![](/images/graphics-bg.png)
Handwritten and printed Hindi numerals recognition
Other Title(s)
تمييز الأرقام الهندية المكتوبة و المطبوعة
Dissertant
Mayahi, Muhammad Husayn Ghalib Abd al-Khaliq
Thesis advisor
Comitee Members
Jabbar, Imad K.
Baithun, Nushwan Yusuf
Ali, Salih Mahdi
University
University of Baghdad
Faculty
College of Science
Department
Department of Computer Science
University Country
Iraq
Degree
Master
Degree Date
2013
English Abstract
Handwritten numerals recognition plays a vital role in postal automation services.
The major problem in handwritten recognition is the huge variability and distortions of patterns.
The aim of the current work is to develop two methods to recognize Hindi printed and handwritten numerals objects.
Two methods have been proposed for extracting features from patterns.
The first method is based on the relative density distribution attributes of each numeral object, specifically it depends on the centralized moments.
This method gives sufficient results to recognize the printed and highly stylized handwritten numeral images.
The attained recognition rate is 97.47% for the printed numeral images and 95.55% for the highly stylized handwritten numeral images, while, the attained recognition rate is unacceptable when the system is applied for a handwritten numeral samples which have wide differences in their shapes; the system is tested for a set consisting of (4500) samples.
The attained recognition rate is (74.93%).
Each tested numeral image is scanned with scanning resolution of 300 dpi.
The second introduced recognition method utilizes: (i) the percentages of strokes in both horizontal and vertical directions and (ii) some morphological operations.
This method led to excellent recognition results for printed and handwritten numeral images.
The attained recognition rate is 100% for the printed numeral images where font size is higher than 10, 100% for the highly stylized handwritten numeral images, and 98.44% for the handwritten numeral samples with wide difference shapes.
The test material (i.e., numeral samples) are same for both introduced methods.
Main Subjects
Information Technology and Computer Science
No. of Pages
68
Table of Contents
Table of contents.
Abstract.
Abstract in Arabic.
Chapter One : General introduction.
Chapter Two : Theoretical background.
Chapter Three : The first proposed method.
Chapter Four : The second proposed method conclusion and future work.
Chapter Five : Conclusions and suggestions for future works.
References.
American Psychological Association (APA)
Mayahi, Muhammad Husayn Ghalib Abd al-Khaliq. (2013). Handwritten and printed Hindi numerals recognition. (Master's theses Theses and Dissertations Master). University of Baghdad, Iraq
https://search.emarefa.net/detail/BIM-605753
Modern Language Association (MLA)
Mayahi, Muhammad Husayn Ghalib Abd al-Khaliq. Handwritten and printed Hindi numerals recognition. (Master's theses Theses and Dissertations Master). University of Baghdad. (2013).
https://search.emarefa.net/detail/BIM-605753
American Medical Association (AMA)
Mayahi, Muhammad Husayn Ghalib Abd al-Khaliq. (2013). Handwritten and printed Hindi numerals recognition. (Master's theses Theses and Dissertations Master). University of Baghdad, Iraq
https://search.emarefa.net/detail/BIM-605753
Language
English
Data Type
Arab Theses
Record ID
BIM-605753