Improvement of iris recognition system using fuzzy segmentation and neural network

Other Title(s)

تطوير نظام التعرف على هوية الأشخاص بواسطة قزحية العين باستخدام تقنية الانقسام الضبابي و الشبكات العصبونية

Dissertant

al-Hawamidah, Kawthar Hamad Allah Muhammad

Thesis advisor

al-Dawud, Isam F.
al-Smadi, Adnan M.

Comitee Members

al-Samawi, Venus Wazir
al-Khalidi, Jihad O.
Abu al-Jabr, Walid

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

2010

English Abstract

A biometric system provides automatic identification of an individual based on a unique features or characteristics.

Iris recognition is regarded as the most reliable and accurate biometric identification system available.

Most commercial Iris recognition systems use patented algorithms developed by Daugman, and these algorithms are able to produce high recognition rates. The work presented in this thesis aims to improve Iris recognition system in order to verify both the uniqueness of the human Iris and its performance as a biometric system.

The system used is based on database of grayscale eye image (CASIA-Iris-V3-Interval). This study consists of two parts.

Part one presents a new segmentation method which is based on C-Mean algorithm.

It is able to localize the circular Iris region, occluding eyelids and eyelashes, and reflections.

Part two uses neural network to match these Irises and to perform the recognition. Finally, the system is implemented on a set of 400 eye images.

We obtained high recognition rate which was about 97.5% with minimum time required.

In addition, our method of Iris recognition is shown to be reliable and accurate biometric technology.

Main Subjects

Information Technology and Computer Science

Topics

No. of Pages

83

Table of Contents

Table of contents.

Abstract.

Chapter One : introduction.

Chapter Two : theoretical background.

Chapter Three : implementation.

Chapter Four : assessing results.

Chapter Five : conclusion and future work.

References.

American Psychological Association (APA)

al-Hawamidah, Kawthar Hamad Allah Muhammad. (2010). Improvement of iris recognition system using fuzzy segmentation and neural network. (Master's theses Theses and Dissertations Master). Al albayt University, Jordan
https://search.emarefa.net/detail/BIM-311507

Modern Language Association (MLA)

al-Hawamidah, Kawthar Hamad Allah Muhammad. Improvement of iris recognition system using fuzzy segmentation and neural network. (Master's theses Theses and Dissertations Master). Al albayt University. (2010).
https://search.emarefa.net/detail/BIM-311507

American Medical Association (AMA)

al-Hawamidah, Kawthar Hamad Allah Muhammad. (2010). Improvement of iris recognition system using fuzzy segmentation and neural network. (Master's theses Theses and Dissertations Master). Al albayt University, Jordan
https://search.emarefa.net/detail/BIM-311507

Language

English

Data Type

Arab Theses

Record ID

BIM-311507