Recognition-Based Segmentation of Nom Characters from Body Text Regions of Stele Images Using Area Voronoi Diagram
Identifieur interne : 000920 ( Main/Exploration ); précédent : 000919; suivant : 000921Recognition-Based Segmentation of Nom Characters from Body Text Regions of Stele Images Using Area Voronoi Diagram
Auteurs : V. Hoang [Viêt Nam, France] ; Salvatore Tabbone [France] ; Ngoc-Yen Pham [Viêt Nam]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2009.
Abstract
Abstract: Segmentation of Nom characters from body text regions of stele images is a challenging problem due to the confusing spatial distribution of the connected components composing these characters. In this paper, for each vertical text line, area Voronoi diagram is employed to represent the neighborhood of the connected components and Voronoi edges are used as nonlinear segmentation hypotheses. Characters are then segmented by selecting appropriate adjacent Voronoi regions. For this purpose, we utilize the information about the horizontal overlap of connected components and the recognition distances of candidate characters provided by an OCR engine. Experimental results show that the proposed method is highly accurate and robust to various types of stele.
Url:
DOI: 10.1007/978-3-642-03767-2_25
Affiliations:
- France, Viêt Nam
- Alsace-Champagne-Ardenne-Lorraine, Lorraine
- Vandoeuvre-lès-Nancy
- Université Nancy 2
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000316
- to stream Istex, to step Curation: 000311
- to stream Istex, to step Checkpoint: 000442
- to stream Main, to step Merge: 000928
- to stream Main, to step Curation: 000920
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Recognition-Based Segmentation of Nom Characters from Body Text Regions of Stele Images Using Area Voronoi Diagram</title>
<author><name sortKey="Hoang, V" sort="Hoang, V" uniqKey="Hoang V" first="V." last="Hoang">V. Hoang</name>
</author>
<author><name sortKey="Tabbone, Salvatore" sort="Tabbone, Salvatore" uniqKey="Tabbone S" first="Salvatore" last="Tabbone">Salvatore Tabbone</name>
</author>
<author><name sortKey="Pham, Ngoc Yen" sort="Pham, Ngoc Yen" uniqKey="Pham N" first="Ngoc-Yen" last="Pham">Ngoc-Yen Pham</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:10ACEFF10D679878C336ED2CD736C58908395270</idno>
<date when="2009" year="2009">2009</date>
<idno type="doi">10.1007/978-3-642-03767-2_25</idno>
<idno type="url">https://api.istex.fr/document/10ACEFF10D679878C336ED2CD736C58908395270/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000316</idno>
<idno type="wicri:Area/Istex/Curation">000311</idno>
<idno type="wicri:Area/Istex/Checkpoint">000442</idno>
<idno type="wicri:doubleKey">0302-9743:2009:Hoang V:recognition:based:segmentation</idno>
<idno type="wicri:Area/Main/Merge">000928</idno>
<idno type="wicri:Area/Main/Curation">000920</idno>
<idno type="wicri:Area/Main/Exploration">000920</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Recognition-Based Segmentation of Nom Characters from Body Text Regions of Stele Images Using Area Voronoi Diagram</title>
<author><name sortKey="Hoang, V" sort="Hoang, V" uniqKey="Hoang V" first="V." last="Hoang">V. Hoang</name>
<affiliation wicri:level="1"><country xml:lang="fr">Viêt Nam</country>
<wicri:regionArea>MICA Research Center, Hanoi University of Technology, Hanoi</wicri:regionArea>
<wicri:noRegion>Hanoi</wicri:noRegion>
</affiliation>
<affiliation wicri:level="4"><country xml:lang="fr">France</country>
<wicri:regionArea>Université Nancy 2, LORIA, UMR 7503, 54506, Vandoeuvre-lès-Nancy</wicri:regionArea>
<placeName><region type="region" nuts="2">Alsace-Champagne-Ardenne-Lorraine</region>
<region type="old region" nuts="2">Lorraine</region>
<settlement type="city">Vandoeuvre-lès-Nancy</settlement>
</placeName>
<orgName type="university">Université Nancy 2</orgName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">France</country>
</affiliation>
</author>
<author><name sortKey="Tabbone, Salvatore" sort="Tabbone, Salvatore" uniqKey="Tabbone S" first="Salvatore" last="Tabbone">Salvatore Tabbone</name>
<affiliation wicri:level="4"><country xml:lang="fr">France</country>
<wicri:regionArea>Université Nancy 2, LORIA, UMR 7503, 54506, Vandoeuvre-lès-Nancy</wicri:regionArea>
<placeName><region type="region" nuts="2">Alsace-Champagne-Ardenne-Lorraine</region>
<region type="old region" nuts="2">Lorraine</region>
<settlement type="city">Vandoeuvre-lès-Nancy</settlement>
</placeName>
<orgName type="university">Université Nancy 2</orgName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">France</country>
</affiliation>
</author>
<author><name sortKey="Pham, Ngoc Yen" sort="Pham, Ngoc Yen" uniqKey="Pham N" first="Ngoc-Yen" last="Pham">Ngoc-Yen Pham</name>
<affiliation wicri:level="1"><country xml:lang="fr">Viêt Nam</country>
<wicri:regionArea>MICA Research Center, Hanoi University of Technology, Hanoi</wicri:regionArea>
<wicri:noRegion>Hanoi</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Viêt Nam</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2009</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">10ACEFF10D679878C336ED2CD736C58908395270</idno>
<idno type="DOI">10.1007/978-3-642-03767-2_25</idno>
<idno type="ChapterID">25</idno>
<idno type="ChapterID">Chap25</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Abstract: Segmentation of Nom characters from body text regions of stele images is a challenging problem due to the confusing spatial distribution of the connected components composing these characters. In this paper, for each vertical text line, area Voronoi diagram is employed to represent the neighborhood of the connected components and Voronoi edges are used as nonlinear segmentation hypotheses. Characters are then segmented by selecting appropriate adjacent Voronoi regions. For this purpose, we utilize the information about the horizontal overlap of connected components and the recognition distances of candidate characters provided by an OCR engine. Experimental results show that the proposed method is highly accurate and robust to various types of stele.</div>
</front>
</TEI>
<affiliations><list><country><li>France</li>
<li>Viêt Nam</li>
</country>
<region><li>Alsace-Champagne-Ardenne-Lorraine</li>
<li>Lorraine</li>
</region>
<settlement><li>Vandoeuvre-lès-Nancy</li>
</settlement>
<orgName><li>Université Nancy 2</li>
</orgName>
</list>
<tree><country name="Viêt Nam"><noRegion><name sortKey="Hoang, V" sort="Hoang, V" uniqKey="Hoang V" first="V." last="Hoang">V. Hoang</name>
</noRegion>
<name sortKey="Pham, Ngoc Yen" sort="Pham, Ngoc Yen" uniqKey="Pham N" first="Ngoc-Yen" last="Pham">Ngoc-Yen Pham</name>
<name sortKey="Pham, Ngoc Yen" sort="Pham, Ngoc Yen" uniqKey="Pham N" first="Ngoc-Yen" last="Pham">Ngoc-Yen Pham</name>
</country>
<country name="France"><region name="Alsace-Champagne-Ardenne-Lorraine"><name sortKey="Hoang, V" sort="Hoang, V" uniqKey="Hoang V" first="V." last="Hoang">V. Hoang</name>
</region>
<name sortKey="Hoang, V" sort="Hoang, V" uniqKey="Hoang V" first="V." last="Hoang">V. Hoang</name>
<name sortKey="Tabbone, Salvatore" sort="Tabbone, Salvatore" uniqKey="Tabbone S" first="Salvatore" last="Tabbone">Salvatore Tabbone</name>
<name sortKey="Tabbone, Salvatore" sort="Tabbone, Salvatore" uniqKey="Tabbone S" first="Salvatore" last="Tabbone">Salvatore Tabbone</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 000920 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000920 | 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= ISTEX:10ACEFF10D679878C336ED2CD736C58908395270 |texte= Recognition-Based Segmentation of Nom Characters from Body Text Regions of Stele Images Using Area Voronoi Diagram }}
This area was generated with Dilib version V0.6.32. |