A framework model for Arabic handwritten text recognition to handle missing text fragments
Other Title(s)
الإطار العملي لنموذج تمييز نصوص العربي بخط اليد للتعامل مع النص المقطوع
Dissertant
al-Qarallah, Baha Abd al-Wahhab Muhsin
Thesis advisor
al-Shammari, Husayn Hadi Uwayyid
Comitee Members
al-Jarrah, Muzaffar Munir
Hirz Allah, Nail B.
University
Middle East University
Faculty
Faculty of Information Technology
Department
Computer Science Department
University Country
Jordan
Degree
Master
Degree Date
2013
English Abstract
In this thesis a framework model for Arabic handwritten text recognition is developed to deal with the missing text fragments.
Since there are many Arabic manuscripts ancient of ancient times have been either destroyed or stolen, whether all or some parts or pages, so it’s important to complete the text.
The framework model consists of two stages; the first stage consists of four parts which are Input 1 scan text image, recognition stage, extracted feature, and Input 2 Typed.
The second stage is the decision stage according to the availability of all Arabic characters set forms.
So if all the Arabic characters set are available in the original text the missing fragments will be discovered from the text, otherwise handwritten missing characters are estimated then embedded the fragment in the original document.
The original handwritten text with missing characters, after extracting the handwritten characters' features, then the missing texts will be typed and converted to handwritten text in the same form of the original text.
In this thesis the handwritten text sample of writers was so small, 17 writers, so the recognition process needs to be much efficient and accurate to recognize the characters written by many different users more than the sample used.
The developed framework model can be used in the library, and governmental offices for discovering the missing text in the handwritten documents.
The programming language used in the implementation was C#.Net.
Main Subjects
Information Technology and Computer Science
No. of Pages
111
Table of Contents
Table of contents.
Abstract.
Abstract in Arabic.
Chapter One : Introduction.
Chapter Two : Termenology.
Chapter Three : Literature survey.
Chapter Four : The structure of framework.
Chapter Five : Implementation and results.
Chapter Six : Conclusion, dicussinon and future works.
References.
American Psychological Association (APA)
al-Qarallah, Baha Abd al-Wahhab Muhsin. (2013). A framework model for Arabic handwritten text recognition to handle missing text fragments. (Master's theses Theses and Dissertations Master). Middle East University, Jordan
https://search.emarefa.net/detail/BIM-693774
Modern Language Association (MLA)
al-Qarallah, Baha Abd al-Wahhab Muhsin. A framework model for Arabic handwritten text recognition to handle missing text fragments. (Master's theses Theses and Dissertations Master). Middle East University. (2013).
https://search.emarefa.net/detail/BIM-693774
American Medical Association (AMA)
al-Qarallah, Baha Abd al-Wahhab Muhsin. (2013). A framework model for Arabic handwritten text recognition to handle missing text fragments. (Master's theses Theses and Dissertations Master). Middle East University, Jordan
https://search.emarefa.net/detail/BIM-693774
Language
English
Data Type
Arab Theses
Record ID
BIM-693774
