Non-uniform slant estimation and correction for Farsi/Arabic handwritten words
Identifieur interne : 000A74 ( Main/Exploration ); précédent : 000A73; suivant : 000A75Non-uniform slant estimation and correction for Farsi/Arabic handwritten words
Auteurs : Majid Ziaratban [Iran] ; Karim Faez [Iran]Source :
- International journal on document analysis and recognition : (Print) [ 1433-2833 ] ; 2009.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
Slant correction is an important part of the normalization task in OCR applications. Due to some special specifications of Farsi and Arabic manuscripts, conventional deslanting methods proposed for other languages do not work properly. In this paper, a fast method is first introduced to estimate the overall tilt of a handwritten word based on directional filters. After overall deslanting, a novel non-uniform slant estimation algorithm computes the remaining slant of each near-vertical stroke of the-word, separately. Each candidate stroke is traced and its slant is calculated. A non-uniform slant correction algorithm is also proposed to reduce the remaining slants of each candidate stroke keeping the dis- tortions of other strokes of the word at a minimum level. Thanks to the special characteristics of Farsi/Arabic scripts, slants are estimated in a specific strip of the written words. A comparison between our approach and three other prevalent methods is drawn. Experiments show that the proposed overall slant estimation method not only represents the least estimation error, but is also the fastest algorithm. The best results are achieved using the proposed overall and non-uniform deslanting methods. It is concluded that successful results can be achieved by considering the special specifications of these two languages.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000191
- to stream PascalFrancis, to step Curation: 000586
- to stream PascalFrancis, to step Checkpoint: 000189
- to stream Main, to step Merge: 000A83
- to stream Main, to step Curation: 000A74
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Non-uniform slant estimation and correction for Farsi/Arabic handwritten words</title>
<author><name sortKey="Ziaratban, Majid" sort="Ziaratban, Majid" uniqKey="Ziaratban M" first="Majid" last="Ziaratban">Majid Ziaratban</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Electrical Engineering Department, Amirkabir University of Technology, 424 Hafez Ave</s1>
<s2>15916-34311 Tehran</s2>
<s3>IRN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Iran</country>
<wicri:noRegion>15916-34311 Tehran</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Faez, Karim" sort="Faez, Karim" uniqKey="Faez K" first="Karim" last="Faez">Karim Faez</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Electrical Engineering Department, Amirkabir University of Technology, 424 Hafez Ave</s1>
<s2>15916-34311 Tehran</s2>
<s3>IRN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Iran</country>
<wicri:noRegion>15916-34311 Tehran</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">10-0182400</idno>
<date when="2009">2009</date>
<idno type="stanalyst">PASCAL 10-0182400 INIST</idno>
<idno type="RBID">Pascal:10-0182400</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000191</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000586</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000189</idno>
<idno type="wicri:doubleKey">1433-2833:2009:Ziaratban M:non:uniform:slant</idno>
<idno type="wicri:Area/Main/Merge">000A83</idno>
<idno type="wicri:Area/Main/Curation">000A74</idno>
<idno type="wicri:Area/Main/Exploration">000A74</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Non-uniform slant estimation and correction for Farsi/Arabic handwritten words</title>
<author><name sortKey="Ziaratban, Majid" sort="Ziaratban, Majid" uniqKey="Ziaratban M" first="Majid" last="Ziaratban">Majid Ziaratban</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Electrical Engineering Department, Amirkabir University of Technology, 424 Hafez Ave</s1>
<s2>15916-34311 Tehran</s2>
<s3>IRN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Iran</country>
<wicri:noRegion>15916-34311 Tehran</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Faez, Karim" sort="Faez, Karim" uniqKey="Faez K" first="Karim" last="Faez">Karim Faez</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Electrical Engineering Department, Amirkabir University of Technology, 424 Hafez Ave</s1>
<s2>15916-34311 Tehran</s2>
<s3>IRN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Iran</country>
<wicri:noRegion>15916-34311 Tehran</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">International journal on document analysis and recognition : (Print)</title>
<title level="j" type="abbreviated">Int. j. doc. anal. recognit. : (Print)</title>
<idno type="ISSN">1433-2833</idno>
<imprint><date when="2009">2009</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">International journal on document analysis and recognition : (Print)</title>
<title level="j" type="abbreviated">Int. j. doc. anal. recognit. : (Print)</title>
<idno type="ISSN">1433-2833</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Arabic</term>
<term>Character recognition</term>
<term>Error correction</term>
<term>Error estimation</term>
<term>Estimation error</term>
<term>Manuscript character</term>
<term>Optical character recognition</term>
<term>Specification language</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance optique caractère</term>
<term>Caractère manuscrit</term>
<term>Reconnaissance caractère</term>
<term>Langage spécification</term>
<term>Arabe</term>
<term>Correction erreur</term>
<term>Erreur estimation</term>
<term>Estimation erreur</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Slant correction is an important part of the normalization task in OCR applications. Due to some special specifications of Farsi and Arabic manuscripts, conventional deslanting methods proposed for other languages do not work properly. In this paper, a fast method is first introduced to estimate the overall tilt of a handwritten word based on directional filters. After overall deslanting, a novel non-uniform slant estimation algorithm computes the remaining slant of each near-vertical stroke of the-word, separately. Each candidate stroke is traced and its slant is calculated. A non-uniform slant correction algorithm is also proposed to reduce the remaining slants of each candidate stroke keeping the dis- tortions of other strokes of the word at a minimum level. Thanks to the special characteristics of Farsi/Arabic scripts, slants are estimated in a specific strip of the written words. A comparison between our approach and three other prevalent methods is drawn. Experiments show that the proposed overall slant estimation method not only represents the least estimation error, but is also the fastest algorithm. The best results are achieved using the proposed overall and non-uniform deslanting methods. It is concluded that successful results can be achieved by considering the special specifications of these two languages.</div>
</front>
</TEI>
<affiliations><list><country><li>Iran</li>
</country>
</list>
<tree><country name="Iran"><noRegion><name sortKey="Ziaratban, Majid" sort="Ziaratban, Majid" uniqKey="Ziaratban M" first="Majid" last="Ziaratban">Majid Ziaratban</name>
</noRegion>
<name sortKey="Faez, Karim" sort="Faez, Karim" uniqKey="Faez K" first="Karim" last="Faez">Karim Faez</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 000A74 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000A74 | 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= Pascal:10-0182400 |texte= Non-uniform slant estimation and correction for Farsi/Arabic handwritten words }}
This area was generated with Dilib version V0.6.32. |