CIDE (2002) Fellah : Différence entre versions

Version actuelle datée du 21 septembre 2016 à 08:07

ArabTDM: Automatic recognition of arabic contents of scientific journals

titre: ArabTDM: Automatic recognition of arabic contents of scientific journals
Auteurs: FELLAH Meriem (1) ; ANJA HABACHA CHAIBI (1) ; MOHAMED BEN AHMED (1) ;
Affiliations

RIADI/ENSI, University of La Manouba, TUNISIE

In: Actes du colloque CIDE.05 (Hammamet 2002)
Source: INIST

Abstract: The work presented in this paper tackling the document analysis and recognition problem, in line with a virtual library project. It presents the design and the implementation of an automatic recognition system of the contents of scientific journals written in Arabic. The system deals with homogeneous and intermediary contents. Its based on an hybrid approach which integrates the top-down approach for the segmentation of the digitised contents into significant blocs and the extraction of the main bloc, and the bottom-up approach which considers the text file representing the body of the contents and uses the tagging technique to extract its different items and to distinguish their relating components: Title, Author(s) and Page numbers. The output of the system is a HTML (HyperText Markup Language) file stored into a database with appropriate hyperlinks.

Mots-clés anglais: HTML language ; Segmentation ; Content analysis ; Arabic ; Language ; Periodical ; Scientific literature ; Optical character recognition ;
Mots-clés français: Langage HTML ; Segmentation ; Analyse contenu ; Arabe ; Langage ; Périodique ; Littérature scientifique ; Reconnaissance optique caractère ;
Mots-clés espagnols: Lenguaje HTML ; Segmentación ; Análisis contenido ; Árabe ; Lenguaje ; Periódico ; Literatura científica ; Reconocimento óptico de caracteres ;

Référence à améliorer :
sémantisation des auteurs et affiliations

@@ Ligne 1 : / Ligne 1 : @@
-{{Wicri travaux|texte=Copier coller d'une notice RefDoc}}
 {{Titre page article
   |titre=ArabTDM: Automatic recognition of arabic contents of scientific journals
@@ Ligne 5 : / Ligne 4 : @@
 {{CIDE boîte bibliographique|texte=
 ;titre:[[A pour titre::ArabTDM: Automatic recognition of arabic contents of scientific journals]]
-;Auteurs:
+;Auteurs:FELLAH Meriem (1) ; ANJA HABACHA CHAIBI (1) ; MOHAMED BEN AHMED (1) ;
-;Affilitions:
+;Affiliations:
-*
+* RIADI/ENSI, University of La Manouba, TUNISIE
 ;In: [[Est dans les actes::CIDE 2002 Hammamet|Actes du colloque CIDE.05]] (Hammamet 2002)
+;Source:INIST
 }}
+;Abstract:The work presented in this paper tackling the document analysis and recognition problem, in line with a virtual library project. It presents the design and the implementation of an automatic recognition system of the contents of scientific journals written in Arabic. The system deals with homogeneous and intermediary contents. Its based on an hybrid approach which integrates the top-down approach for the segmentation of the digitised contents into significant blocs and the extraction of the main bloc, and the bottom-up approach which considers the text file representing the body of the contents and uses the tagging technique to extract its different items and to distinguish their relating components: Title, Author(s) and Page numbers. The output of the system is a HTML (HyperText Markup Language) file stored into a database with appropriate hyperlinks.
-Auteur(s) / Author(s)
-FELLAH Meriem (1) ; ANJA HABACHA CHAIBI (1) ; MOHAMED BEN AHMED (1) ;
+;Mots-clés anglais :HTML language ; Segmentation ; Content analysis ; Arabic ; Language ; Periodical ; Scientific literature ; Optical character recognition ;
-Affiliation(s) du ou des auteurs / Author(s) Affiliation(s)
+;Mots-clés français :Langage HTML ; Segmentation ; Analyse contenu ; Arabe ; Langage ; Périodique ; Littérature scientifique ; Reconnaissance optique caractère ;
-(1) RIADI/ENSI, University of La Manouba, TUNISIE
+;Mots-clés espagnols : Lenguaje HTML ; Segmentación ; Análisis contenido ; Árabe ; Lenguaje ; Periódico ; Literatura científica ; Reconocimento óptico de caracteres ;
-Résumé / Abstract
+[[Catégorie:Référence bibliographique, article de conférence]]
-The work presented in this paper tackling the document analysis and recognition problem, in line with a virtual library project. It presents the design and the implementation of an automatic recognition system of the contents of scientific journals written in Arabic. The system deals with homogeneous and intermediary contents. Its based on an hybrid approach which integrates the top-down approach for the segmentation of the digitised contents into significant blocs and the extraction of the main bloc, and the bottom-up approach which considers the text file representing the body of the contents and uses the tagging technique to extract its different items and to distinguish their relating components: Title, Author(s) and Page numbers. The output of the system is a HTML (HyperText Markup Language) file stored into a database with appropriate hyperlinks.
+{{CIDE référence à améliorer|texte=sémantisation des auteurs et affiliations}}
-Source / Source
+__SHOWFACTBOX__
-Congrès
-Documents dans les systèmes d'information mobiles :   ( Hammamet, 20-23 octobre 2002 )
-CIDE : colloque international sur le document électronique No5, Hammamet , TUNISIE (20/10/2002)
-  , pp. 83-96[Note(s) :  [308 p.]] [Document : 14 p.] (8 ref.) ISBN 2-7261-1223-4 ;  Illustration : Illustration ;
-Langue / Language
-Anglais
-Revue : Français
-Editeur / Publisher
-INRIA, Le Chesnay, FRANCE  (2002) (Monographie)
-Mots-clés anglais / English Keywords
-HTML language ; Segmentation ; Content analysis ; Arabic ; Language ; Periodical ; Scientific literature ; Optical character recognition ;
-Mots-clés français / French Keywords
-Langage HTML ; Segmentation ; Analyse contenu ; Arabe ; Langage ; Périodique ; Littérature scientifique ; Reconnaissance optique caractère ;
-Mots-clés espagnols / Spanish Keywords
-Lenguaje HTML ; Segmentación ; Análisis contenido ; Árabe ; Lenguaje ; Periódico ; Literatura científica ; Reconocimento óptico de caracteres ;
-Localisation / Location
-INIST-CNRS, Cote INIST : Y 34559, 35400010854579.0060

CIDE (2002) Fellah : Différence entre versions

Version actuelle datée du 21 septembre 2016 à 08:07

Menu de navigation

Affichages

Outils personnels

Navigation

Rechercher

Outils