Robust reconstruction of low-resolution document images by exploiting repetitive character behaviour
Identifieur interne : 000D04 ( Main/Exploration ); précédent : 000D03; suivant : 000D05Robust reconstruction of low-resolution document images by exploiting repetitive character behaviour
Auteurs : Hiêp Q. Luong [Belgique] ; Wilfried Philips [Belgique]Source :
- International journal on document analysis and recognition : (Print) [ 1433-2833 ] ; 2008.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
In this paper, we present a new approach for reconstructing low-resolution document images. Unlike other conventional reconstruction methods, the unknown pixel values are not estimated based on their local surrounding neighbourhood, but on the whole image. In particular, we exploit the multiple occurrence of characters in the scanned document. In order to take advantage of this repetitive behaviour, we divide the image into character segments and match similar character segments to filter relevant information before the reconstruction. A great advantage of our proposed approach over conventional approaches is that we have more information at our disposal, which leads to a better reconstruction of the high-resolution (HR) image. Experimental results confirm the effectiveness of our proposed method, which is expressed in a better optical character recognition (OCR) accuracy and visual superiority to other traditional interpolation and restoration methods.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000243
- to stream PascalFrancis, to step Curation: 000536
- to stream PascalFrancis, to step Checkpoint: 000226
- to stream Main, to step Merge: 000D16
- to stream Main, to step Curation: 000D04
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Robust reconstruction of low-resolution document images by exploiting repetitive character behaviour</title>
<author><name sortKey="Luong, Hiep Q" sort="Luong, Hiep Q" uniqKey="Luong H" first="Hiêp Q." last="Luong">Hiêp Q. Luong</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Department of Telecommunications and Information Processing, IPI, IBBT, Ghent University, Sint-Pietersnieuwstraat 41</s1>
<s2>9000 Ghent</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Philips, Wilfried" sort="Philips, Wilfried" uniqKey="Philips W" first="Wilfried" last="Philips">Wilfried Philips</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Department of Telecommunications and Information Processing, IPI, IBBT, Ghent University, Sint-Pietersnieuwstraat 41</s1>
<s2>9000 Ghent</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">09-0010034</idno>
<date when="2008">2008</date>
<idno type="stanalyst">PASCAL 09-0010034 INIST</idno>
<idno type="RBID">Pascal:09-0010034</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000243</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000536</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000226</idno>
<idno type="wicri:doubleKey">1433-2833:2008:Luong H:robust:reconstruction:of</idno>
<idno type="wicri:Area/Main/Merge">000D16</idno>
<idno type="wicri:Area/Main/Curation">000D04</idno>
<idno type="wicri:Area/Main/Exploration">000D04</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Robust reconstruction of low-resolution document images by exploiting repetitive character behaviour</title>
<author><name sortKey="Luong, Hiep Q" sort="Luong, Hiep Q" uniqKey="Luong H" first="Hiêp Q." last="Luong">Hiêp Q. Luong</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Department of Telecommunications and Information Processing, IPI, IBBT, Ghent University, Sint-Pietersnieuwstraat 41</s1>
<s2>9000 Ghent</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Philips, Wilfried" sort="Philips, Wilfried" uniqKey="Philips W" first="Wilfried" last="Philips">Wilfried Philips</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>Department of Telecommunications and Information Processing, IPI, IBBT, Ghent University, Sint-Pietersnieuwstraat 41</s1>
<s2>9000 Ghent</s2>
<s3>BEL</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Belgique</country>
<placeName><region type="province" nuts="2">Province de Flandre-Orientale</region>
<settlement type="city">Gand</settlement>
</placeName>
</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="2008">2008</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>High resolution</term>
<term>Image processing</term>
<term>Image reconstruction</term>
<term>Image resolution</term>
<term>Low resolution</term>
<term>Optical character recognition</term>
<term>Segmentation</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Résolution image</term>
<term>Traitement image</term>
<term>Reconstruction image</term>
<term>Haute résolution</term>
<term>Reconnaissance optique caractère</term>
<term>Reconnaissance caractère</term>
<term>Basse résolution</term>
<term>Segmentation</term>
<term>.</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">In this paper, we present a new approach for reconstructing low-resolution document images. Unlike other conventional reconstruction methods, the unknown pixel values are not estimated based on their local surrounding neighbourhood, but on the whole image. In particular, we exploit the multiple occurrence of characters in the scanned document. In order to take advantage of this repetitive behaviour, we divide the image into character segments and match similar character segments to filter relevant information before the reconstruction. A great advantage of our proposed approach over conventional approaches is that we have more information at our disposal, which leads to a better reconstruction of the high-resolution (HR) image. Experimental results confirm the effectiveness of our proposed method, which is expressed in a better optical character recognition (OCR) accuracy and visual superiority to other traditional interpolation and restoration methods.</div>
</front>
</TEI>
<affiliations><list><country><li>Belgique</li>
</country>
<region><li>Province de Flandre-Orientale</li>
</region>
<settlement><li>Gand</li>
</settlement>
</list>
<tree><country name="Belgique"><region name="Province de Flandre-Orientale"><name sortKey="Luong, Hiep Q" sort="Luong, Hiep Q" uniqKey="Luong H" first="Hiêp Q." last="Luong">Hiêp Q. Luong</name>
</region>
<name sortKey="Philips, Wilfried" sort="Philips, Wilfried" uniqKey="Philips W" first="Wilfried" last="Philips">Wilfried Philips</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 000D04 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000D04 | 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:09-0010034 |texte= Robust reconstruction of low-resolution document images by exploiting repetitive character behaviour }}
This area was generated with Dilib version V0.6.32. |