Arabic character recognition using 1-D slices of the character spectrum
Identifieur interne : 002440 ( Main/Exploration ); précédent : 002439; suivant : 002441Arabic character recognition using 1-D slices of the character spectrum
Auteurs : Saleh A. Alshebeili [Burundi, Arabie saoudite] ; Asim A.-F. Nabawi [Arabie saoudite] ; Sabri A. Mahmoud [Arabie saoudite]Source :
- Signal Processing [ 0165-1684 ] ; 1995.
Abstract
An Arabic character recognition algorithm using 1-D slices of the character spectrum is presented. The Fourier spectrum of the character's projections on the X- and Y-axes is estimated. The features are extracted from this 2-D spectrum. The features of 10 sets of characters were used as model features. The features of an input character are compared with the models' features using a distance measure. The model with the minimum distance is taken as the class representing the input character. Experimental results have shown that the presented algorithm is capable of recognizing Arabic characters with a recognition rate of 99.06%, using 10 features of the X-projection. This rate rises to 99.94% when 10 features of the Y-projection are added. The proposed system was compared with another, based on the Fourier descriptors, which was capable of recognizing 97.5% of test characters using 10 Fourier descriptors. The presented technique is superior to that of the Fourier descriptors in terms of recognition rates and speed, as fast Fourier transform is used in the calculation of the spectrum while standard equations are used to compute the Fourier descriptors. Both techniques are invariant to shift. However, the Fourier descriptor is invariant also to rotation and scale.
Url:
DOI: 10.1016/S0165-1684(96)00150-8
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000061
- to stream Istex, to step Curation: 000060
- to stream Istex, to step Checkpoint: 001891
- to stream Main, to step Merge: 002570
- to stream Main, to step Curation: 002440
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Arabic character recognition using 1-D slices of the character spectrum</title><author><name sortKey="Alshebeili, Saleh A" sort="Alshebeili, Saleh A" uniqKey="Alshebeili S" first="Saleh A." last="Alshebeili">Saleh A. Alshebeili</name></author><author><name sortKey="Nabawi, Asim A F" sort="Nabawi, Asim A F" uniqKey="Nabawi A" first="Asim A.-F." last="Nabawi">Asim A.-F. Nabawi</name></author><author><name sortKey="Mahmoud, Sabri A" sort="Mahmoud, Sabri A" uniqKey="Mahmoud S" first="Sabri A." last="Mahmoud">Sabri A. Mahmoud</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:09BFAB68656A137E157AB3FB45D22605EC94216C</idno><date when="1997" year="1997">1997</date><idno type="doi">10.1016/S0165-1684(96)00150-8</idno><idno type="url">https://api.istex.fr/document/09BFAB68656A137E157AB3FB45D22605EC94216C/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000061</idno><idno type="wicri:Area/Istex/Curation">000060</idno><idno type="wicri:Area/Istex/Checkpoint">001891</idno><idno type="wicri:doubleKey">0165-1684:1997:Alshebeili S:arabic:character:recognition</idno><idno type="wicri:Area/Main/Merge">002570</idno><idno type="wicri:Area/Main/Curation">002440</idno><idno type="wicri:Area/Main/Exploration">002440</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a">Arabic character recognition using 1-D slices of the character spectrum</title><author><name sortKey="Alshebeili, Saleh A" sort="Alshebeili, Saleh A" uniqKey="Alshebeili S" first="Saleh A." last="Alshebeili">Saleh A. Alshebeili</name><affiliation wicri:level="1"><country wicri:rule="url">Burundi</country></affiliation><affiliation wicri:level="1"><country xml:lang="fr">Arabie saoudite</country><wicri:regionArea>Electrical Engineering Department, King Saud University, P.O. Box 800, Riyadh 11421</wicri:regionArea><wicri:noRegion>Riyadh 11421</wicri:noRegion></affiliation></author><author><name sortKey="Nabawi, Asim A F" sort="Nabawi, Asim A F" uniqKey="Nabawi A" first="Asim A.-F." last="Nabawi">Asim A.-F. Nabawi</name><affiliation wicri:level="1"><country xml:lang="fr">Arabie saoudite</country><wicri:regionArea>Computer Engineering Department, College of Computer and Information Sciences, King Saud University, P.O. Box 51178, Riyadh 11543</wicri:regionArea><wicri:noRegion>Riyadh 11543</wicri:noRegion></affiliation></author><author><name sortKey="Mahmoud, Sabri A" sort="Mahmoud, Sabri A" uniqKey="Mahmoud S" first="Sabri A." last="Mahmoud">Sabri A. Mahmoud</name><affiliation wicri:level="1"><country xml:lang="fr">Arabie saoudite</country><wicri:regionArea>Al-Manarain Est. for Technical Applications, P.O. Box 53531, Riyadh 11593</wicri:regionArea><wicri:noRegion>Riyadh 11593</wicri:noRegion></affiliation></author></analytic><monogr></monogr><series><title level="j">Signal Processing</title><title level="j" type="abbrev">SIGPRO</title><idno type="ISSN">0165-1684</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="1995">1995</date><biblScope unit="volume">56</biblScope><biblScope unit="issue">1</biblScope><biblScope unit="page" from="59">59</biblScope><biblScope unit="page" to="75">75</biblScope></imprint><idno type="ISSN">0165-1684</idno></series><idno type="istex">09BFAB68656A137E157AB3FB45D22605EC94216C</idno><idno type="DOI">10.1016/S0165-1684(96)00150-8</idno><idno type="PII">S0165-1684(96)00150-8</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0165-1684</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">An Arabic character recognition algorithm using 1-D slices of the character spectrum is presented. The Fourier spectrum of the character's projections on the X- and Y-axes is estimated. The features are extracted from this 2-D spectrum. The features of 10 sets of characters were used as model features. The features of an input character are compared with the models' features using a distance measure. The model with the minimum distance is taken as the class representing the input character. Experimental results have shown that the presented algorithm is capable of recognizing Arabic characters with a recognition rate of 99.06%, using 10 features of the X-projection. This rate rises to 99.94% when 10 features of the Y-projection are added. The proposed system was compared with another, based on the Fourier descriptors, which was capable of recognizing 97.5% of test characters using 10 Fourier descriptors. The presented technique is superior to that of the Fourier descriptors in terms of recognition rates and speed, as fast Fourier transform is used in the calculation of the spectrum while standard equations are used to compute the Fourier descriptors. Both techniques are invariant to shift. However, the Fourier descriptor is invariant also to rotation and scale.</div></front></TEI><affiliations><list><country><li>Arabie saoudite</li><li>Burundi</li></country></list><tree><country name="Burundi"><noRegion><name sortKey="Alshebeili, Saleh A" sort="Alshebeili, Saleh A" uniqKey="Alshebeili S" first="Saleh A." last="Alshebeili">Saleh A. Alshebeili</name></noRegion></country><country name="Arabie saoudite"><noRegion><name sortKey="Alshebeili, Saleh A" sort="Alshebeili, Saleh A" uniqKey="Alshebeili S" first="Saleh A." last="Alshebeili">Saleh A. Alshebeili</name></noRegion><name sortKey="Mahmoud, Sabri A" sort="Mahmoud, Sabri A" uniqKey="Mahmoud S" first="Sabri A." last="Mahmoud">Sabri A. Mahmoud</name><name sortKey="Nabawi, Asim A F" sort="Nabawi, Asim A F" uniqKey="Nabawi A" first="Asim A.-F." last="Nabawi">Asim A.-F. Nabawi</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 002440 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002440 | 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:09BFAB68656A137E157AB3FB45D22605EC94216C
|texte= Arabic character recognition using 1-D slices of the character spectrum
}}
| This area was generated with Dilib version V0.6.32. |  |