Development of an efficient neural-based segmentation technique for Arabic handwriting recognition
Dissertant
Thesis advisor
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
No. of Pages
151
Table of Contents
Table of contents.
Abstract.
Chapter one : Introduction.
Chapter two : Handwriting segmentation and recognition research.
Chapter three : The techniques and methodologies.
Chapter four : Experimental results.
Chapter five : Analysis and comparison of results.
Chapter six : Conclusions and future research.
References.
American Psychological Association (APA)
al-Hamad, Husam Ahmad%. (2008). Development of an efficient neural-based segmentation technique for Arabic handwriting recognition. (Doctoral dissertations Theses and Dissertations Master). Arab Academy for Financial and Banking Sciences, Jordan
https://search.emarefa.net/detail/BIM-305975
Modern Language Association (MLA)
al-Hamad, Husam Ahmad%. Development of an efficient neural-based segmentation technique for Arabic handwriting recognition. (Doctoral dissertations Theses and Dissertations Master). Arab Academy for Financial and Banking Sciences. (2008).
https://search.emarefa.net/detail/BIM-305975
American Medical Association (AMA)
al-Hamad, Husam Ahmad%. (2008). Development of an efficient neural-based segmentation technique for Arabic handwriting recognition. (Doctoral dissertations Theses and Dissertations Master). Arab Academy for Financial and Banking Sciences, Jordan
https://search.emarefa.net/detail/BIM-305975
Language
English
Data Type
Arab Theses
Record ID
BIM-305975