Development of an efficient neural-based segmentation technique for Arabic handwriting recognition

Dissertant

al-Hamad, Husam Ahmad%

Thesis advisor

al-Shalabi, Riyad

Comitee Members

al-Yasin, Mustafa
Ghassan, Kanan

University

Arab Academy for Financial and Banking Sciences

Faculty

The Faculty of Information Systems and Technology

Department

Computer information systems

University Country

Jordan

Degree

Ph.D.

Degree Date

2008

English Abstract

Off-line Arabic handwriting recognition and segmentation has been a popular field of research for many years.

It still remains an open problem.

The challenging nature of handwriting recognition and segmentation has attracted the attention of researchers from industry and academic circles.

Recognition and segmentation of Arabic handwritten script is a difficult task because the Arabic handwritten characters are naturally both cursive and unconstrained.

The analysis of Arabic script is further complicated in comparison with English script.

It is believed, good segmentation is one reason for high accuracy character recognition.

This thesis reviews all aspects of handwriting segmentation research.

Four main techniques are proposed and investigated.

First, a new feature-based Arabic heuristic segmentation AHS technique is proposed and investigated for the purpose of partition Arabic handwritten words into primitives (over-segmentation) that may then be processed further to provide the best segmentation, various heuristics are developed and employed to decide how to split the Arabic words into segments and enhance overall segmentation results.

Second, a new feature extraction technique (Modified Direction Features − MDF) is also investigated for the purpose of segmented character classification.

Direction features extraction technique combines local feature vector and global structural information and provides integrated features to a neural network for training and testing, Location transition (LT) and direction transition (DT) for Arabic Handwritten are also investigated.

Third, novel neural-based techniques for validating prospective segmentation points of Arabic handwriting are proposed and investigated based on direction features.

In particular, the vital process of handwriting segmentation is examined in great detail.

The classifier chosen for segmentation point validation classification is a feed-forward trained with the back-propagation algorithm vi Forth, new fusion equations are proposed and investigation to examine and evaluate a prospective segmentation points by obtaining a fused value from three neural confidence values obtained from right and centre character recognition outputs in addition to the segmentation point validation (SPV) output.

Confidence values are assigned to each segmentation point that is located through feature detection.

All technique components are tested on a local benchmark database.

High segmentation accuracy is reported in this research along with comparable results for character recognition and segmentation.

Main Subjects

Information Technology and Computer Science

Topics

• Writing
• Data processing
• Arabic language

No. of Pages

151

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-305975