Title :
Three decision levels strategy for Arabic and Latin texts differentiation in printed and handwritten natures
Author :
Ben Jlaiel, M. ; Kanoun, Slim ; Alimi, Adel Mohamed ; Mullot, RéMy
Author_Institution :
Univ. of Sfax, Sfax
Abstract :
Arabic and Latin script identification in printed and handwritten nature present several difficulties because the Arabic (printed or handwritten) and the handwritten Latin scripts are cursive scripts of nature. To avoid all possible confusions which can be generated, we propose in this paper a strategy which is based on three decision levels where each level will have its own features vector and will consist in identifying only one script among the scripts to identify.
Keywords :
natural language processing; text analysis; Arabic script identification; Arabic texts differentiation; Latin script identification; Latin texts differentiation; cursive scripts; decision levels strategy; handwritten Latin scripts; handwritten nature; printed nature; Automation; Character recognition; Image recognition; Image texture analysis; Informatics; Laboratories; Machine intelligence; Optical character recognition software; Optical sensors; Text analysis;
Conference_Titel :
Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on
Conference_Location :
Parana
Print_ISBN :
978-0-7695-2822-9
DOI :
10.1109/ICDAR.2007.4377086