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

Ulwan, Muhammad Samir

Thesis advisor

al-Khalidi, Jihad O.

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

• Neural networks(Computer science)

No. of Pages

51

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-321354