Combination of Local and Global Vision Modelling for Arabic Handwritten Words Recognition
Identifieur interne : 008276 ( Main/Exploration ); précédent : 008275; suivant : 008277Combination of Local and Global Vision Modelling for Arabic Handwritten Words Recognition
Auteurs : Samia Snoussi-Maddouri ; Hamidi Amiri ; Abdel Belaïd [France] ; Christophe ChoisySource :
English descriptors
Abstract
We propose in this paper a recognition system of Arabic hand-written words issued from literal amounts of Arabic checks. This system is based on the concept of PERCEPTRO developed by M. Côté for Latin word recognition. It is a specific NN, named Transparent Neural Network (TNN), combining a global and a local vision modelling (GVM - LVM) of the word. In the forward propagation movement, the former (GVM) proposes a list of structural features characterising the presence of some letters in the word. GVM proposes a list of possible letters and words containing these characteristics. Then, in the back-propagation movement, these letters are confirmed or not according to their proximity with corresponding printed letters. The correspondence between the letter shapes and the corresponding printed letters is performed by LVM using the correspondence of their Fourier descriptors, playing the role of a letter shape normalizer.
Affiliations:
- France
- Grand Est, Lorraine (région)
- Nancy
- Centre national de la recherche scientifique, Institut national de recherche en informatique et en automatique, Laboratoire lorrain de recherche en informatique et ses applications, Université de Lorraine
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 003402
- to stream Crin, to step Curation: 003402
- to stream Crin, to step Checkpoint: 000F64
- to stream Main, to step Merge: 008732
- to stream Main, to step Curation: 008276
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="839">Combination of Local and Global Vision Modelling for Arabic Handwritten Words Recognition</title></titleStmt><publicationStmt><idno type="RBID">CRIN:snoussi-maddouri02b</idno><date when="2002" year="2002">2002</date><idno type="wicri:Area/Crin/Corpus">003402</idno><idno type="wicri:Area/Crin/Curation">003402</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">003402</idno><idno type="wicri:Area/Crin/Checkpoint">000F64</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">000F64</idno><idno type="wicri:Area/Main/Merge">008732</idno><idno type="wicri:Area/Main/Curation">008276</idno><idno type="wicri:Area/Main/Exploration">008276</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Combination of Local and Global Vision Modelling for Arabic Handwritten Words Recognition</title><author><name sortKey="Snoussi Maddouri, Samia" sort="Snoussi Maddouri, Samia" uniqKey="Snoussi Maddouri S" first="Samia" last="Snoussi-Maddouri">Samia Snoussi-Maddouri</name></author><author><name sortKey="Amiri, Hamidi" sort="Amiri, Hamidi" uniqKey="Amiri H" first="Hamidi" last="Amiri">Hamidi Amiri</name></author><author><name sortKey="Belaid, Abdel" sort="Belaid, Abdel" uniqKey="Belaid A" first="Abdel" last="Belaid">Abdel Belaïd</name><affiliation><country>France</country><placeName><settlement type="city">Nancy</settlement><region type="region" nuts="2">Grand Est</region><region type="region" nuts="2">Lorraine (région)</region></placeName><orgName type="laboratoire" n="5">Laboratoire lorrain de recherche en informatique et ses applications</orgName><orgName type="university">Université de Lorraine</orgName><orgName type="institution">Centre national de la recherche scientifique</orgName><orgName type="institution">Institut national de recherche en informatique et en automatique</orgName></affiliation></author><author><name sortKey="Choisy, Christophe" sort="Choisy, Christophe" uniqKey="Choisy C" first="Christophe" last="Choisy">Christophe Choisy</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>arabic handwriting recognition</term><term>fourier descriptors</term><term>transparent neural network</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="2006">We propose in this paper a recognition system of Arabic hand-written words issued from literal amounts of Arabic checks. This system is based on the concept of PERCEPTRO developed by M. Côté for Latin word recognition. It is a specific NN, named Transparent Neural Network (TNN), combining a global and a local vision modelling (GVM - LVM) of the word. In the forward propagation movement, the former (GVM) proposes a list of structural features characterising the presence of some letters in the word. GVM proposes a list of possible letters and words containing these characteristics. Then, in the back-propagation movement, these letters are confirmed or not according to their proximity with corresponding printed letters. The correspondence between the letter shapes and the corresponding printed letters is performed by LVM using the correspondence of their Fourier descriptors, playing the role of a letter shape normalizer.</div></front></TEI><affiliations><list><country><li>France</li></country><region><li>Grand Est</li><li>Lorraine (région)</li></region><settlement><li>Nancy</li></settlement><orgName><li>Centre national de la recherche scientifique</li><li>Institut national de recherche en informatique et en automatique</li><li>Laboratoire lorrain de recherche en informatique et ses applications</li><li>Université de Lorraine</li></orgName></list><tree><noCountry><name sortKey="Amiri, Hamidi" sort="Amiri, Hamidi" uniqKey="Amiri H" first="Hamidi" last="Amiri">Hamidi Amiri</name><name sortKey="Choisy, Christophe" sort="Choisy, Christophe" uniqKey="Choisy C" first="Christophe" last="Choisy">Christophe Choisy</name><name sortKey="Snoussi Maddouri, Samia" sort="Snoussi Maddouri, Samia" uniqKey="Snoussi Maddouri S" first="Samia" last="Snoussi-Maddouri">Samia Snoussi-Maddouri</name></noCountry><country name="France"><region name="Grand Est"><name sortKey="Belaid, Abdel" sort="Belaid, Abdel" uniqKey="Belaid A" first="Abdel" last="Belaid">Abdel Belaïd</name></region></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 008276 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 008276 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Exploration
|type= RBID
|clé= CRIN:snoussi-maddouri02b
|texte= Combination of Local and Global Vision Modelling for Arabic Handwritten Words Recognition
}}
| This area was generated with Dilib version V0.6.33. |  |