Character recognition system for artistic Arabic style

Dissertant

Abu Awdah, Abd al-Salam Aql Khalil

Thesis advisor

Fadil, Muayyad A.

Comitee Members

Samawi, Venus W.
al-Zubaydi, Rashid A.
Ghoal, Sad

University

Philadelphia University

Faculty

Faculty of Information Technology

Department

Department of Computer Science

University Country

Jordan

Degree

Master

Degree Date

2008

English Abstract

-Despite the tremendous achievement which has been made on the reading mechanism in the field of desktop publishing, the door remains open to the great efforts should be done in this field for the Arabic language contrary to the languages based on Latin and Chinese characters.

The characteristics of the Arabic text, such as the complexity of characters and overlapping, and some characters do not accept the contact only one side in addition to the varied forms of characters in accordance with its position in the middle, beginning or the end of the word, all these factors increase the specificity and uniqueness of the research in this area.

The recognition of Arabic characters pass through several steps; the preprocessing, segmentation, feature extraction, recognition and post processing.

However, the Arab character recognition depends mainly on the segmentation, because the segmentation has many problems resulting from the characteristics of Arabic characters such as the complexity of characters and overlap, a number of researches have emerged dealing with this problem in the printed and handwritten text, and reached a series of solutions and proposals and recommendations to solve the problem of segmentation.

There are many obstacles facing researchers working on Arabic character recognition mainly in segmentation process such as overlapping, ligatures and over-segmentation.

So, this thesis address the subject of this research concerning segmentation of artistic Arabic characters, using Thulth font that have the mentioned obstacles above, trying to segment the artistic words into characters and recognizing these characters.

XII Segmentation based on colors have been used in the research to solve the problem of the segmentation, which has passed into three steps, the first step coloring each connection part by a separate color, the second step segmentation of colored text to connection parts, and the third step segmentation of each connection part into its characters.

The outcome of the segmentation gave successful results.

There are several ways of character recognition, such as Matrix matching and feature extraction.

Matrix matching has been used because it is widely used and the easiness of its usage.

Matrix Matching compares the scanned picture of the character with the matrix library or pattern characters, and if the scanned picture of the character match one of the pictures in the matrix library within a known limit of similarity, the program considers that picture as identical ASCII character.

During the application of the system, the result of recognition was high and exceeds 89.19 % for the words tested in the system which are around 400 words.

Main Subjects

Electronic engineering

Topics

• Computational linguistics

No. of Pages

72

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-543979