A unified framework for document restoration using inpainting and shape-from-shading
Identifieur interne : 000557 ( PascalFrancis/Curation ); précédent : 000556; suivant : 000558A unified framework for document restoration using inpainting and shape-from-shading
Auteurs : LI ZHANG [Singapour] ; A. M. Yip [Singapour] ; M. S. Brown [Singapour] ; CHEW LIM TAN [Singapour]Source :
- Pattern recognition [ 0031-3203 ] ; 2009.
Descripteurs français
- Pascal (Inist)
- Topographie, Reconstruction surface, Détection forme, Ombrage, Artefact, Volume, Ombre, Evaluation performance, Reconnaissance optique caractère, Traitement image document, Restauration image, Gauchissement, Fonction base radiale, Aplatissement, Traitement image, Reconstruction image, Reconnaissance forme.
English descriptors
- KwdEn :
Abstract
We present a restoration framework to reduce undesirable distortions in imaged documents. Our framework is based on two components: (1) an image inpainting procedure that can separate non-uniform illumination (and other) artifacts from the printed content and (2) a shape-from-shading (SfS) formulation that can reconstruct the 3D shape of the document's surface. Used either piecewise or in its entirety, this framework can correct a variety of distortions including shading, shadow, ink-bleed, show-through, perspective and geometric distortions, for both camera-imaged and flatbed-imaged documents. Our overall framework is described in detail. In addition, our SfS formulation can be easily modified to target various illumination conditions to suit different real-world applications. Results on images of synthetic and real documents demonstrate the effectiveness of our approach. OCR results are also used to gauge the performance of our approach.
pA |
|
---|
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000222
Links to Exploration step
Pascal:09-0316643Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">A unified framework for document restoration using inpainting and shape-from-shading</title>
<author><name sortKey="Li Zhang" sort="Li Zhang" uniqKey="Li Zhang" last="Li Zhang">LI ZHANG</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computing, National University of Singapore</s1>
<s3>SGP</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Singapour</country>
</affiliation>
</author>
<author><name sortKey="Yip, A M" sort="Yip, A M" uniqKey="Yip A" first="A. M." last="Yip">A. M. Yip</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Department of Mathematics, National University of Singapore</s1>
<s3>SGP</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Singapour</country>
</affiliation>
</author>
<author><name sortKey="Brown, M S" sort="Brown, M S" uniqKey="Brown M" first="M. S." last="Brown">M. S. Brown</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computing, National University of Singapore</s1>
<s3>SGP</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Singapour</country>
</affiliation>
</author>
<author><name sortKey="Chew Lim Tan" sort="Chew Lim Tan" uniqKey="Chew Lim Tan" last="Chew Lim Tan">CHEW LIM TAN</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computing, National University of Singapore</s1>
<s3>SGP</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Singapour</country>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">09-0316643</idno>
<date when="2009">2009</date>
<idno type="stanalyst">PASCAL 09-0316643 INIST</idno>
<idno type="RBID">Pascal:09-0316643</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000222</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000557</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">A unified framework for document restoration using inpainting and shape-from-shading</title>
<author><name sortKey="Li Zhang" sort="Li Zhang" uniqKey="Li Zhang" last="Li Zhang">LI ZHANG</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computing, National University of Singapore</s1>
<s3>SGP</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Singapour</country>
</affiliation>
</author>
<author><name sortKey="Yip, A M" sort="Yip, A M" uniqKey="Yip A" first="A. M." last="Yip">A. M. Yip</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Department of Mathematics, National University of Singapore</s1>
<s3>SGP</s3>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Singapour</country>
</affiliation>
</author>
<author><name sortKey="Brown, M S" sort="Brown, M S" uniqKey="Brown M" first="M. S." last="Brown">M. S. Brown</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computing, National University of Singapore</s1>
<s3>SGP</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Singapour</country>
</affiliation>
</author>
<author><name sortKey="Chew Lim Tan" sort="Chew Lim Tan" uniqKey="Chew Lim Tan" last="Chew Lim Tan">CHEW LIM TAN</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>School of Computing, National University of Singapore</s1>
<s3>SGP</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Singapour</country>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Pattern recognition</title>
<title level="j" type="abbreviated">Pattern recogn.</title>
<idno type="ISSN">0031-3203</idno>
<imprint><date when="2009">2009</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Pattern recognition</title>
<title level="j" type="abbreviated">Pattern recogn.</title>
<idno type="ISSN">0031-3203</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Artefact</term>
<term>Document image processing</term>
<term>Flattening</term>
<term>Image processing</term>
<term>Image reconstruction</term>
<term>Image restoration</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Performance evaluation</term>
<term>Radial basis function</term>
<term>Shadow</term>
<term>Shadowing</term>
<term>Shape detection</term>
<term>Surface reconstruction</term>
<term>Topography</term>
<term>Volume</term>
<term>Warping</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Topographie</term>
<term>Reconstruction surface</term>
<term>Détection forme</term>
<term>Ombrage</term>
<term>Artefact</term>
<term>Volume</term>
<term>Ombre</term>
<term>Evaluation performance</term>
<term>Reconnaissance optique caractère</term>
<term>Traitement image document</term>
<term>Restauration image</term>
<term>Gauchissement</term>
<term>Fonction base radiale</term>
<term>Aplatissement</term>
<term>Traitement image</term>
<term>Reconstruction image</term>
<term>Reconnaissance forme</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">We present a restoration framework to reduce undesirable distortions in imaged documents. Our framework is based on two components: (1) an image inpainting procedure that can separate non-uniform illumination (and other) artifacts from the printed content and (2) a shape-from-shading (SfS) formulation that can reconstruct the 3D shape of the document's surface. Used either piecewise or in its entirety, this framework can correct a variety of distortions including shading, shadow, ink-bleed, show-through, perspective and geometric distortions, for both camera-imaged and flatbed-imaged documents. Our overall framework is described in detail. In addition, our SfS formulation can be easily modified to target various illumination conditions to suit different real-world applications. Results on images of synthetic and real documents demonstrate the effectiveness of our approach. OCR results are also used to gauge the performance of our approach.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0031-3203</s0>
</fA01>
<fA02 i1="01"><s0>PTNRA8</s0>
</fA02>
<fA03 i2="1"><s0>Pattern recogn.</s0>
</fA03>
<fA05><s2>42</s2>
</fA05>
<fA06><s2>11</s2>
</fA06>
<fA08 i1="01" i2="1" l="ENG"><s1>A unified framework for document restoration using inpainting and shape-from-shading</s1>
</fA08>
<fA11 i1="01" i2="1"><s1>LI ZHANG</s1>
</fA11>
<fA11 i1="02" i2="1"><s1>YIP (A. M.)</s1>
</fA11>
<fA11 i1="03" i2="1"><s1>BROWN (M. S.)</s1>
</fA11>
<fA11 i1="04" i2="1"><s1>CHEW LIM TAN</s1>
</fA11>
<fA14 i1="01"><s1>School of Computing, National University of Singapore</s1>
<s3>SGP</s3>
<sZ>1 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</fA14>
<fA14 i1="02"><s1>Department of Mathematics, National University of Singapore</s1>
<s3>SGP</s3>
<sZ>2 aut.</sZ>
</fA14>
<fA20><s1>2961-2978</s1>
</fA20>
<fA21><s1>2009</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA43 i1="01"><s1>INIST</s1>
<s2>15220</s2>
<s5>354000187477260520</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2009 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>64 ref.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>09-0316643</s0>
</fA47>
<fA60><s1>P</s1>
</fA60>
<fA61><s0>A</s0>
</fA61>
<fA64 i1="01" i2="1"><s0>Pattern recognition</s0>
</fA64>
<fA66 i1="01"><s0>GBR</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>We present a restoration framework to reduce undesirable distortions in imaged documents. Our framework is based on two components: (1) an image inpainting procedure that can separate non-uniform illumination (and other) artifacts from the printed content and (2) a shape-from-shading (SfS) formulation that can reconstruct the 3D shape of the document's surface. Used either piecewise or in its entirety, this framework can correct a variety of distortions including shading, shadow, ink-bleed, show-through, perspective and geometric distortions, for both camera-imaged and flatbed-imaged documents. Our overall framework is described in detail. In addition, our SfS formulation can be easily modified to target various illumination conditions to suit different real-world applications. Results on images of synthetic and real documents demonstrate the effectiveness of our approach. OCR results are also used to gauge the performance of our approach.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D04A05A</s0>
</fC02>
<fC02 i1="02" i2="X"><s0>001D04A05C</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Topographie</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Topography</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Topografía</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="X" l="FRE"><s0>Reconstruction surface</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="ENG"><s0>Surface reconstruction</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="X" l="SPA"><s0>Reconstrucción superficie</s0>
<s5>02</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Détection forme</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Shape detection</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Detección forma</s0>
<s5>03</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Ombrage</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Shadowing</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Umbría</s0>
<s5>04</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Artefact</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>Artefact</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Artefacto</s0>
<s5>05</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Volume</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Volume</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Volumen</s0>
<s5>06</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Ombre</s0>
<s5>07</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Shadow</s0>
<s5>07</s5>
</fC03>
<fC03 i1="07" i2="X" l="SPA"><s0>Sombra</s0>
<s5>07</s5>
</fC03>
<fC03 i1="08" i2="X" l="FRE"><s0>Evaluation performance</s0>
<s5>08</s5>
</fC03>
<fC03 i1="08" i2="X" l="ENG"><s0>Performance evaluation</s0>
<s5>08</s5>
</fC03>
<fC03 i1="08" i2="X" l="SPA"><s0>Evaluación prestación</s0>
<s5>08</s5>
</fC03>
<fC03 i1="09" i2="X" l="FRE"><s0>Reconnaissance optique caractère</s0>
<s5>09</s5>
</fC03>
<fC03 i1="09" i2="X" l="ENG"><s0>Optical character recognition</s0>
<s5>09</s5>
</fC03>
<fC03 i1="09" i2="X" l="SPA"><s0>Reconocimento óptico de caracteres</s0>
<s5>09</s5>
</fC03>
<fC03 i1="10" i2="3" l="FRE"><s0>Traitement image document</s0>
<s5>10</s5>
</fC03>
<fC03 i1="10" i2="3" l="ENG"><s0>Document image processing</s0>
<s5>10</s5>
</fC03>
<fC03 i1="11" i2="X" l="FRE"><s0>Restauration image</s0>
<s5>11</s5>
</fC03>
<fC03 i1="11" i2="X" l="ENG"><s0>Image restoration</s0>
<s5>11</s5>
</fC03>
<fC03 i1="11" i2="X" l="SPA"><s0>Restauración imagen</s0>
<s5>11</s5>
</fC03>
<fC03 i1="12" i2="X" l="FRE"><s0>Gauchissement</s0>
<s5>12</s5>
</fC03>
<fC03 i1="12" i2="X" l="ENG"><s0>Warping</s0>
<s5>12</s5>
</fC03>
<fC03 i1="12" i2="X" l="SPA"><s0>Torcimiento</s0>
<s5>12</s5>
</fC03>
<fC03 i1="13" i2="X" l="FRE"><s0>Fonction base radiale</s0>
<s5>13</s5>
</fC03>
<fC03 i1="13" i2="X" l="ENG"><s0>Radial basis function</s0>
<s5>13</s5>
</fC03>
<fC03 i1="13" i2="X" l="SPA"><s0>Función radial base</s0>
<s5>13</s5>
</fC03>
<fC03 i1="14" i2="X" l="FRE"><s0>Aplatissement</s0>
<s5>14</s5>
</fC03>
<fC03 i1="14" i2="X" l="ENG"><s0>Flattening</s0>
<s5>14</s5>
</fC03>
<fC03 i1="14" i2="X" l="SPA"><s0>Aplanamiento</s0>
<s5>14</s5>
</fC03>
<fC03 i1="15" i2="X" l="FRE"><s0>Traitement image</s0>
<s5>31</s5>
</fC03>
<fC03 i1="15" i2="X" l="ENG"><s0>Image processing</s0>
<s5>31</s5>
</fC03>
<fC03 i1="15" i2="X" l="SPA"><s0>Procesamiento imagen</s0>
<s5>31</s5>
</fC03>
<fC03 i1="16" i2="X" l="FRE"><s0>Reconstruction image</s0>
<s5>32</s5>
</fC03>
<fC03 i1="16" i2="X" l="ENG"><s0>Image reconstruction</s0>
<s5>32</s5>
</fC03>
<fC03 i1="16" i2="X" l="SPA"><s0>Reconstrucción imagen</s0>
<s5>32</s5>
</fC03>
<fC03 i1="17" i2="X" l="FRE"><s0>Reconnaissance forme</s0>
<s5>33</s5>
</fC03>
<fC03 i1="17" i2="X" l="ENG"><s0>Pattern recognition</s0>
<s5>33</s5>
</fC03>
<fC03 i1="17" i2="X" l="SPA"><s0>Reconocimiento patrón</s0>
<s5>33</s5>
</fC03>
<fN21><s1>229</s1>
</fN21>
<fN44 i1="01"><s1>OTO</s1>
</fN44>
<fN82><s1>OTO</s1>
</fN82>
</pA>
</standard>
</inist>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PascalFrancis/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000557 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Curation/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= PascalFrancis |étape= Curation |type= RBID |clé= Pascal:09-0316643 |texte= A unified framework for document restoration using inpainting and shape-from-shading }}
This area was generated with Dilib version V0.6.32. |