Recognition system for printed multi-font and multi-size Arabic characters
Joint Authors
Source
The Arabian Journal for Science and Engineering. Section B, Engineering
Issue
Vol. 27, Issue 1B (30 Apr. 2002), pp.57-72, 16 p.
Publisher
King Fahd University of Petroleum and Minerals
Publication Date
2002-04-30
Country of Publication
Saudi Arabia
No. of Pages
16
Main Subjects
Arabic language and Literature
Topics
Abstract AR
يصف هذا البحث نظام التعرف الأتوماتيكي على الحروف العربية.
و تتمثل المعضلة الأساسية في القراءة الأتوماتيكية للنصوص العربية في إمكانية تجزئتها إلى الحروف المكونة لها نجزئ أولا النص إلى أسطر, و نجزئ كلمات كل سطر حسب حروفها المتصلة, ثم نقوم بتقسيم كل من هذه الأجزاء إلى حروف.
و هذا التقسيم يعتمد على خصائص بنية الكتابة العربية. الطريقة المتبعة للتعرف على الحروف هي طريقة تركيبية بنيوية تعتمد على استخراج الخصائص الأساسية – ثقوب و تقعرات في الاتجاهات الأربعة – بغية الترتيب مع الخصائص الثانوية للتمييز بين الحروف العربية و إزالة الالتباس.
Abstract EN
This paper describes an automatic recognition system for Arabic writing.
The major problem in automatic reading of Arabic cursive characters is the segmentation of their constituent elements.
First, the text is segmented in lines, then in connected parts, and nally in characters.
This segmentation is based on the contextual properties of Arabic writing and gives a solution to the problem of over-segmentation of some characters.
The adopted recognition method is a structural one.
It is based on the detection of holes and concavities in four directions (up, down, left, and right), which permits the classi cation of characters.
In addition, secondary characteristics are used in order to differentiate between the characters of each class and to reduce the confusions that are, in practise, encountered in every multi-font system.
American Psychological Association (APA)
Hamami, Latifah& Burkani, Dawud. 2002. Recognition system for printed multi-font and multi-size Arabic characters. The Arabian Journal for Science and Engineering. Section B, Engineering،Vol. 27, no. 1B, pp.57-72.
https://search.emarefa.net/detail/BIM-359879
Modern Language Association (MLA)
Hamami, Latifah& Burkani, Dawud. Recognition system for printed multi-font and multi-size Arabic characters. The Arabian Journal for Science and Engineering. Section B, Engineering Vol. 27, no. 1B (Apr. 2002), pp.57-72.
https://search.emarefa.net/detail/BIM-359879
American Medical Association (AMA)
Hamami, Latifah& Burkani, Dawud. Recognition system for printed multi-font and multi-size Arabic characters. The Arabian Journal for Science and Engineering. Section B, Engineering. 2002. Vol. 27, no. 1B, pp.57-72.
https://search.emarefa.net/detail/BIM-359879
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 71-72
Record ID
BIM-359879