Linear-quadratic blind source separating structure for removing show-through in scanned documents
Identifieur interne : 000557 ( Main/Exploration ); précédent : 000556; suivant : 000558Linear-quadratic blind source separating structure for removing show-through in scanned documents
Auteurs : Farnood Merrikh-Bayat [Iran] ; Massoud Babaie-Zadeh [France] ; Christian Jutten [France]Source :
- International journal on document analysis and recognition : (Print) [ 1433-2833 ] ; 2011.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
- mix :
Abstract
Digital documents are usually degraded during the scanning process due to the contents of the backside of the scanned manuscript. This is often caused by the show-through effect, i.e. the backside image that interferes with the main front side picture due to the intrinsic transparency of the paper. This phenomenon is one of the degradations that one would like to remove especially in the field of Optical Character Recognition (OCR) or document digitalization which require denoised texts as inputs. In this paper, we first propose a novel and general nonlinear model for canceling the show-through phenomenon. A nonlinear blind source separation algorithm is used for this purpose based on a new recursive and extendible structure. However, the results are restricted due to a blurring effect that appears during the scanning process due to the light transfer function of the paper. Consequently, for improving the results, we introduce a refined separating architecture for simultaneously removing the show-through and blurring effects.
Url:
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000105
- to stream PascalFrancis, to step Curation: 000667
- to stream PascalFrancis, to step Checkpoint: 000111
- to stream Main, to step Merge: 000563
- to stream Hal, to step Corpus: 000078
- to stream Hal, to step Curation: 000078
- to stream Hal, to step Checkpoint: 000079
- to stream Main, to step Merge: 000335
- to stream Main, to step Curation: 000557
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Linear-quadratic blind source separating structure for removing show-through in scanned documents</title>
<author><name sortKey="Merrikh Bayat, Farnood" sort="Merrikh Bayat, Farnood" uniqKey="Merrikh Bayat F" first="Farnood" last="Merrikh-Bayat">Farnood Merrikh-Bayat</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Electrical engineering department, Sharif university of technology, Azadi Avenue</s1>
<s2>Tehran</s2>
<s3>IRN</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>Iran</country>
<wicri:noRegion>Tehran</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Babaie Zadeh, Massoud" sort="Babaie Zadeh, Massoud" uniqKey="Babaie Zadeh M" first="Massoud" last="Babaie-Zadeh">Massoud Babaie-Zadeh</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>GIPSA-lab, Department of Images and Signal</s1>
<s2>Grenoble</s2>
<s3>FRA</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Grenoble</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Jutten, Christian" sort="Jutten, Christian" uniqKey="Jutten C" first="Christian" last="Jutten">Christian Jutten</name>
<affiliation wicri:level="1"><inist:fA14 i1="03"><s1>Institut Universitaire de France</s1>
<s2>Paris</s2>
<s3>FRA</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Paris</settlement>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">12-0083116</idno>
<date when="2011">2011</date>
<idno type="stanalyst">PASCAL 12-0083116 INIST</idno>
<idno type="RBID">Pascal:12-0083116</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000105</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000667</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000111</idno>
<idno type="wicri:doubleKey">1433-2833:2011:Merrikh Bayat F:linear:quadratic:blind</idno>
<idno type="wicri:Area/Main/Merge">000563</idno>
<idno type="wicri:source">HAL</idno>
<idno type="RBID">Hal:hal-00643471</idno>
<idno type="url">https://hal.archives-ouvertes.fr/hal-00643471</idno>
<idno type="wicri:Area/Hal/Corpus">000078</idno>
<idno type="wicri:Area/Hal/Curation">000078</idno>
<idno type="wicri:Area/Hal/Checkpoint">000079</idno>
<idno type="wicri:doubleKey">1433-2833:2011:Merrikh Bayat F:linear:quadratic:blind</idno>
<idno type="wicri:Area/Main/Merge">000335</idno>
<idno type="wicri:Area/Main/Curation">000557</idno>
<idno type="wicri:Area/Main/Exploration">000557</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Linear-quadratic blind source separating structure for removing show-through in scanned documents</title>
<author><name sortKey="Merrikh Bayat, Farnood" sort="Merrikh Bayat, Farnood" uniqKey="Merrikh Bayat F" first="Farnood" last="Merrikh-Bayat">Farnood Merrikh-Bayat</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Electrical engineering department, Sharif university of technology, Azadi Avenue</s1>
<s2>Tehran</s2>
<s3>IRN</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>Iran</country>
<wicri:noRegion>Tehran</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Babaie Zadeh, Massoud" sort="Babaie Zadeh, Massoud" uniqKey="Babaie Zadeh M" first="Massoud" last="Babaie-Zadeh">Massoud Babaie-Zadeh</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>GIPSA-lab, Department of Images and Signal</s1>
<s2>Grenoble</s2>
<s3>FRA</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Grenoble</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Jutten, Christian" sort="Jutten, Christian" uniqKey="Jutten C" first="Christian" last="Jutten">Christian Jutten</name>
<affiliation wicri:level="1"><inist:fA14 i1="03"><s1>Institut Universitaire de France</s1>
<s2>Paris</s2>
<s3>FRA</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Paris</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="2011">2011</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>Blind</term>
<term>Blind separation</term>
<term>Character recognition</term>
<term>Linear source</term>
<term>Non linear model</term>
<term>Optical character recognition</term>
<term>Source separation</term>
<term>Text</term>
<term>Transfer function</term>
<term>Transparency</term>
<term>blurring image</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance optique caractère</term>
<term>Reconnaissance caractère</term>
<term>Texte</term>
<term>Floutage</term>
<term>Source linéaire</term>
<term>Aveugle</term>
<term>Transparence</term>
<term>Séparation aveugle</term>
<term>Séparation source</term>
<term>Modèle non linéaire</term>
<term>Fonction transfert</term>
<term>.</term>
</keywords>
<keywords scheme="mix" xml:lang="en"><term>Blind source separation</term>
<term>Blurring effect</term>
<term>Linear-quadratic</term>
<term>Show-through reduction</term>
<term>convolutive mixtures</term>
<term>nonlinear mixtures</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Digital documents are usually degraded during the scanning process due to the contents of the backside of the scanned manuscript. This is often caused by the show-through effect, i.e. the backside image that interferes with the main front side picture due to the intrinsic transparency of the paper. This phenomenon is one of the degradations that one would like to remove especially in the field of Optical Character Recognition (OCR) or document digitalization which require denoised texts as inputs. In this paper, we first propose a novel and general nonlinear model for canceling the show-through phenomenon. A nonlinear blind source separation algorithm is used for this purpose based on a new recursive and extendible structure. However, the results are restricted due to a blurring effect that appears during the scanning process due to the light transfer function of the paper. Consequently, for improving the results, we introduce a refined separating architecture for simultaneously removing the show-through and blurring effects.</div>
</front>
</TEI>
<affiliations><list><country><li>France</li>
<li>Iran</li>
</country>
<settlement><li>Grenoble</li>
<li>Paris</li>
</settlement>
</list>
<tree><country name="Iran"><noRegion><name sortKey="Merrikh Bayat, Farnood" sort="Merrikh Bayat, Farnood" uniqKey="Merrikh Bayat F" first="Farnood" last="Merrikh-Bayat">Farnood Merrikh-Bayat</name>
</noRegion>
</country>
<country name="France"><noRegion><name sortKey="Babaie Zadeh, Massoud" sort="Babaie Zadeh, Massoud" uniqKey="Babaie Zadeh M" first="Massoud" last="Babaie-Zadeh">Massoud Babaie-Zadeh</name>
</noRegion>
<name sortKey="Jutten, Christian" sort="Jutten, Christian" uniqKey="Jutten C" first="Christian" last="Jutten">Christian Jutten</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 000557 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000557 | 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:12-0083116 |texte= Linear-quadratic blind source separating structure for removing show-through in scanned documents }}
This area was generated with Dilib version V0.6.32. |