International Journal of Engineering Trends and Technology (IJETT) – Volume 25 Number 1- July 2015
A Review on biometric system
1
ER. Vishakha, 2ER. Jujhar Singh
1
Student of M.Tech, G.I.T.M (KARNAL),
HARYANA, INDIA
2
Assistant Professor in CSE Dept. G.I.T.M (KARNAL),
Haryana, India
ABSTRACT
The most common approach for fingerprint analysis is
using minutiae that identifies corresponding features and
evaluates the resemblance between two fingerprint
impressions. Although many minutiae point pattern
matching algorithms have been proposed, reliable
automatic fingerprint verification remains as a
challenging problem. Finger print recognition can be
done effectively using texture classification approach.
Important aspect here is appropriate selection of features
that recognize the finger print. We propose an effective
combination of features for multi-scale and multidirectional recognition of fingerprints. The features
include standard deviation, kurtosis, and skewers . We
apply the method by analyzing the finger prints with
discrete wavelet transform (DWT) . We used Canberra
distance metric for similarity comparison between the
texture classes. We trained 30 images and obtained an
overall performance up to 95%.
Keywords: Wavelet transform, minutiae, finger print
recognition,
analysis.
texture
classification,
multi-directional
physiological measurements or behavioural traits
[1]. Since biometric identifiers are associated
permanently with the user. They are more reliable
than token or knowledge based authentication
methods. It can be used to achieve a “positive
identification” with a very high level of confidence,
such as an error rate of 0.001% Biometrics offers
several advantages over traditional security
measures.
The various biometric modalities can be broadly
categorized as
Physical biometrics: These involve some
form of physical measurement and include
modalities such as face, fingerprints, iris-scans,
hand, finger-knuckle print geometry etc.
Behavioural biometrics: These are
usually temporal in nature and involve measuring
the way in which a user performs certain tasks.
This includes modalities such as speech, signature,
gait, keystroke dynamics etc.
INTRODUCTION
1 Overview of Biometric Recognition System
In an increasingly digitized world the reliable
personal authentication has become an important
human computer interface activity. National
security, e-commerce and access to computer
networks are now very common where
establishing a person’s identity has become
vital. Existing security measures rely on
knowledge-based approaches like passwords or
token-based approaches such as swipe cards
and passports to control access to physical and
virtual spaces, but these methods are not very
secure. Tokens such as badges and access cards
may be duplicated or stolen. Passwords and
personal identification number (PIN) numbers may
be stolen electronically. Furthermore,
they
differentiate between authorized user and a
person having access to the tokens or
knowledge. Biometrics such as finger-knuckle
print, face and voice print offers means of
reliable personal authentication that can address
these problems and is gaining citizen and
government acceptance.
1.1.1Biometrics
the
Biometrics is the science of verifying
identity
of
an
individual
through
ISSN: 2231-5381
Fingerprints have several advantages over other
biometrics such as the following:
a) High universality
A large majority of the human
population has legible fingerprints and can
therefore be easily authenticated. This exceeds the
extent of the population who possess passports, ID
cards or any other form of tokens.
b) High distinctiveness
Even identical twins who share the
same deoxyribo nucleus acid (DNA) have been
shown to have different fingerprints, since the
ridge structure on the finger is not encoded in the
genes of an individual. Thus fingerprints
represent a stronger authentication mechanism than
DNA. Furthermore, there has been no evidence of
identical fingerprints in more than a century of
forensic practice. There are also mathematical
models that justify the high distinctiveness of
fingerprint patterns.
c)
High permanence
The ridge patterns on the surface of
the finger are formed in the womb and remain
invariant until death except in the case of severe
burns or deep physical injuries.
http://www.ijettjournal.org
Page 1
International Journal of Engineering Trends and Technology (IJETT) – Volume 25 Number 1- July 2015
d) Easy collectability
The process of collecting fingerprints
has become very easy with the advent of online
sensors. These sensors are capable of capturing
high resolution images of the finger surface within
a matter of seconds. This process requires
minimal or no user training and can be collected
easily from co-operative or non cooperative
users. In contrast, other accurate modalities like
iris recognition require very co-operative users and
have considerable learning curve in using the
identification system.
e)
High performance
Fingerprints remain one of the most
accurate biometric modalities available to date with
jointly optimal false accept rate (FAR) and false
reject rate (FRR). Forensic systems are currently
capable of achieving FAR of less than 10-4.
f)
Wide acceptability
While a minority of the user population is
reluctant to give their fingerprints due to the
association
with
criminal
and
forensic
fingerprint databases, it is by far the most
widely used modality for biometric authentication.
In identifying the fingerprint, there are two
major level involved which are classification and
matching. Fingerprint classification is a technique
to group the fingerprint into a few types while
fingerprint matching is a technique to assign the
fingerprint to which person it belongs to.
Fingerprint classification can be broadly
categorized into two main categories, model based
and structure based. Model based classification
uses the location of singular points (core and delta)
while structure based approach uses the estimated
orientation field in a fingerprint image to classify
the fingerprint. [2][3]
2 Fingerprint as a Biometric Fingerprint has
been used as identifications for individuals since
late 19thcentury and it has been discovered that
every individual has different fingerprints even for
identical twins. Fingerprints have the properties of
distinctiveness or individuality, and the fingerprints
of a particular person remain almost the same
(persistence) over time. These properties make
fingerprints suitable for biometric uses [4][5]
Figure 1.1. (a) Local Features Minutiae (b) Global Features Core and Delta
The ridges of a fingerprint give patterns that can be
grouped into various types. Patterns are important
for fingerprint classification. Fingerprints are
ISSN: 2231-5381
commonly classified into 3 main types; those are
loop, whorl and arch as shown in figure 1.2 below.
http://www.ijettjournal.org
Page 2
International Journal of Engineering Trends and Technology (IJETT) – Volume 25 Number 1- July 2015
Figure 1.2. Types of Fingerprints
3. Conclusion
The work explored the use of wavelet transform to
reduce the size of fingerprint images with less preprocessing and post-processing operations which
made the system simple and less space and time
consuming. It has also explored the use of new
feature vector wavelet co-occurrence signatures to
match the database fingerprint images with the
input fingerprint images using Euclidian distance.
REFERENCES
[1] A.K. Jain, R. Bolle and S. Pankanti, Biometrics, “Personal
Identification in a Networked
Society”, Kluwer Academic
Publishers, 1999.
[2] K. Nandakumar, Y. Chen and A. K. Jain, “Quality Based
Score Level Fusion In Multibiometric Systems”, Proc. 18th Int.
Conf. Pattern Recognition (ICPR), pp. 473-476, 2006.
[3] A. K. Jain and A. Ross, “Learning User Specific Parameters
In A Multibiometric System”, Proc. Int. Conf. Image Processing
(ICIP), New York , pp. 57-60, 2002.
[4]X. F. Liang and Asano Lab., “A more Robust Fingerprint
Identification Algorithm”, Report, pp. 1-4, 2000.
[5] Musa Mohd Mokji and Syed Abd. Rahman Syed Abu Bakar,
“Directional Image Construction Based on Wavelet Transform
for Fingerprint Classification and Matching”, National
Conference on Computer Graphics and Multimedia, pp. 331 –
335, 2002
ISSN: 2231-5381
http://www.ijettjournal.org
Page 3