Geometric rectification of camera-captured document images.
Identifieur interne : 000B17 ( Main/Exploration ); précédent : 000B16; suivant : 000B18Geometric rectification of camera-captured document images.
Auteurs : Jian Liang [États-Unis] ; Daniel Dementhon ; David DoermannSource :
- IEEE transactions on pattern analysis and machine intelligence [ 0162-8828 ] ; 2008.
English descriptors
- KwdEn :
- Algorithms, Artifacts, Artificial Intelligence, Automatic Data Processing (methods), Documentation (methods), Image Enhancement (methods), Image Interpretation, Computer-Assisted (methods), Imaging, Three-Dimensional (methods), Pattern Recognition, Automated (methods), Photography (methods), Reproducibility of Results, Sensitivity and Specificity.
- MESH :
Abstract
Compared to typical scanners, handheld cameras offer convenient, flexible, portable, and non-contact image capture, which enables many new applications and breathes new life into existing ones. However, camera-captured documents may suffer from distortions caused by non-planar document shape and perspective projection, which lead to failure of current OCR technologies. We present a geometric rectification framework for restoring the frontal-flat view of a document from a single camera-captured image. Our approach estimates 3D document shape from texture flow information obtained directly from the image without requiring additional 3D/metric data or prior camera calibration. Our framework provides a unified solution for both planar and curved documents and can be applied in many, especially mobile, camera-based document analysis applications. Experiments show that our method produces results that are significantly more OCR compatible than the original images.
DOI: 10.1109/TPAMI.2007.70724
PubMed: 18276966
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PubMed, to step Corpus: 000052
- to stream PubMed, to step Curation: 000052
- to stream PubMed, to step Checkpoint: 000052
- to stream Ncbi, to step Merge: 000048
- to stream Ncbi, to step Curation: 000048
- to stream Ncbi, to step Checkpoint: 000048
- to stream Main, to step Merge: 000B29
- to stream Main, to step Curation: 000B17
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Geometric rectification of camera-captured document images.</title>
<author><name sortKey="Liang, Jian" sort="Liang, Jian" uniqKey="Liang J" first="Jian" last="Liang">Jian Liang</name>
<affiliation wicri:level="2"><nlm:affiliation>Amazon.com, 701 5th Avenue #614.B, Seattle, WA 98104, USA. jliang@amazon.com</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Amazon.com, 701 5th Avenue #614.B, Seattle, WA 98104</wicri:regionArea>
<placeName><region type="state">Washington (État)</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Dementhon, Daniel" sort="Dementhon, Daniel" uniqKey="Dementhon D" first="Daniel" last="Dementhon">Daniel Dementhon</name>
</author>
<author><name sortKey="Doermann, David" sort="Doermann, David" uniqKey="Doermann D" first="David" last="Doermann">David Doermann</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2008">2008</date>
<idno type="doi">10.1109/TPAMI.2007.70724</idno>
<idno type="RBID">pubmed:18276966</idno>
<idno type="pmid">18276966</idno>
<idno type="wicri:Area/PubMed/Corpus">000052</idno>
<idno type="wicri:Area/PubMed/Curation">000052</idno>
<idno type="wicri:Area/PubMed/Checkpoint">000052</idno>
<idno type="wicri:Area/Ncbi/Merge">000048</idno>
<idno type="wicri:Area/Ncbi/Curation">000048</idno>
<idno type="wicri:Area/Ncbi/Checkpoint">000048</idno>
<idno type="wicri:doubleKey">0162-8828:2008:Liang J:geometric:rectification:of</idno>
<idno type="wicri:Area/Main/Merge">000B29</idno>
<idno type="wicri:Area/Main/Curation">000B17</idno>
<idno type="wicri:Area/Main/Exploration">000B17</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Geometric rectification of camera-captured document images.</title>
<author><name sortKey="Liang, Jian" sort="Liang, Jian" uniqKey="Liang J" first="Jian" last="Liang">Jian Liang</name>
<affiliation wicri:level="2"><nlm:affiliation>Amazon.com, 701 5th Avenue #614.B, Seattle, WA 98104, USA. jliang@amazon.com</nlm:affiliation>
<country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Amazon.com, 701 5th Avenue #614.B, Seattle, WA 98104</wicri:regionArea>
<placeName><region type="state">Washington (État)</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Dementhon, Daniel" sort="Dementhon, Daniel" uniqKey="Dementhon D" first="Daniel" last="Dementhon">Daniel Dementhon</name>
</author>
<author><name sortKey="Doermann, David" sort="Doermann, David" uniqKey="Doermann D" first="David" last="Doermann">David Doermann</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="2008" type="published">2008</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>Documentation (methods)</term>
<term>Image Enhancement (methods)</term>
<term>Image Interpretation, Computer-Assisted (methods)</term>
<term>Imaging, Three-Dimensional (methods)</term>
<term>Pattern Recognition, Automated (methods)</term>
<term>Photography (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>Pattern Recognition, Automated</term>
<term>Photography</term>
</keywords>
<keywords scheme="MESH" xml:lang="en"><term>Algorithms</term>
<term>Artifacts</term>
<term>Artificial Intelligence</term>
<term>Reproducibility of Results</term>
<term>Sensitivity and Specificity</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Compared to typical scanners, handheld cameras offer convenient, flexible, portable, and non-contact image capture, which enables many new applications and breathes new life into existing ones. However, camera-captured documents may suffer from distortions caused by non-planar document shape and perspective projection, which lead to failure of current OCR technologies. We present a geometric rectification framework for restoring the frontal-flat view of a document from a single camera-captured image. Our approach estimates 3D document shape from texture flow information obtained directly from the image without requiring additional 3D/metric data or prior camera calibration. Our framework provides a unified solution for both planar and curved documents and can be applied in many, especially mobile, camera-based document analysis applications. Experiments show that our method produces results that are significantly more OCR compatible than the original images.</div>
</front>
</TEI>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>Washington (État)</li>
</region>
</list>
<tree><noCountry><name sortKey="Dementhon, Daniel" sort="Dementhon, Daniel" uniqKey="Dementhon D" first="Daniel" last="Dementhon">Daniel Dementhon</name>
<name sortKey="Doermann, David" sort="Doermann, David" uniqKey="Doermann D" first="David" last="Doermann">David Doermann</name>
</noCountry>
<country name="États-Unis"><region name="Washington (État)"><name sortKey="Liang, Jian" sort="Liang, Jian" uniqKey="Liang J" first="Jian" last="Liang">Jian Liang</name>
</region>
</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 000B17 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000B17 | 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= pubmed:18276966 |texte= Geometric rectification of camera-captured document images. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:18276966" \ | HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \ | NlmPubMed2Wicri -a OcrV1
This area was generated with Dilib version V0.6.32. |