PINK PANTHER: A COMPLETE ENVIRONMENT FOR GROUND-TRUTHING AND BENCHMARKING DOCUMENT PAGE SEGMENTATION
Identifieur interne : 002109 ( Main/Exploration ); précédent : 002108; suivant : 002110PINK PANTHER: A COMPLETE ENVIRONMENT FOR GROUND-TRUTHING AND BENCHMARKING DOCUMENT PAGE SEGMENTATION
Auteurs : Berrin A. Yanikoglu [États-Unis] ; Luc Vincent [États-Unis]Source :
- Pattern Recognition [ 0031-3203 ] ; 1997.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
We describe a new approach for the automatic evaluation of document page segmentation algorithms. Unlike techniques that rely on OCR output, our method is region-based: segmentation quality is assessed by comparing the segmentation output, described as a set of regions, to the corresponding ground-truth. Error maps are used to keep track of all the errors associated with each pixel, regardless of the document complexity. Misclassifications, splitting, and merging of regions are among the errors detected by the system. Each error can be weighted individually and the system can be customized to benchmark virtually any type of segmentation task.
Url:
DOI: 10.1016/S0031-3203(97)00137-4
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000275
- to stream Istex, to step Curation: 000270
- to stream Istex, to step Checkpoint: 001613
- to stream Main, to step Merge: 002226
- to stream PascalFrancis, to step Corpus: 000858
- to stream PascalFrancis, to step Curation: 000B38
- to stream PascalFrancis, to step Checkpoint: 000818
- to stream Main, to step Merge: 002412
- to stream Main, to step Curation: 002109
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>PINK PANTHER: A COMPLETE ENVIRONMENT FOR GROUND-TRUTHING AND BENCHMARKING DOCUMENT PAGE SEGMENTATION</title><author><name sortKey="Yanikoglu, Berrin A" sort="Yanikoglu, Berrin A" uniqKey="Yanikoglu B" first="Berrin A." last="Yanikoglu">Berrin A. Yanikoglu</name></author><author><name sortKey="Vincent, Luc" sort="Vincent, Luc" uniqKey="Vincent L" first="Luc" last="Vincent">Luc Vincent</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:A9B3D95815AB77E4F32DD782C6F48B935A34A24B</idno><date when="1998" year="1998">1998</date><idno type="doi">10.1016/S0031-3203(97)00137-4</idno><idno type="url">https://api.istex.fr/document/A9B3D95815AB77E4F32DD782C6F48B935A34A24B/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000275</idno><idno type="wicri:Area/Istex/Curation">000270</idno><idno type="wicri:Area/Istex/Checkpoint">001613</idno><idno type="wicri:doubleKey">0031-3203:1998:Yanikoglu B:pink:panther:a</idno><idno type="wicri:Area/Main/Merge">002226</idno><idno type="wicri:source">INIST</idno><idno type="RBID">Pascal:98-0412936</idno><idno type="wicri:Area/PascalFrancis/Corpus">000858</idno><idno type="wicri:Area/PascalFrancis/Curation">000B38</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000818</idno><idno type="wicri:doubleKey">0031-3203:1998:Yanikoglu B:pink:panther:a</idno><idno type="wicri:Area/Main/Merge">002412</idno><idno type="wicri:Area/Main/Curation">002109</idno><idno type="wicri:Area/Main/Exploration">002109</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">PINK PANTHER: A COMPLETE ENVIRONMENT FOR GROUND-TRUTHING AND BENCHMARKING DOCUMENT PAGE SEGMENTATION</title><author><name sortKey="Yanikoglu, Berrin A" sort="Yanikoglu, Berrin A" uniqKey="Yanikoglu B" first="Berrin A." last="Yanikoglu">Berrin A. Yanikoglu</name><affiliation><wicri:noCountry code="no comma">E-mail: berrin@almaden.ibm.com</wicri:noCountry></affiliation><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><wicri:regionArea>IBM Almaden Research Center, 650 Harry Road, San Jose, CA 95120</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author><author><name sortKey="Vincent, Luc" sort="Vincent, Luc" uniqKey="Vincent L" first="Luc" last="Vincent">Luc Vincent</name><affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country><wicri:regionArea>Xerox Desktop Document Systems, 3400 Hillview Avenue, Palo Alto, CA 94304</wicri:regionArea><placeName><region type="state">Californie</region></placeName></affiliation></author></analytic><monogr></monogr><series><title level="j">Pattern Recognition</title><title level="j" type="abbrev">PR</title><idno type="ISSN">0031-3203</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1997">1997</date><biblScope unit="volume">31</biblScope><biblScope unit="issue">9</biblScope><biblScope unit="page" from="1191">1191</biblScope><biblScope unit="page" to="1204">1204</biblScope></imprint><idno type="ISSN">0031-3203</idno></series><idno type="istex">A9B3D95815AB77E4F32DD782C6F48B935A34A24B</idno><idno type="DOI">10.1016/S0031-3203(97)00137-4</idno><idno type="PII">S0031-3203(97)00137-4</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0031-3203</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Bench mark</term><term>Document processing</term><term>Expert system</term><term>Ground truth</term><term>Optical character recognition</term><term>Pagination</term><term>Pattern recognition</term><term>Segmentation</term><term>Utility program</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Cote nivellement</term><term>Pagination</term><term>Programme utilitaire</term><term>Reconnaissance forme</term><term>Reconnaissance optique caractère</term><term>Réalité terrain</term><term>Segmentation</term><term>Système expert</term><term>Traitement document</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">We describe a new approach for the automatic evaluation of document page segmentation algorithms. Unlike techniques that rely on OCR output, our method is region-based: segmentation quality is assessed by comparing the segmentation output, described as a set of regions, to the corresponding ground-truth. Error maps are used to keep track of all the errors associated with each pixel, regardless of the document complexity. Misclassifications, splitting, and merging of regions are among the errors detected by the system. Each error can be weighted individually and the system can be customized to benchmark virtually any type of segmentation task.</div></front></TEI><affiliations><list><country><li>États-Unis</li></country><region><li>Californie</li></region></list><tree><country name="États-Unis"><region name="Californie"><name sortKey="Yanikoglu, Berrin A" sort="Yanikoglu, Berrin A" uniqKey="Yanikoglu B" first="Berrin A." last="Yanikoglu">Berrin A. Yanikoglu</name></region><name sortKey="Vincent, Luc" sort="Vincent, Luc" uniqKey="Vincent L" first="Luc" last="Vincent">Luc Vincent</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 002109 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002109 | 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= ISTEX:A9B3D95815AB77E4F32DD782C6F48B935A34A24B
|texte= PINK PANTHER: A COMPLETE ENVIRONMENT FOR GROUND-TRUTHING AND BENCHMARKING DOCUMENT PAGE SEGMENTATION
}}
| This area was generated with Dilib version V0.6.32. |  |