Off line handwritten recognition Arabic number using mathematical morphology and neural network
Other Title(s)
تمييز الأرقام العربية المكتوبة بخط اليد باستخدام المورفولوجيا و الشبكات العصبية
Dissertant
Thesis advisor
Comitee Members
Ababinah, Ismail M.
Slait, Azzam Talal
Battayihah, Khalid
University
Al albayt University
Faculty
Prince Hussein Bin Abdullah Faculty for Information Technology
Department
Department of Computer Science
University Country
Jordan
Degree
Master
Degree Date
2012
English Abstract
Character recognition plays an important role in the modern world ; It has many applications such as postal code, bank cheques, etc.
This research aims to design a system which is able to recognize handwritten Arabic (Indian) numerals using supervised neural network (back propagation) and mathematical morphology.
This research uses a new Arabic number (Indian) dataset, collected in order to evaluate the proposed method.
Dataset consists of 130 samples written by 13 writers, these samples are divided into two parts, the first 30 samples used as a tanning, while the second contains 100 samples used for testing the proposed system.
Experiments finally show that the proposed method is efficient in handwritten number recognition ; This study achieves recognition rates between (68 %) to (72.5 %).
Results differed depending on the threshold used.
In this research was to compare the results that have been achieved with the results of other researches, and the results were varying based on used dataset in the testing process.
This research used a method that showed the integration between morphological and neural networks which gives better results recognition.
Feature extraction phase is to choose the appropriate features, since feature extraction is the most important phase of this research.
This research uses a set of properties with ability to adapt with various images.
The main objective of this system is to recognize isolated Arabic (Indian) numbers used in different applications.
This research was implemented by using MATLAB.
Main Subjects
Information Technology and Computer Science
Topics
No. of Pages
51
Table of Contents
Table of contents.
Abstract.
Chapter One : introduction.
Chapter Two : theoretical background.
Chapter Three : proposed approach.
Chapter Four : experimental result.
Chapter Five : conclusion and future work.
References.
American Psychological Association (APA)
Ulwan, Muhammad Samir. (2012). Off line handwritten recognition Arabic number using mathematical morphology and neural network. (Master's theses Theses and Dissertations Master). Al albayt University, Jordan
https://search.emarefa.net/detail/BIM-321354
Modern Language Association (MLA)
Ulwan, Muhammad Samir. Off line handwritten recognition Arabic number using mathematical morphology and neural network. (Master's theses Theses and Dissertations Master). Al albayt University. (2012).
https://search.emarefa.net/detail/BIM-321354
American Medical Association (AMA)
Ulwan, Muhammad Samir. (2012). Off line handwritten recognition Arabic number using mathematical morphology and neural network. (Master's theses Theses and Dissertations Master). Al albayt University, Jordan
https://search.emarefa.net/detail/BIM-321354
Language
English
Data Type
Arab Theses
Record ID
BIM-321354