Arabic character recognition using fourier descriptors and character contour encoding
Identifieur interne : 000209 ( Istex/Corpus ); précédent : 000208; suivant : 000210Arabic character recognition using fourier descriptors and character contour encoding
Auteurs : Sabri A. MahmoudSource :
- Pattern Recognition [ 0031-3203 ] ; 1993.
Abstract
Normalized Fourier descriptors are known to be invariant to scale, translation, and rotation. This technique was used by researchers of Latin OCR yielding acceptable results. In addition, contour analysis was used in object recognition with success. Both techniques are adopted as they are necessary for the recognition of Arabic characters with acceptable recognition rates. This combination was deemed necessary due to the special characteristics of Arabic characters that have some very similar characters. The character images are smoothed by a statistically-based algorithm to eliminate noise. Then, the contours of the image (namely the character primary part, the dots, and hole contours) are extracted. Fourier descriptors and curvature features of the primary part of the character are computed. These features of the training set are used as the model features. The features of an input character are compared to the models' features using a distance measure. The model with the minimum distance is taken as the class representing the character. The dots' and holes' features are then used to specify the particular character. Experimental results have shown that the combination of the Fourier descriptors, the curvature features and the use of dots' and holes' features to be powerful in successfully classifying Arabic characters. Recognition rates of 100% were achieved for the model classes. However, this rate has come down to 98% in the post-recognition phase of identifying the specific characters. The major part of these errors come from corrupted data.
Url:
DOI: 10.1016/0031-3203(94)90166-X
Links to Exploration step
ISTEX:5CFA95A6CE082E7A147A16B2B6D5C27C27681127Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Arabic character recognition using fourier descriptors and character contour encoding</title>
<author><name sortKey="Mahmoud, Sabri A" sort="Mahmoud, Sabri A" uniqKey="Mahmoud S" first="Sabri A." last="Mahmoud">Sabri A. Mahmoud</name>
<affiliation><mods:affiliation>Computer Engineering Department, College of Computers and Information Sciences, King Saud University, P.O. Box 51405, Riyadh 11543, Saudi Arabia</mods:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:5CFA95A6CE082E7A147A16B2B6D5C27C27681127</idno>
<date when="1994" year="1994">1994</date>
<idno type="doi">10.1016/0031-3203(94)90166-X</idno>
<idno type="url">https://api.istex.fr/document/5CFA95A6CE082E7A147A16B2B6D5C27C27681127/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000209</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a">Arabic character recognition using fourier descriptors and character contour encoding</title>
<author><name sortKey="Mahmoud, Sabri A" sort="Mahmoud, Sabri A" uniqKey="Mahmoud S" first="Sabri A." last="Mahmoud">Sabri A. Mahmoud</name>
<affiliation><mods:affiliation>Computer Engineering Department, College of Computers and Information Sciences, King Saud University, P.O. Box 51405, Riyadh 11543, Saudi Arabia</mods:affiliation>
</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="1993">1993</date>
<biblScope unit="volume">27</biblScope>
<biblScope unit="issue">6</biblScope>
<biblScope unit="page" from="815">815</biblScope>
<biblScope unit="page" to="824">824</biblScope>
</imprint>
<idno type="ISSN">0031-3203</idno>
</series>
<idno type="istex">5CFA95A6CE082E7A147A16B2B6D5C27C27681127</idno>
<idno type="DOI">10.1016/0031-3203(94)90166-X</idno>
<idno type="PII">0031-3203(94)90166-X</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0031-3203</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Normalized Fourier descriptors are known to be invariant to scale, translation, and rotation. This technique was used by researchers of Latin OCR yielding acceptable results. In addition, contour analysis was used in object recognition with success. Both techniques are adopted as they are necessary for the recognition of Arabic characters with acceptable recognition rates. This combination was deemed necessary due to the special characteristics of Arabic characters that have some very similar characters. The character images are smoothed by a statistically-based algorithm to eliminate noise. Then, the contours of the image (namely the character primary part, the dots, and hole contours) are extracted. Fourier descriptors and curvature features of the primary part of the character are computed. These features of the training set are used as the model features. The features of an input character are compared to the models' features using a distance measure. The model with the minimum distance is taken as the class representing the character. The dots' and holes' features are then used to specify the particular character. Experimental results have shown that the combination of the Fourier descriptors, the curvature features and the use of dots' and holes' features to be powerful in successfully classifying Arabic characters. Recognition rates of 100% were achieved for the model classes. However, this rate has come down to 98% in the post-recognition phase of identifying the specific characters. The major part of these errors come from corrupted data.</div>
</front>
</TEI>
<istex><corpusName>elsevier</corpusName>
<author><json:item><name>Sabri A. Mahmoud</name>
<affiliations><json:string>Computer Engineering Department, College of Computers and Information Sciences, King Saud University, P.O. Box 51405, Riyadh 11543, Saudi Arabia</json:string>
</affiliations>
</json:item>
</author>
<subject><json:item><lang><json:string>eng</json:string>
</lang>
<value>Arabic character recognition</value>
</json:item>
<json:item><lang><json:string>eng</json:string>
</lang>
<value>OCR</value>
</json:item>
<json:item><lang><json:string>eng</json:string>
</lang>
<value>Fourier descriptors</value>
</json:item>
<json:item><lang><json:string>eng</json:string>
</lang>
<value>Contour analysis</value>
</json:item>
<json:item><lang><json:string>eng</json:string>
</lang>
<value>Curvature features</value>
</json:item>
<json:item><lang><json:string>eng</json:string>
</lang>
<value>Direction features</value>
</json:item>
</subject>
<language><json:string>eng</json:string>
</language>
<abstract>Normalized Fourier descriptors are known to be invariant to scale, translation, and rotation. This technique was used by researchers of Latin OCR yielding acceptable results. In addition, contour analysis was used in object recognition with success. Both techniques are adopted as they are necessary for the recognition of Arabic characters with acceptable recognition rates. This combination was deemed necessary due to the special characteristics of Arabic characters that have some very similar characters. The character images are smoothed by a statistically-based algorithm to eliminate noise. Then, the contours of the image (namely the character primary part, the dots, and hole contours) are extracted. Fourier descriptors and curvature features of the primary part of the character are computed. These features of the training set are used as the model features. The features of an input character are compared to the models' features using a distance measure. The model with the minimum distance is taken as the class representing the character. The dots' and holes' features are then used to specify the particular character. Experimental results have shown that the combination of the Fourier descriptors, the curvature features and the use of dots' and holes' features to be powerful in successfully classifying Arabic characters. Recognition rates of 100% were achieved for the model classes. However, this rate has come down to 98% in the post-recognition phase of identifying the specific characters. The major part of these errors come from corrupted data.</abstract>
<qualityIndicators><score>7.868</score>
<pdfVersion>1.2</pdfVersion>
<pdfPageSize>533 x 778 pts</pdfPageSize>
<refBibsNative>true</refBibsNative>
<keywordCount>6</keywordCount>
<abstractCharCount>1573</abstractCharCount>
<pdfWordCount>6683</pdfWordCount>
<pdfCharCount>37672</pdfCharCount>
<pdfPageCount>10</pdfPageCount>
<abstractWordCount>239</abstractWordCount>
</qualityIndicators>
<title>Arabic character recognition using fourier descriptors and character contour encoding</title>
<pii><json:string>0031-3203(94)90166-X</json:string>
</pii>
<genre><json:string>research-article</json:string>
</genre>
<serie><pages><last>336</last>
<first>330</first>
</pages>
<conference><json:item><name>Proc. SPIE 22nd Annual Technical Symp. on Optical and Optoelectronics Applied Science and Engineering - San Diego, California</name>
</json:item>
</conference>
<genre></genre>
<language><json:string>unknown</json:string>
</language>
<title>Proc. SPIE 22nd Annual Technical Symp. on Optical and Optoelectronics Applied Science and Engineering</title>
</serie>
<host><volume>27</volume>
<pii><json:string>S0031-3203(00)X0235-X</json:string>
</pii>
<pages><last>824</last>
<first>815</first>
</pages>
<issn><json:string>0031-3203</json:string>
</issn>
<issue>6</issue>
<genre><json:string>Journal</json:string>
</genre>
<language><json:string>unknown</json:string>
</language>
<title>Pattern Recognition</title>
<publicationDate>1994</publicationDate>
</host>
<categories><wos><json:string>COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</json:string>
<json:string>ENGINEERING, ELECTRICAL & ELECTRONIC</json:string>
</wos>
</categories>
<publicationDate>1993</publicationDate>
<copyrightDate>1994</copyrightDate>
<doi><json:string>10.1016/0031-3203(94)90166-X</json:string>
</doi>
<id>5CFA95A6CE082E7A147A16B2B6D5C27C27681127</id>
<fulltext><json:item><original>true</original>
<mimetype>application/pdf</mimetype>
<extension>pdf</extension>
<uri>https://api.istex.fr/document/5CFA95A6CE082E7A147A16B2B6D5C27C27681127/fulltext/pdf</uri>
</json:item>
<json:item><original>true</original>
<mimetype>text/plain</mimetype>
<extension>txt</extension>
<uri>https://api.istex.fr/document/5CFA95A6CE082E7A147A16B2B6D5C27C27681127/fulltext/txt</uri>
</json:item>
<json:item><original>false</original>
<mimetype>application/zip</mimetype>
<extension>zip</extension>
<uri>https://api.istex.fr/document/5CFA95A6CE082E7A147A16B2B6D5C27C27681127/fulltext/zip</uri>
</json:item>
<istex:fulltextTEI uri="https://api.istex.fr/document/5CFA95A6CE082E7A147A16B2B6D5C27C27681127/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a">Arabic character recognition using fourier descriptors and character contour encoding</title>
</titleStmt>
<publicationStmt><authority>ISTEX</authority>
<publisher>ELSEVIER</publisher>
<availability><p>ELSEVIER</p>
</availability>
<date>1994</date>
</publicationStmt>
<sourceDesc><biblStruct type="inbook"><analytic><title level="a">Arabic character recognition using fourier descriptors and character contour encoding</title>
<author><persName><forename type="first">Sabri A.</forename>
<surname>Mahmoud</surname>
</persName>
<affiliation>Computer Engineering Department, College of Computers and Information Sciences, King Saud University, P.O. Box 51405, Riyadh 11543, Saudi Arabia</affiliation>
</author>
</analytic>
<monogr><title level="j">Pattern Recognition</title>
<title level="j" type="abbrev">PR</title>
<idno type="pISSN">0031-3203</idno>
<idno type="PII">S0031-3203(00)X0235-X</idno>
<imprint><publisher>ELSEVIER</publisher>
<date type="published" when="1993"></date>
<biblScope unit="volume">27</biblScope>
<biblScope unit="issue">6</biblScope>
<biblScope unit="page" from="815">815</biblScope>
<biblScope unit="page" to="824">824</biblScope>
</imprint>
</monogr>
<idno type="istex">5CFA95A6CE082E7A147A16B2B6D5C27C27681127</idno>
<idno type="DOI">10.1016/0031-3203(94)90166-X</idno>
<idno type="PII">0031-3203(94)90166-X</idno>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><creation><date>1994</date>
</creation>
<langUsage><language ident="en">en</language>
</langUsage>
<abstract xml:lang="en"><p>Normalized Fourier descriptors are known to be invariant to scale, translation, and rotation. This technique was used by researchers of Latin OCR yielding acceptable results. In addition, contour analysis was used in object recognition with success. Both techniques are adopted as they are necessary for the recognition of Arabic characters with acceptable recognition rates. This combination was deemed necessary due to the special characteristics of Arabic characters that have some very similar characters. The character images are smoothed by a statistically-based algorithm to eliminate noise. Then, the contours of the image (namely the character primary part, the dots, and hole contours) are extracted. Fourier descriptors and curvature features of the primary part of the character are computed. These features of the training set are used as the model features. The features of an input character are compared to the models' features using a distance measure. The model with the minimum distance is taken as the class representing the character. The dots' and holes' features are then used to specify the particular character. Experimental results have shown that the combination of the Fourier descriptors, the curvature features and the use of dots' and holes' features to be powerful in successfully classifying Arabic characters. Recognition rates of 100% were achieved for the model classes. However, this rate has come down to 98% in the post-recognition phase of identifying the specific characters. The major part of these errors come from corrupted data.</p>
</abstract>
<textClass><keywords scheme="keyword"><list><head>Keywords</head>
<item><term>Arabic character recognition</term>
</item>
<item><term>OCR</term>
</item>
<item><term>Fourier descriptors</term>
</item>
<item><term>Contour analysis</term>
</item>
<item><term>Curvature features</term>
</item>
<item><term>Direction features</term>
</item>
</list>
</keywords>
</textClass>
</profileDesc>
<revisionDesc><change when="1993-12-02">Registration</change>
<change when="1993-11-24">Modified</change>
<change when="1993">Published</change>
</revisionDesc>
</teiHeader>
</istex:fulltextTEI>
</fulltext>
<metadata><istex:metadataXml wicri:clean="Elsevier, elements deleted: tail"><istex:xmlDeclaration>version="1.0" encoding="utf-8"</istex:xmlDeclaration>
<istex:docType PUBLIC="-//ES//DTD journal article DTD version 4.5.2//EN//XML" URI="art452.dtd" name="istex:docType"></istex:docType>
<istex:document><converted-article version="4.5.2" docsubtype="fla"><item-info><jid>PR</jid>
<aid>9490166X</aid>
<ce:pii>0031-3203(94)90166-X</ce:pii>
<ce:doi>10.1016/0031-3203(94)90166-X</ce:doi>
<ce:copyright type="unknown" year="1994"></ce:copyright>
</item-info>
<head><ce:title>Arabic character recognition using fourier descriptors and character contour encoding</ce:title>
<ce:author-group><ce:author><ce:given-name>Sabri A.</ce:given-name>
<ce:surname>Mahmoud</ce:surname>
</ce:author>
<ce:affiliation><ce:textfn>Computer Engineering Department, College of Computers and Information Sciences, King Saud University, P.O. Box 51405, Riyadh 11543, Saudi Arabia</ce:textfn>
</ce:affiliation>
</ce:author-group>
<ce:date-received day="25" month="1" year="1993"></ce:date-received>
<ce:date-revised day="24" month="11" year="1993"></ce:date-revised>
<ce:date-accepted day="2" month="12" year="1993"></ce:date-accepted>
<ce:abstract><ce:section-title>Abstract</ce:section-title>
<ce:abstract-sec><ce:simple-para>Normalized Fourier descriptors are known to be invariant to scale, translation, and rotation. This technique was used by researchers of Latin OCR yielding acceptable results. In addition, contour analysis was used in object recognition with success. Both techniques are adopted as they are necessary for the recognition of Arabic characters with acceptable recognition rates. This combination was deemed necessary due to the special characteristics of Arabic characters that have some very similar characters. The character images are smoothed by a statistically-based algorithm to eliminate noise. Then, the contours of the image (namely the character primary part, the dots, and hole contours) are extracted. Fourier descriptors and curvature features of the primary part of the character are computed. These features of the training set are used as the model features. The features of an input character are compared to the models' features using a distance measure. The model with the minimum distance is taken as the class representing the character. The dots' and holes' features are then used to specify the particular character. Experimental results have shown that the combination of the Fourier descriptors, the curvature features and the use of dots' and holes' features to be powerful in successfully classifying Arabic characters. Recognition rates of 100% were achieved for the model classes. However, this rate has come down to 98% in the post-recognition phase of identifying the specific characters. The major part of these errors come from corrupted data.</ce:simple-para>
</ce:abstract-sec>
</ce:abstract>
<ce:keywords><ce:section-title>Keywords</ce:section-title>
<ce:keyword><ce:text>Arabic character recognition</ce:text>
</ce:keyword>
<ce:keyword><ce:text>OCR</ce:text>
</ce:keyword>
<ce:keyword><ce:text>Fourier descriptors</ce:text>
</ce:keyword>
<ce:keyword><ce:text>Contour analysis</ce:text>
</ce:keyword>
<ce:keyword><ce:text>Curvature features</ce:text>
</ce:keyword>
<ce:keyword><ce:text>Direction features</ce:text>
</ce:keyword>
</ce:keywords>
</head>
</converted-article>
</istex:document>
</istex:metadataXml>
<mods version="3.6"><titleInfo><title>Arabic character recognition using fourier descriptors and character contour encoding</title>
</titleInfo>
<titleInfo type="alternative" contentType="CDATA"><title>Arabic character recognition using fourier descriptors and character contour encoding</title>
</titleInfo>
<name type="personal"><namePart type="given">Sabri A.</namePart>
<namePart type="family">Mahmoud</namePart>
<affiliation>Computer Engineering Department, College of Computers and Information Sciences, King Saud University, P.O. Box 51405, Riyadh 11543, Saudi Arabia</affiliation>
<role><roleTerm type="text">author</roleTerm>
</role>
</name>
<typeOfResource>text</typeOfResource>
<genre type="research-article" displayLabel="Full-length article"></genre>
<originInfo><publisher>ELSEVIER</publisher>
<dateIssued encoding="w3cdtf">1993</dateIssued>
<dateValid encoding="w3cdtf">1993-12-02</dateValid>
<dateModified encoding="w3cdtf">1993-11-24</dateModified>
<copyrightDate encoding="w3cdtf">1994</copyrightDate>
</originInfo>
<language><languageTerm type="code" authority="iso639-2b">eng</languageTerm>
<languageTerm type="code" authority="rfc3066">en</languageTerm>
</language>
<physicalDescription><internetMediaType>text/html</internetMediaType>
</physicalDescription>
<abstract lang="en">Normalized Fourier descriptors are known to be invariant to scale, translation, and rotation. This technique was used by researchers of Latin OCR yielding acceptable results. In addition, contour analysis was used in object recognition with success. Both techniques are adopted as they are necessary for the recognition of Arabic characters with acceptable recognition rates. This combination was deemed necessary due to the special characteristics of Arabic characters that have some very similar characters. The character images are smoothed by a statistically-based algorithm to eliminate noise. Then, the contours of the image (namely the character primary part, the dots, and hole contours) are extracted. Fourier descriptors and curvature features of the primary part of the character are computed. These features of the training set are used as the model features. The features of an input character are compared to the models' features using a distance measure. The model with the minimum distance is taken as the class representing the character. The dots' and holes' features are then used to specify the particular character. Experimental results have shown that the combination of the Fourier descriptors, the curvature features and the use of dots' and holes' features to be powerful in successfully classifying Arabic characters. Recognition rates of 100% were achieved for the model classes. However, this rate has come down to 98% in the post-recognition phase of identifying the specific characters. The major part of these errors come from corrupted data.</abstract>
<subject><genre>Keywords</genre>
<topic>Arabic character recognition</topic>
<topic>OCR</topic>
<topic>Fourier descriptors</topic>
<topic>Contour analysis</topic>
<topic>Curvature features</topic>
<topic>Direction features</topic>
</subject>
<relatedItem type="host"><titleInfo><title>Pattern Recognition</title>
</titleInfo>
<titleInfo type="abbreviated"><title>PR</title>
</titleInfo>
<genre type="Journal">journal</genre>
<originInfo><dateIssued encoding="w3cdtf">199406</dateIssued>
</originInfo>
<identifier type="ISSN">0031-3203</identifier>
<identifier type="PII">S0031-3203(00)X0235-X</identifier>
<part><date>199406</date>
<detail type="volume"><number>27</number>
<caption>vol.</caption>
</detail>
<detail type="issue"><number>6</number>
<caption>no.</caption>
</detail>
<extent unit="issue pages"><start>765</start>
<end>865</end>
</extent>
<extent unit="pages"><start>815</start>
<end>824</end>
</extent>
</part>
</relatedItem>
<identifier type="istex">5CFA95A6CE082E7A147A16B2B6D5C27C27681127</identifier>
<identifier type="DOI">10.1016/0031-3203(94)90166-X</identifier>
<identifier type="PII">0031-3203(94)90166-X</identifier>
<recordInfo><recordContentSource>ELSEVIER</recordContentSource>
</recordInfo>
</mods>
</metadata>
<enrichments><istex:catWosTEI uri="https://api.istex.fr/document/5CFA95A6CE082E7A147A16B2B6D5C27C27681127/enrichments/catWos"><teiHeader><profileDesc><textClass><classCode scheme="WOS">COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</classCode>
<classCode scheme="WOS">ENGINEERING, ELECTRICAL & ELECTRONIC</classCode>
</textClass>
</profileDesc>
</teiHeader>
</istex:catWosTEI>
</enrichments>
</istex>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000209 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 000209 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Istex |étape= Corpus |type= RBID |clé= ISTEX:5CFA95A6CE082E7A147A16B2B6D5C27C27681127 |texte= Arabic character recognition using fourier descriptors and character contour encoding }}
![]() | This area was generated with Dilib version V0.6.32. | ![]() |