Evaluation of Binarization Algorithms for Camera-Based Devices
Identifieur interne : 000479 ( Main/Exploration ); précédent : 000478; suivant : 000480Evaluation of Binarization Algorithms for Camera-Based Devices
Auteurs : M. Nava-Ortiz [Mexique] ; W. G Mez-Flores [Mexique] ; A. Díaz-Pérez [Mexique] ; G. Toscano-Pulido [Mexique]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2011.
Abstract
Abstract: Segmentation is an important step within optical character recognition systems, since the recognition rates depends strongly on the accuracy of binarization techniques. Hence, it is necessary to evaluate different segmentation methods for selecting the most adequate for a specific application. However, when gold patterns are not available for comparing the binarized outputs, the recognition rates of the entire system could be used for assessing the performance. In this article we present the evaluation of five local adaptive binarization methods for digit recognition in water meters by measuring misclassification rates. These methods were studied due to of their simplicity to be implemented in based-camera devices, such as cell phones, with limited hardware capabilities. The obtained results pointed out that Bernsens method achieved the best recognition rates when the normalized central moments are employed as features.
Url:
DOI: 10.1007/978-3-642-21587-2_18
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000123
- to stream Istex, to step Curation: 000121
- to stream Istex, to step Checkpoint: 000136
- to stream Main, to step Merge: 000485
- to stream Main, to step Curation: 000479
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Evaluation of Binarization Algorithms for Camera-Based Devices</title><author><name sortKey="Nava Ortiz, M" sort="Nava Ortiz, M" uniqKey="Nava Ortiz M" first="M." last="Nava-Ortiz">M. Nava-Ortiz</name></author><author><name sortKey="G Mez Flores, W" sort="G Mez Flores, W" uniqKey="G Mez Flores W" first="W." last="G Mez-Flores">W. G Mez-Flores</name></author><author><name sortKey="Diaz Perez, A" sort="Diaz Perez, A" uniqKey="Diaz Perez A" first="A." last="Díaz-Pérez">A. Díaz-Pérez</name></author><author><name sortKey="Toscano Pulido, G" sort="Toscano Pulido, G" uniqKey="Toscano Pulido G" first="G." last="Toscano-Pulido">G. Toscano-Pulido</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:301A444F3CD1100189D4E65FBB5B6A7090AC6460</idno><date when="2011" year="2011">2011</date><idno type="doi">10.1007/978-3-642-21587-2_18</idno><idno type="url">https://api.istex.fr/document/301A444F3CD1100189D4E65FBB5B6A7090AC6460/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000123</idno><idno type="wicri:Area/Istex/Curation">000121</idno><idno type="wicri:Area/Istex/Checkpoint">000136</idno><idno type="wicri:doubleKey">0302-9743:2011:Nava Ortiz M:evaluation:of:binarization</idno><idno type="wicri:Area/Main/Merge">000485</idno><idno type="wicri:Area/Main/Curation">000479</idno><idno type="wicri:Area/Main/Exploration">000479</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Evaluation of Binarization Algorithms for Camera-Based Devices</title><author><name sortKey="Nava Ortiz, M" sort="Nava Ortiz, M" uniqKey="Nava Ortiz M" first="M." last="Nava-Ortiz">M. Nava-Ortiz</name><affiliation wicri:level="1"><country xml:lang="fr">Mexique</country><wicri:regionArea>Information Technology Laboratory, CINVESTAV-IPN, Ciudad Victoria</wicri:regionArea><wicri:noRegion>Ciudad Victoria</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Mexique</country></affiliation></author><author><name sortKey="G Mez Flores, W" sort="G Mez Flores, W" uniqKey="G Mez Flores W" first="W." last="G Mez-Flores">W. G Mez-Flores</name><affiliation wicri:level="1"><country xml:lang="fr">Mexique</country><wicri:regionArea>Information Technology Laboratory, CINVESTAV-IPN, Ciudad Victoria</wicri:regionArea><wicri:noRegion>Ciudad Victoria</wicri:noRegion></affiliation></author><author><name sortKey="Diaz Perez, A" sort="Diaz Perez, A" uniqKey="Diaz Perez A" first="A." last="Díaz-Pérez">A. Díaz-Pérez</name><affiliation wicri:level="1"><country xml:lang="fr">Mexique</country><wicri:regionArea>Information Technology Laboratory, CINVESTAV-IPN, Ciudad Victoria</wicri:regionArea><wicri:noRegion>Ciudad Victoria</wicri:noRegion></affiliation></author><author><name sortKey="Toscano Pulido, G" sort="Toscano Pulido, G" uniqKey="Toscano Pulido G" first="G." last="Toscano-Pulido">G. Toscano-Pulido</name><affiliation wicri:level="1"><country xml:lang="fr">Mexique</country><wicri:regionArea>Information Technology Laboratory, CINVESTAV-IPN, Ciudad Victoria</wicri:regionArea><wicri:noRegion>Ciudad Victoria</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2011</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">301A444F3CD1100189D4E65FBB5B6A7090AC6460</idno><idno type="DOI">10.1007/978-3-642-21587-2_18</idno><idno type="ChapterID">18</idno><idno type="ChapterID">Chap18</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: Segmentation is an important step within optical character recognition systems, since the recognition rates depends strongly on the accuracy of binarization techniques. Hence, it is necessary to evaluate different segmentation methods for selecting the most adequate for a specific application. However, when gold patterns are not available for comparing the binarized outputs, the recognition rates of the entire system could be used for assessing the performance. In this article we present the evaluation of five local adaptive binarization methods for digit recognition in water meters by measuring misclassification rates. These methods were studied due to of their simplicity to be implemented in based-camera devices, such as cell phones, with limited hardware capabilities. The obtained results pointed out that Bernsens method achieved the best recognition rates when the normalized central moments are employed as features.</div></front></TEI><affiliations><list><country><li>Mexique</li></country></list><tree><country name="Mexique"><noRegion><name sortKey="Nava Ortiz, M" sort="Nava Ortiz, M" uniqKey="Nava Ortiz M" first="M." last="Nava-Ortiz">M. Nava-Ortiz</name></noRegion><name sortKey="Diaz Perez, A" sort="Diaz Perez, A" uniqKey="Diaz Perez A" first="A." last="Díaz-Pérez">A. Díaz-Pérez</name><name sortKey="G Mez Flores, W" sort="G Mez Flores, W" uniqKey="G Mez Flores W" first="W." last="G Mez-Flores">W. G Mez-Flores</name><name sortKey="Nava Ortiz, M" sort="Nava Ortiz, M" uniqKey="Nava Ortiz M" first="M." last="Nava-Ortiz">M. Nava-Ortiz</name><name sortKey="Toscano Pulido, G" sort="Toscano Pulido, G" uniqKey="Toscano Pulido G" first="G." last="Toscano-Pulido">G. Toscano-Pulido</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 000479 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000479 | 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:301A444F3CD1100189D4E65FBB5B6A7090AC6460
|texte= Evaluation of Binarization Algorithms for Camera-Based Devices
}}
| This area was generated with Dilib version V0.6.32. |  |