
<fA43 i1="01">
<s1>INIST</s1>
<s2>26790</s2>
<s5>354000505430660020</s5>
</fA43>
<fA44>
<s0>0000</s0>
<s1>© 2013 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45>
<s0>48 ref.</s0>
</fA45>
<fA47 i1="01" i2="1">
<s0>13-0072755</s0>
</fA47>
<fA60>
<s1>P</s1>
</fA60>
<fA61>
<s0>A</s0>
</fA61>
<fA64 i1="01" i2="1">
<s0>International journal on document analysis and recognition : (Print)</s0>
</fA64>
<fA66 i1="01">
<s0>DEU</s0>
</fA66>
<fC01 i1="01" l="ENG">
<s0>The multi-orientation occurs frequently in ancient handwritten documents, where the writers try to update a document by adding some annotations in the margins. Due to the margin narrowness, this gives rise to lines in different directions and orientations. Document recognition needs to find the lines everywhere they are written whatever their orientation. This is why we propose in this paper a new approach allowing us to extract the multi-oriented lines in scanned documents. Because of the multi-orientation of lines and their dispersion in the page, we use an image meshing allowing us to progressively and locally determine the lines. Once the meshing is established, the orientation is determined using the Wigner-Ville distribution on the projection histogram profile. This local orientation is then enlarged to limit the orientation in the neighborhood. Afterward, the text lines are extracted locally in each zone basing on the follow-up of the orientation lines and the proximity of connected components. Finally, the connected components that overlap and touch in adjacent lines are separated. The morphology analysis of the terminal letters of Arabic words is here considered. The proposed approach has been experimented on 100 documents reaching an accuracy of about 98.6%.</s0>
</fC01>
<fC02 i1="01" i2="X">
<s0>001D02C03</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE">
<s0>Extraction information</s0>
<s5>06</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG">
<s0>Information extraction</s0>
<s5>06</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA">
<s0>Extracción información</s0>
<s5>06</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE">
<s0>Texte</s0>
<s5>07</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG">
<s0>Text</s0>
<s5>07</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA">
<s0>Texto</s0>
<s5>07</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE">
<s0>Caractère manuscrit</s0>
<s5>08</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG">
<s0>Manuscript character</s0>
<s5>08</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA">
<s0>Carácter manuscrito</s0>
<s5>08</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE">
<s0>Mise à jour</s0>
<s5>09</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG">
<s0>Updating</s0>
<s5>09</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA">
<s0>Actualización</s0>
<s5>09</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE">
<s0>Analyse documentaire</s0>
<s5>10</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG">
<s0>Document analysis</s0>
<s5>10</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA">
<s0>Análisis documental</s0>
<s5>10</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE">
<s0>Histogramme</s0>
<s5>11</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG">
<s0>Histogram</s0>
<s5>11</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA">
<s0>Histograma</s0>
<s5>11</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE">
<s0>Traitement document</s0>
<s5>12</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG">
<s0>Document processing</s0>
<s5>12</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA">
<s0>Tratamiento documento</s0>
<s5>12</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE">
<s0>Document manuscrit</s0>
<s5>18</s5>
</fC03>
<fC03 i1="08" i2="X" l="ENG">
<s0>Manuscript document</s0>
<s5>18</s5>
</fC03>
<fC03 i1="08" i2="X" l="SPA">
<s0>Documento manuscrito</s0>
<s5>18</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE">
<s0>Annotation</s0>
<s5>19</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG">
<s0>Annotation</s0>
<s5>19</s5>
</fC03>
<fC03 i1="09" i2="X" l="SPA">
<s0>Anotación</s0>
<s5>19</s5>
</fC03>
<fC03 i1="10" i2="X" l="FRE">
<s0>Morphologie</s0>
<s5>20</s5>
</fC03>
<fC03 i1="10" i2="X" l="ENG">
<s0>Morphology</s0>
<s5>20</s5>
</fC03>
<fC03 i1="10" i2="X" l="SPA">
<s0>Morfología</s0>
<s5>20</s5>
</fC03>
<fC03 i1="11" i2="X" l="FRE">
<s0>Terminal</s0>
<s5>21</s5>
</fC03>
<fC03 i1="11" i2="X" l="ENG">
<s0>Terminal</s0>
<s5>21</s5>
</fC03>
<fC03 i1="11" i2="X" l="SPA">
<s0>Terminal</s0>
<s5>21</s5>
</fC03>
<fC03 i1="12" i2="X" l="FRE">
<s0>Arabe</s0>
<s5>22</s5>
</fC03>
<fC03 i1="12" i2="X" l="ENG">
<s0>Arabic</s0>
<s5>22</s5>
</fC03>
<fC03 i1="12" i2="X" l="SPA">
<s0>Árabe</s0>
<s5>22</s5>
</fC03>
<fC03 i1="13" i2="X" l="FRE">
<s0>Extraction forme</s0>
<s5>23</s5>
</fC03>
<fC03 i1="13" i2="X" l="ENG">
<s0>Pattern extraction</s0>
<s5>23</s5>
</fC03>
<fC03 i1="13" i2="X" l="SPA">
<s0>Extracción forma</s0>
<s5>23</s5>
</fC03>
<fC03 i1="14" i2="X" l="FRE">
<s0>Proximité</s0>
<s5>24</s5>
</fC03>
<fC03 i1="14" i2="X" l="ENG">
<s0>Proximity</s0>
<s5>24</s5>
</fC03>
<fC03 i1="14" i2="X" l="SPA">
<s0>Proximidad</s0>
<s5>24</s5>
</fC03>
<fC03 i1="15" i2="X" l="FRE">
<s0>Recouvrement</s0>
<s5>25</s5>
</fC03>
<fC03 i1="15" i2="X" l="ENG">
<s0>Overlay</s0>
<s5>25</s5>
</fC03>
<fC03 i1="15" i2="X" l="SPA">
<s0>Recubrimiento</s0>
<s5>25</s5>
</fC03>
<fC03 i1="16" i2="X" l="FRE">
<s0>.</s0>
<s4>INC</s4>
<s5>82</s5>
</fC03>
<fC03 i1="17" i2="X" l="FRE">
<s0>Traitement image document</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="17" i2="X" l="ENG">
<s0>Document image processing</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="17" i2="X" l="SPA">
<s0>Tratamiento de imágenes de documentos</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="18" i2="X" l="FRE">
<s0>Segmentation image</s0>
<s4>CD</s4>
<s5>97</s5>
</fC03>
<fC03 i1="18" i2="X" l="ENG">
<s0>Image segmentation</s0>
<s4>CD</s4>
<s5>97</s5>
</fC03>
<fC03 i1="18" i2="X" l="SPA">
<s0>Segmentación de imágenes</s0>
<s4>CD</s4>
<s5>97</s5>
</fC03>
<fN21>
<s1>042</s1>
</fN21>
<fN44 i1="01">
<s1>OTO</s1>
</fN44>
<fN82>
<s1>OTO</s1>
</fN82>
</pA>
</standard>
<server>
<NO>PASCAL 13-0072755 INIST</NO>
<ET>A general approach for multi-oriented text line extraction of handwritten documents</ET>
<AU>OUWAYED (Nazih); BELAÏD (Abdel)</AU>
<AF>LORIA, University Nancy 2/Vandoeuvre-Les-Nancy/France (1 aut., 2 aut.)</AF>
<DT>Publication en série; Niveau analytique</DT>
<SO>International journal on document analysis and recognition : (Print); ISSN 1433-2833; Allemagne; Da. 2012; Vol. 15; No. 4; Pp. 297-314; Bibl. 48 ref.</SO>
<LA>Anglais</LA>
<EA>The multi-orientation occurs frequently in ancient handwritten documents, where the writers try to update a document by adding some annotations in the margins. Due to the margin narrowness, this gives rise to lines in different directions and orientations. Document recognition needs to find the lines everywhere they are written whatever their orientation. This is why we propose in this paper a new approach allowing us to extract the multi-oriented lines in scanned documents. Because of the multi-orientation of lines and their dispersion in the page, we use an image meshing allowing us to progressively and locally determine the lines. Once the meshing is established, the orientation is determined using the Wigner-Ville distribution on the projection histogram profile. This local orientation is then enlarged to limit the orientation in the neighborhood. Afterward, the text lines are extracted locally in each zone basing on the follow-up of the orientation lines and the proximity of connected components. Finally, the connected components that overlap and touch in adjacent lines are separated. The morphology analysis of the terminal letters of Arabic words is here considered. The proposed approach has been experimented on 100 documents reaching an accuracy of about 98.6%.</EA>
<CC>001D02C03</CC>
<FD>Extraction information; Texte; Caractère manuscrit; Mise à jour; Analyse documentaire; Histogramme; Traitement document; Document manuscrit; Annotation; Morphologie; Terminal; Arabe; Extraction forme; Proximité; Recouvrement; .; Traitement image document; Segmentation image</FD>
<ED>Information extraction; Text; Manuscript character; Updating; Document analysis; Histogram; Document processing; Manuscript document; Annotation; Morphology; Terminal; Arabic; Pattern extraction; Proximity; Overlay; Document image processing; Image segmentation</ED>
<SD>Extracción información; Texto; Carácter manuscrito; Actualización; Análisis documental; Histograma; Tratamiento documento; Documento manuscrito; Anotación; Morfología; Terminal; Árabe; Extracción forma; Proximidad; Recubrimiento; Tratamiento de imágenes de documentos; Segmentación de imágenes</SD>
<LO>INIST-26790.354000505430660020</LO>
<ID>13-0072755</ID>
</server>
</inist>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/PascalFrancis/Corpus

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000090 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000090 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Lorraine
   |area=    InforLorV4
   |flux=    PascalFrancis
   |étape=   Corpus
   |type=    RBID
   |clé=     Pascal:13-0072755
   |texte=   A general approach for multi-oriented text line extraction of handwritten documents
}}
Wicri

This area was generated with Dilib version V0.6.33.
Data generation: Mon Jun 10 21:56:28 2019. Site generation: Fri Feb 25 15:29:27 2022