Restoring warped document images through 3D shape modeling.
Identifieur interne : 000F74 ( Main/Merge ); précédent : 000F73; suivant : 000F75Restoring warped document images through 3D shape modeling.
Auteurs : Chew Lim Tan [Singapour] ; Li Zhang ; Zheng Zhang ; Tao XiaSource :
- IEEE transactions on pattern analysis and machine intelligence [ 0162-8828 ] ; 2006.
English descriptors
- KwdEn :
- Algorithms, Artifacts, Artificial Intelligence, Automatic Data Processing (methods), Computer Graphics, Computer Simulation, Documentation (methods), Image Enhancement (methods), Image Interpretation, Computer-Assisted (methods), Imaging, Three-Dimensional (methods), Information Storage and Retrieval (methods), Models, Theoretical, Pattern Recognition, Automated (methods), Reproducibility of Results, Sensitivity and Specificity.
- MESH :
- methods : Automatic Data Processing, Documentation, Image Enhancement, Image Interpretation, Computer-Assisted, Imaging, Three-Dimensional, Information Storage and Retrieval, Pattern Recognition, Automated.
- Algorithms, Artifacts, Artificial Intelligence, Computer Graphics, Computer Simulation, Models, Theoretical, Reproducibility of Results, Sensitivity and Specificity.
Abstract
Scanning a document page from a thick bound volume often results in two kinds of distortions in the scanned image, i.e., shade along the "spine" of the book and warping in the shade area. In this paper, we propose an efficient restoration method based on the discovery of the 3D shape of a book surface from the shading information in a scanned document image. From a technical point of view, this shape from shading (SFS) problem in real-world environments is characterized by 1) a proximal and moving light source, 2) Lambertian reflection, 3) nonuniform albedo distribution, and 4) document skew. Taking all these factors into account, we first build practical models (consisting of a 3D geometric model and a 3D optical model) for the practical scanning conditions to reconstruct the 3D shape of the book surface. We next restore the scanned document image using this shape based on deshading and dewarping models. Finally, we evaluate the restoration results by comparing our estimated surface shape with the real shape as well as the OCR performance on original and restored document images. The results show that the geometric and photometric distortions are mostly removed and the OCR results are improved markedly.
DOI: 10.1109/TPAMI.2006.40
PubMed: 16468617
Links toward previous steps (curation, corpus...)
- to stream PubMed, to step Corpus: 000064
- to stream PubMed, to step Curation: 000064
- to stream PubMed, to step Checkpoint: 000064
- to stream Ncbi, to step Merge: 000026
- to stream Ncbi, to step Curation: 000026
- to stream Ncbi, to step Checkpoint: 000026
Links to Exploration step
pubmed:16468617Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Restoring warped document images through 3D shape modeling.</title>
<author><name sortKey="Tan, Chew Lim" sort="Tan, Chew Lim" uniqKey="Tan C" first="Chew Lim" last="Tan">Chew Lim Tan</name>
<affiliation wicri:level="1"><nlm:affiliation>School of Computing, National University of Singapore 3, Science Drive 2, Singapore. tancl@comp.nus.edu.sg</nlm:affiliation>
<country xml:lang="fr">Singapour</country>
<wicri:regionArea>School of Computing, National University of Singapore 3, Science Drive 2</wicri:regionArea>
<wicri:noRegion>Science Drive 2</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Zhang, Li" sort="Zhang, Li" uniqKey="Zhang L" first="Li" last="Zhang">Li Zhang</name>
</author>
<author><name sortKey="Zhang, Zheng" sort="Zhang, Zheng" uniqKey="Zhang Z" first="Zheng" last="Zhang">Zheng Zhang</name>
</author>
<author><name sortKey="Xia, Tao" sort="Xia, Tao" uniqKey="Xia T" first="Tao" last="Xia">Tao Xia</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2006">2006</date>
<idno type="RBID">pubmed:16468617</idno>
<idno type="pmid">16468617</idno>
<idno type="doi">10.1109/TPAMI.2006.40</idno>
<idno type="wicri:Area/PubMed/Corpus">000064</idno>
<idno type="wicri:Area/PubMed/Curation">000064</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000064</idno>
<idno type="wicri:Area/Ncbi/Merge">000026</idno>
<idno type="wicri:Area/Ncbi/Curation">000026</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">000026</idno>
<idno type="wicri:doubleKey">0162-8828:2006:Tan C:restoring:warped:document</idno>
<idno type="wicri:Area/Main/Merge">000F74</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Restoring warped document images through 3D shape modeling.</title>
<author><name sortKey="Tan, Chew Lim" sort="Tan, Chew Lim" uniqKey="Tan C" first="Chew Lim" last="Tan">Chew Lim Tan</name>
<affiliation wicri:level="1"><nlm:affiliation>School of Computing, National University of Singapore 3, Science Drive 2, Singapore. tancl@comp.nus.edu.sg</nlm:affiliation>
<country xml:lang="fr">Singapour</country>
<wicri:regionArea>School of Computing, National University of Singapore 3, Science Drive 2</wicri:regionArea>
<wicri:noRegion>Science Drive 2</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Zhang, Li" sort="Zhang, Li" uniqKey="Zhang L" first="Li" last="Zhang">Li Zhang</name>
</author>
<author><name sortKey="Zhang, Zheng" sort="Zhang, Zheng" uniqKey="Zhang Z" first="Zheng" last="Zhang">Zheng Zhang</name>
</author>
<author><name sortKey="Xia, Tao" sort="Xia, Tao" uniqKey="Xia T" first="Tao" last="Xia">Tao Xia</name>
</author>
</analytic>
<series><title level="j">IEEE transactions on pattern analysis and machine intelligence</title>
<idno type="ISSN">0162-8828</idno>
<imprint><date when="2006" type="published">2006</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term>
<term>Artifacts</term>
<term>Artificial Intelligence</term>
<term>Automatic Data Processing (methods)</term>
<term>Computer Graphics</term>
<term>Computer Simulation</term>
<term>Documentation (methods)</term>
<term>Image Enhancement (methods)</term>
<term>Image Interpretation, Computer-Assisted (methods)</term>
<term>Imaging, Three-Dimensional (methods)</term>
<term>Information Storage and Retrieval (methods)</term>
<term>Models, Theoretical</term>
<term>Pattern Recognition, Automated (methods)</term>
<term>Reproducibility of Results</term>
<term>Sensitivity and Specificity</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>Imaging, Three-Dimensional</term>
<term>Information Storage and Retrieval</term>
<term>Pattern Recognition, Automated</term>
</keywords>
<keywords scheme="MESH" xml:lang="en"><term>Algorithms</term>
<term>Artifacts</term>
<term>Artificial Intelligence</term>
<term>Computer Graphics</term>
<term>Computer Simulation</term>
<term>Models, Theoretical</term>
<term>Reproducibility of Results</term>
<term>Sensitivity and Specificity</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Scanning a document page from a thick bound volume often results in two kinds of distortions in the scanned image, i.e., shade along the "spine" of the book and warping in the shade area. In this paper, we propose an efficient restoration method based on the discovery of the 3D shape of a book surface from the shading information in a scanned document image. From a technical point of view, this shape from shading (SFS) problem in real-world environments is characterized by 1) a proximal and moving light source, 2) Lambertian reflection, 3) nonuniform albedo distribution, and 4) document skew. Taking all these factors into account, we first build practical models (consisting of a 3D geometric model and a 3D optical model) for the practical scanning conditions to reconstruct the 3D shape of the book surface. We next restore the scanned document image using this shape based on deshading and dewarping models. Finally, we evaluate the restoration results by comparing our estimated surface shape with the real shape as well as the OCR performance on original and restored document images. The results show that the geometric and photometric distortions are mostly removed and the OCR results are improved markedly.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000F74 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 000F74 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Merge |type= RBID |clé= pubmed:16468617 |texte= Restoring warped document images through 3D shape modeling. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Merge/RBID.i -Sk "pubmed:16468617" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Merge/biblio.hfd \ | NlmPubMed2Wicri -a OcrV1
This area was generated with Dilib version V0.6.32. |