A new segmentation technique for omnifont Farsi text
Identifieur interne : 001A52 ( Main/Exploration ); précédent : 001A51; suivant : 001A53A new segmentation technique for omnifont Farsi text
Auteurs : R. Azmi [Iran] ; E. Kabir [Iran]Source :
- Pattern Recognition Letters [ 0167-8655 ] ; 1999.
Abstract
A new segmentation algorithm based on the conditional labeling of the upper contour is presented. A pre-processing technique is proposed that adjusts the local base line for each subword. The algorithm was tested on a data set of printed Farsi texts in 20 fonts. 98.5% of the connected characters were correctly segmented.
Url:
DOI: 10.1016/S0167-8655(00)00086-6
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002963
- to stream Istex, to step Curation: 002762
- to stream Istex, to step Checkpoint: 001106
- to stream Main, to step Merge: 001B45
- to stream Main, to step Curation: 001A52
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>A new segmentation technique for omnifont Farsi text</title><author><name sortKey="Azmi, R" sort="Azmi, R" uniqKey="Azmi R" first="R" last="Azmi">R. Azmi</name></author><author><name sortKey="Kabir, E" sort="Kabir, E" uniqKey="Kabir E" first="E" last="Kabir">E. Kabir</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:1F1FB991B7ADFC2BFCBC50F8D984CF157BE91CDF</idno><date when="2001" year="2001">2001</date><idno type="doi">10.1016/S0167-8655(00)00086-6</idno><idno type="url">https://api.istex.fr/document/1F1FB991B7ADFC2BFCBC50F8D984CF157BE91CDF/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">002963</idno><idno type="wicri:Area/Istex/Curation">002762</idno><idno type="wicri:Area/Istex/Checkpoint">001106</idno><idno type="wicri:doubleKey">0167-8655:2001:Azmi R:a:new:segmentation</idno><idno type="wicri:Area/Main/Merge">001B45</idno><idno type="wicri:Area/Main/Curation">001A52</idno><idno type="wicri:Area/Main/Exploration">001A52</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">A new segmentation technique for omnifont Farsi text</title><author><name sortKey="Azmi, R" sort="Azmi, R" uniqKey="Azmi R" first="R" last="Azmi">R. Azmi</name><affiliation wicri:level="1"><country xml:lang="fr">Iran</country><wicri:regionArea>Department of Electrical Engineering, Tarbiat Modarres University, P.O. Box 14115-143, Tehran</wicri:regionArea><wicri:noRegion>Tehran</wicri:noRegion></affiliation></author><author><name sortKey="Kabir, E" sort="Kabir, E" uniqKey="Kabir E" first="E" last="Kabir">E. Kabir</name><affiliation wicri:level="1"><country xml:lang="fr">Iran</country><wicri:regionArea>Department of Electrical Engineering, Tarbiat Modarres University, P.O. Box 14115-143, Tehran</wicri:regionArea><wicri:noRegion>Tehran</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Iran</country></affiliation></author></analytic><monogr></monogr><series><title level="j">Pattern Recognition Letters</title><title level="j" type="abbrev">PATREC</title><idno type="ISSN">0167-8655</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1999">1999</date><biblScope unit="volume">22</biblScope><biblScope unit="issue">2</biblScope><biblScope unit="page" from="97">97</biblScope><biblScope unit="page" to="104">104</biblScope></imprint><idno type="ISSN">0167-8655</idno></series><idno type="istex">1F1FB991B7ADFC2BFCBC50F8D984CF157BE91CDF</idno><idno type="DOI">10.1016/S0167-8655(00)00086-6</idno><idno type="PII">S0167-8655(00)00086-6</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0167-8655</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">A new segmentation algorithm based on the conditional labeling of the upper contour is presented. A pre-processing technique is proposed that adjusts the local base line for each subword. The algorithm was tested on a data set of printed Farsi texts in 20 fonts. 98.5% of the connected characters were correctly segmented.</div></front></TEI><affiliations><list><country><li>Iran</li></country></list><tree><country name="Iran"><noRegion><name sortKey="Azmi, R" sort="Azmi, R" uniqKey="Azmi R" first="R" last="Azmi">R. Azmi</name></noRegion><name sortKey="Kabir, E" sort="Kabir, E" uniqKey="Kabir E" first="E" last="Kabir">E. Kabir</name><name sortKey="Kabir, E" sort="Kabir, E" uniqKey="Kabir E" first="E" last="Kabir">E. Kabir</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 001A52 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001A52 | 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:1F1FB991B7ADFC2BFCBC50F8D984CF157BE91CDF
|texte= A new segmentation technique for omnifont Farsi text
}}
| This area was generated with Dilib version V0.6.32. |  |