research centers


Search results: Found 3

Listing 1 - 3 of 3
Sort by

Article
Comprehensive collection for Arabic characters and numbers written by hand

Author: S.A. Ahmed
Journal: Engineering and Technology Journal مجلة الهندسة والتكنولوجيا ISSN: 16816900 24120758 Year: 2017 Volume: 35 Issue: 2 Part (B) Scientific Pages: 204-210
Publisher: University of Technology الجامعة التكنولوجية

Loading...
Loading...
Abstract

An Optical Character Recognition system for Arabic language should recognize Arabic handwritten words. However, it is difficult to find a freely accessible and comprehensive database of all Arabic words that can be employed for this purpose. Therefore, it is more efficient to divide the Arabic words into sub-words or characters. As there is no comprehensive Arabic handwritten character database that is accessible free of charge, interested researchers can utilize the database developed as a part of this work in recognition system training and output testing.In the present paper, a database is presented containing scanned images of 700 Arabic handwritten characters, Hindi numbers used in Arabic countries, and some special characters utilized in Arabic alphabet, along with their different positions (e.g., standalone, initial, medial and terminal), different sizes, styles and font colors. The aim is to provide sufficient samples for all character shapes for software training, resulting in greater accuracy in the recognition phase.These forms were filled by students of the Applied Sciences College, University of Technology, Baghdad, Iraq and were scanned at the 200, 300, and 600 dpi resolution. A graphical user interface (GUI) software environment is employed to make the manipulation of the created database easier, and provide many image processing functions that are allowed to be built the database easier


Article
Printed Arabic Characters Recognition Based on Minimum Distance Classifier Technique

Author: Printed Arabic Characters Recognition Based on Minimum Distance Classifier Technique
Journal: Iraqi Journal of Science المجلة العراقية للعلوم ISSN: 00672904/23121637 Year: 2018 Volume: 59 Issue: 2A Pages: 762-770
Publisher: Baghdad University جامعة بغداد

Loading...
Loading...
Abstract

The printed Arabic character recognition are faced numerous challenges due to its character body which are changed depending on its position in any sentence (at beginning or in the middle or in the end of the word). This paper portrays recognition strategies. These strategies depend on new pre-processing processes, extraction the structural and numerical features to build databases for printed alphabetical Arabic characters. The database information that obtained from features extracted was applied in recognition stage. Minimum Distance Classifier technique (MDC) was used to classify and train the classes of characters. The procedure of one character against all characters (OAA) was used in determining the rate of recognition. The suggested approaches have yielded unique and encouraging results in terms of accuracy in which the recognition rate reached to 97.28%. These approaches are faster and more efficient than other methods.


Article
Freeman Chain Code Contour Processing For Handwritten Isolated Arabic Characters Recognition
سلسلة فريمان لمعالجة الأحرف العربية المعزولة المكتوبة يدويا وتمييزها

Author: Majida Ali Abed ماجده علي
Journal: AL-yarmouk Journall مجلة كلية اليرموك الجامعة ISSN: 20752954 Year: 2012 Issue: 1 Pages: 90-105
Publisher: College Yarmouk University كلية اليرموك الجامعة

Loading...
Loading...
Abstract

The Arabic characters are being used in various languages. Recognition of handwritten characters of Arabic alphabet set is an important area of research. The work on recognition of Handwritten Isolated Arabic Characters (HIAC) is still an open research problem and it has numerous applications. Machine reading of optically scanned text is usually called optical Character recognition (OCR). In this paper we present an OCR for Handwritten Isolated Arabic Characters. Basic Characters are recognized by Freeman chain code. The proposed method obtains the contour of the character and then generates a Freeman Chain Code for contoured character. The obtained Freeman chain code is unique for handwritten isolated characters. The present method is based on template matching to recognize handwritten printed isolated Arabic characters. It was trained and validated on 200 images (consisting of 7400 Arabic characters written by 18 writers). Our experimentation observed the overall recognition rate is 95%. It is carried out in order to improve the rate and the performance of an Arabic handwritten word recognition system. The proposed system has been implemented and tested on Matlab R2008b environment

اللغة العربية هي مصدر اللغات السامية ، وحروفها تستخدم في مختلف اللغات . التمييز للحروف المكتوبة يدويا من مجموعة حروف اللغة العربية هو من أهم مجالات البحث. العمل على تمييز الحروف العربية المعزولة و المكتوبة يدويا (HIAC) لا يزال قيد البحث وله العديد من التطبيقات. في هذا البحث, نستعرض عملية التمييز للحروف العربية المعزولة والمكتوبة بخط اليد. الهدف من البحث هو تمييز الحروف العربية المعزولة المكتوبة يدويا باستخدام سلسلة فريمان. . الطريقة المقترحة تتضمن الحصول على مخططات الحروف ومن ثم توليد سلسلة فريمان الخاصة بها. النتيجة الحاصلة من سلسلة فريمان تكون وحيدة للحرف العربي المطلوب تمييزه. . تستند الطريقة المقترحة على مطابقة القوالب للتمييز. تم التدريب والتحقق من صحة الطريقة المقترحة على 200 صورة (التي تتكون من 7400 الحروف العربية والتي كتبت بواسطة 18 شخص). أظهرت النتائج العملية ان معدل التمييز هو 95 ٪. يتم تنفيذه من أجل تحسين معدل وأداء أنظمة التمييز للحروف العربية المكتوبة يدويا. تم تطبيق هذا النظام المقترح واختباره على البيئة الماتلاب R2008b

Listing 1 - 3 of 3
Sort by
Narrow your search

Resource type

article (3)


Language

English (3)


Year
From To Submit

2018 (1)

2017 (1)

2012 (1)