You are on page 1of 5

 

CHAPTER I

INTRODUCTION

1.1 Background

In the world of technology, we can see information technology is

rapidly changing everyday. Nowadays, information technology is not only

use for supporting company but also enhancing people life by combining

various scientific fields. One of the technologies that would be the focus of

this study is biometric technology.

Biometric technology is an automatic method of identification of a

person based on their physiological or behavioral characteristics such as

fingerprint, iris pattern, facial feature, voice, odor, DNA, signature, and

speech (Jain, Ross, & Prabhakar, 2004). U.S.Government's Biometric

Consortium (2011) claimed that “biometric technologies are becoming the

foundation of an extensive array of highly secure identification and

personal verification solutions”

Among biometric technology, iris pattern has attracted a lot of

attention in biometric technology (Lim, Lee, Byeon, & Kim, 2001)

because of its physical characteristics such as the uniqueness, the accuracy

and the stability (Gawande, Zaveri, & Kapur, 2010). Iris is located behind

the cornea which makes it very difficult to modify, and if it happens, the


 
 

risk will be at the eye and cannot be rebuilt (Ommy, Rizal, & Murti,

2008).

Iris recognition is widely used in many areas, for examples: for

access control, the replacement of password (Fakhry & Cardozo, 2006;

Jain, Ross, & Prabhakar, 2004), and border control in Heathrow, Gatwick,

Birmingham, Manchester, and Stansted (The Nationality, Immigration and

Asylum Act, 2002).

This study has purpose to evaluate the better performance on iris

recognition is to avoid things that are not desirable. For example, if in an

international airport that use iris as their identification and security

systems, but due to the incomplete existing methods, the failure is

produced, then the queue for re-identification can reach tens and even

hundreds of times and will take time.

The performance of commercially available and open source

algorithm on iris recognition will be compared in this study. VeriEye’s

algorithm will be studied as the commercial algorithm and Libor Masek’s

algorithm as the open source algorithm.

1.2 Statement of Problems

As of writing, there has been no comparison between the

performance of the commercially available and the open source algorithm

namely Libor and VeriEye.


 
 

1.3 Purposes of Study

The main purpose of this study is to evaluate the performance of

the commercially available and the open source algorithm using Bath iris

images databases. The comparison study results can assist the users in

reviewing better iris recognition algorithm such as the VeriEye’s and

Libor Masek’s algorithm.

1.4 Benefits of Study

The benefit of this study is users will know whether the open

source algorithm (Libor Masek) would perform as good as the

commercially available one (VeriEye) especially when cost is the essential

factor in this regard. The other benefit other than the cost is by opening the

door for developer to start developing application that incorporates this

open source algorithm if the result is promising.

1.5 Hypothesis

Hypothesis: There is performance difference between VeriEye’s

(commercially available) and Libor Masek’s (open source)

on iris recognition.


 
 

1.6 Scope

Because of the limitation of time, not all algorithms for iris

recognition will be studied. This study will focus in comparing two

algorithms between VeriEye’s algorithm and Libor Masek’s algorithm on

iris recognition. The only iris image format that is used for the study is

jpeg format because of its compatibility with VeriEye’s algorithms and

grayscale images because of its compatibility with Libor Masek’s

a;gorithms. And the performance which defines in this study will include

False Reject Rate, False Accept Rate, and Time.

1.7 Definition of Term

• Performance

o False Rejection Rate (FRR): the proportion of transactions

with truthful claims of identity that are incorrectly denied

(Mansfield and Wayman, 2002).

o False Accept Rate (FAR): the proportion of transactions

with wrongful claims of identity that are incorrectly

confirmed (Mansfield and Wayman, 2002).

o Time: This study will measure the time which adapted from

Biometric Transaction Time. (Elliot, Kukula, Lazarick,

2009)


 
 

(-) Biometric Transaction Time is the processes of

presentation of biometric characteristic(s), sample

acquisition, sample processing, and Biometric Subsystem

Decision. (Elliot, Kukula, Lazarick, 2009)

(+) Biometric Transaction Time is the processes of Sample

Processing Time and Biometric Decision Time.


 

You might also like