OcrV1, Main, Exploration, bibRecord, 000F25

Restoring 2D content from distorted documents

Identifieur interne : 000F25 ( Main/Exploration ); précédent : 000F24; suivant : 000F26

Restoring 2D content from distorted documents

Auteurs : Michael S. Brown [Singapour] ; MINGXUAN SUN [États-Unis] ; RUIGANG YANG [États-Unis] ; LIN YUN [États-Unis] ; W. Brent Seales [États-Unis]

Source :

IEEE transactions on pattern analysis and machine intelligence [ 0162-8828 ] ; 2007.

RBID : Pascal:07-0506314

Descripteurs français

Pascal (Inist)
- Intelligence artificielle, Analyse forme, Eclairement, Texte, Formation image, Reconnaissance optique caractère, Reconnaissance caractère, Haute résolution, Résolution image, Traitement image, Image tridimensionnelle, Traitement document, Caractère imprimé, Document imprimé, Luminance, Surface plane, Structure document, Transformation géométrique, Transformation conforme, Gradient, Facteur réflexion, Artefact, Source lumineuse.
Wicri :
- topic : Intelligence artificielle.

English descriptors

Abstract

-This paper presents a framework to restore the 2D content printed on documents in the presence of geometric distortion and nonuniform illumination. Compared with text-based document imaging approaches that correct distortion to a level necessary to obtain sufficiently readable text or to facilitate optical character recognition (OCR), our work targets nontextual documents where the original printed content is desired. To achieve this goal, our framework acquires a 3D scan of the document's surface together with a high-resolution image. Conformal mapping is used to rectify geometric distortion by mapping the 3D surface back to a plane while minimizing angular distortion. This conformal "deskewing" assumes no parametric model of the document's surface and is suitable for arbitrary distortions. Illumination correction is performed by using the 3D shape to distinguish content gradient edges from illumination gradient edges in the high-resolution image. Integration is performed using only the content edges to obtain a reflectance image with significantly less illumination artifacts. This approach makes no assumptions about light sources and their positions. The results from the geometric and photometric correction are combined to produce the final output.

Affiliations:

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Restoring 2D content from distorted documents</title>
<author><name sortKey="Brown, Michael S" sort="Brown, Michael S" uniqKey="Brown M" first="Michael S." last="Brown">Michael S. Brown</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computer Engineering, Nanyang Technological University, Blk N4, 2A-32, Nanyang Avenue</s1>
<s2>Singapore 639798</s2>
<s3>SGP</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>Singapour</country>
<wicri:noRegion>Singapore 639798</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Mingxuan Sun" sort="Mingxuan Sun" uniqKey="Mingxuan Sun" last="Mingxuan Sun">MINGXUAN SUN</name>
<affiliation wicri:level="2"><inist:fA14 i1="02"><s1>GVU Center, Georgia Institute of Technology, 85 Fifth St. NW</s1>
<s2>Atlanta, GA 30332-0760</s2>
<s3>USA</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Géorgie (États-Unis)</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Ruigang Yang" sort="Ruigang Yang" uniqKey="Ruigang Yang" last="Ruigang Yang">RUIGANG YANG</name>
<affiliation wicri:level="2"><inist:fA14 i1="03"><s1>Computer Science Department, University of Kentucky, 232 Hardymon Building</s1>
<s2>Lexington, KY 40506</s2>
<s3>USA</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Kentucky</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Lin Yun" sort="Lin Yun" uniqKey="Lin Yun" last="Lin Yun">LIN YUN</name>
<affiliation wicri:level="2"><inist:fA14 i1="04"><s1>Laboratory for Advanced Networking, University of Kentucky, Hardymon Building, 2nd Floor, 301 Rose Street</s1>
<s2>Lexington, KY 40506-0495</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Kentucky</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Seales, W Brent" sort="Seales, W Brent" uniqKey="Seales W" first="W. Brent" last="Seales">W. Brent Seales</name>
<affiliation wicri:level="2"><inist:fA14 i1="04"><s1>Laboratory for Advanced Networking, University of Kentucky, Hardymon Building, 2nd Floor, 301 Rose Street</s1>
<s2>Lexington, KY 40506-0495</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Kentucky</region>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">07-0506314</idno>
<date when="2007">2007</date>
<idno type="stanalyst">PASCAL 07-0506314 INIST</idno>
<idno type="RBID">Pascal:07-0506314</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000317</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000469</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000267</idno>
<idno type="wicri:doubleKey">0162-8828:2007:Brown M:restoring:d:content</idno>
<idno type="wicri:Area/Main/Merge">000F38</idno>
<idno type="wicri:source">PubMed</idno>
<idno type="RBID">pubmed:17848773</idno>
<idno type="wicri:Area/PubMed/Corpus">000058</idno>
<idno type="wicri:Area/PubMed/Curation">000058</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000058</idno>
<idno type="wicri:Area/Ncbi/Merge">000041</idno>
<idno type="wicri:Area/Ncbi/Curation">000041</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">000041</idno>
<idno type="wicri:doubleKey">0162-8828:2007:Brown M:restoring:d:content</idno>
<idno type="wicri:Area/Main/Merge">000D55</idno>
<idno type="wicri:Area/Main/Curation">000F25</idno>
<idno type="wicri:Area/Main/Exploration">000F25</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Restoring 2D content from distorted documents</title>
<author><name sortKey="Brown, Michael S" sort="Brown, Michael S" uniqKey="Brown M" first="Michael S." last="Brown">Michael S. Brown</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computer Engineering, Nanyang Technological University, Blk N4, 2A-32, Nanyang Avenue</s1>
<s2>Singapore 639798</s2>
<s3>SGP</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>Singapour</country>
<wicri:noRegion>Singapore 639798</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Mingxuan Sun" sort="Mingxuan Sun" uniqKey="Mingxuan Sun" last="Mingxuan Sun">MINGXUAN SUN</name>
<affiliation wicri:level="2"><inist:fA14 i1="02"><s1>GVU Center, Georgia Institute of Technology, 85 Fifth St. NW</s1>
<s2>Atlanta, GA 30332-0760</s2>
<s3>USA</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Géorgie (États-Unis)</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Ruigang Yang" sort="Ruigang Yang" uniqKey="Ruigang Yang" last="Ruigang Yang">RUIGANG YANG</name>
<affiliation wicri:level="2"><inist:fA14 i1="03"><s1>Computer Science Department, University of Kentucky, 232 Hardymon Building</s1>
<s2>Lexington, KY 40506</s2>
<s3>USA</s3>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Kentucky</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Lin Yun" sort="Lin Yun" uniqKey="Lin Yun" last="Lin Yun">LIN YUN</name>
<affiliation wicri:level="2"><inist:fA14 i1="04"><s1>Laboratory for Advanced Networking, University of Kentucky, Hardymon Building, 2nd Floor, 301 Rose Street</s1>
<s2>Lexington, KY 40506-0495</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Kentucky</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Seales, W Brent" sort="Seales, W Brent" uniqKey="Seales W" first="W. Brent" last="Seales">W. Brent Seales</name>
<affiliation wicri:level="2"><inist:fA14 i1="04"><s1>Laboratory for Advanced Networking, University of Kentucky, Hardymon Building, 2nd Floor, 301 Rose Street</s1>
<s2>Lexington, KY 40506-0495</s2>
<s3>USA</s3>
<sZ>4 aut.</sZ>
<sZ>5 aut.</sZ>
</inist:fA14>
<country>États-Unis</country>
<placeName><region type="state">Kentucky</region>
</placeName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">IEEE transactions on pattern analysis and machine intelligence</title>
<title level="j" type="abbreviated">IEEE trans. pattern anal. mach. intell.</title>
<idno type="ISSN">0162-8828</idno>
<imprint><date when="2007">2007</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">IEEE transactions on pattern analysis and machine intelligence</title>
<title level="j" type="abbreviated">IEEE trans. pattern anal. mach. intell.</title>
<idno type="ISSN">0162-8828</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term>
<term>Artefact</term>
<term>Artificial Intelligence</term>
<term>Artificial intelligence</term>
<term>Automatic Data Processing (methods)</term>
<term>Character recognition</term>
<term>Computer Graphics</term>
<term>Conformal transformation</term>
<term>Document processing</term>
<term>Document structure</term>
<term>Documentation (methods)</term>
<term>Geometric transformation</term>
<term>Gradient</term>
<term>High resolution</term>
<term>Illumination</term>
<term>Image Enhancement (methods)</term>
<term>Image Interpretation, Computer-Assisted (methods)</term>
<term>Image processing</term>
<term>Image resolution</term>
<term>Imaging</term>
<term>Information Storage and Retrieval (methods)</term>
<term>Light source</term>
<term>Luminance</term>
<term>Numerical Analysis, Computer-Assisted</term>
<term>Optical character recognition</term>
<term>Pattern Recognition, Automated (methods)</term>
<term>Pattern analysis</term>
<term>Plane surface</term>
<term>Printed character</term>
<term>Printed document</term>
<term>Reflectance</term>
<term>Reproducibility of Results</term>
<term>Sensitivity and Specificity</term>
<term>Signal Processing, Computer-Assisted</term>
<term>Subtraction Technique</term>
<term>Text</term>
<term>Tridimensional image</term>
<term>User-Computer Interface</term>
</keywords>
<keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Automatic Data Processing</term>
<term>Documentation</term>
<term>Image Enhancement</term>
<term>Image Interpretation, Computer-Assisted</term>
<term>Information Storage and Retrieval</term>
<term>Pattern Recognition, Automated</term>
</keywords>
<keywords scheme="MESH" xml:lang="en"><term>Algorithms</term>
<term>Artificial Intelligence</term>
<term>Computer Graphics</term>
<term>Numerical Analysis, Computer-Assisted</term>
<term>Reproducibility of Results</term>
<term>Sensitivity and Specificity</term>
<term>Signal Processing, Computer-Assisted</term>
<term>Subtraction Technique</term>
<term>User-Computer Interface</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Intelligence artificielle</term>
<term>Analyse forme</term>
<term>Eclairement</term>
<term>Texte</term>
<term>Formation image</term>
<term>Reconnaissance optique caractère</term>
<term>Reconnaissance caractère</term>
<term>Haute résolution</term>
<term>Résolution image</term>
<term>Traitement image</term>
<term>Image tridimensionnelle</term>
<term>Traitement document</term>
<term>Caractère imprimé</term>
<term>Document imprimé</term>
<term>Luminance</term>
<term>Surface plane</term>
<term>Structure document</term>
<term>Transformation géométrique</term>
<term>Transformation conforme</term>
<term>Gradient</term>
<term>Facteur réflexion</term>
<term>Artefact</term>
<term>Source lumineuse</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Intelligence artificielle</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">-This paper presents a framework to restore the 2D content printed on documents in the presence of geometric distortion and nonuniform illumination. Compared with text-based document imaging approaches that correct distortion to a level necessary to obtain sufficiently readable text or to facilitate optical character recognition (OCR), our work targets nontextual documents where the original printed content is desired. To achieve this goal, our framework acquires a 3D scan of the document's surface together with a high-resolution image. Conformal mapping is used to rectify geometric distortion by mapping the 3D surface back to a plane while minimizing angular distortion. This conformal "deskewing" assumes no parametric model of the document's surface and is suitable for arbitrary distortions. Illumination correction is performed by using the 3D shape to distinguish content gradient edges from illumination gradient edges in the high-resolution image. Integration is performed using only the content edges to obtain a reflectance image with significantly less illumination artifacts. This approach makes no assumptions about light sources and their positions. The results from the geometric and photometric correction are combined to produce the final output.</div>
</front>
</TEI>
<affiliations><list><country><li>Singapour</li>
<li>États-Unis</li>
</country>
<region><li>Géorgie (États-Unis)</li>
<li>Kentucky</li>
</region>
</list>
<tree><country name="Singapour"><noRegion><name sortKey="Brown, Michael S" sort="Brown, Michael S" uniqKey="Brown M" first="Michael S." last="Brown">Michael S. Brown</name>
</noRegion>
</country>
<country name="États-Unis"><region name="Géorgie (États-Unis)"><name sortKey="Mingxuan Sun" sort="Mingxuan Sun" uniqKey="Mingxuan Sun" last="Mingxuan Sun">MINGXUAN SUN</name>
</region>
<name sortKey="Lin Yun" sort="Lin Yun" uniqKey="Lin Yun" last="Lin Yun">LIN YUN</name>
<name sortKey="Ruigang Yang" sort="Ruigang Yang" uniqKey="Ruigang Yang" last="Ruigang Yang">RUIGANG YANG</name>
<name sortKey="Seales, W Brent" sort="Seales, W Brent" uniqKey="Seales W" first="W. Brent" last="Seales">W. Brent Seales</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 000F25 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000F25 | 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:07-0506314
   |texte=   Restoring 2D content from distorted documents
}}

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

Restoring 2D content from distorted documents

Restoring 2D content from distorted documents

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

	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.