Multimodal biometric system over
Unimodal biometric system
Priya Singh[1],Meenakshi Saraswat[2],Pragya Aggrawal3]
1.priya74singh74@gmail.com
2.cutegrl.aditi@gmail.com
3.pragya@rkgitw.edu.in
RKGITW,Ghaziabad
Abstract— A biometric system is essentially a pattern recognition
system that operates by acquiring biometric data from an
individual, extracting features from data and comparing
features. The purpose of such schemes is to ensure that the
rendered services are accessed only by Multimodal biometric
system is becoming more and more popular. It integrates face
recognition or behavior characteristics. It integrates face
recognition, finger print verification and speaker verification etc.
By using this it confirm an individual identity. In this paper, we
give a brief overview of the field of Biometrics and summarize
some of its advantages, disadvantages, strengths and its
limitation.
Keywords—Unimodel Biometrics, Multimodel Biometrics,
Physiological Biometrices, Behavioural Biometrices, Application
of Biometrices and Limitations.
I.
INTRODUCTION
Humans have used body characteristics such as face, voice,
etc. for thousands of years to recognize each other. Biometrics
is a technique for identification of an individual by his or her
physiological
or
behavioural
characteristics.
The
characteristics of Physiological are related to the shape of the
body. Examples such as face recognition, fingerprint, iris
recognition, retina, DNA, Palm print, hand geometry. The
characteristics of Behavioral related to the shape of the body.
Examples such as voice, vein, typing rhythm, gait. Most
Unimodel biometric system have a variety of problem such as
noisy data, inter-class variation, non-universality or spoof
attacks. As a typical example of biometrics, Face recognition
is a technique which identifies individuals based on their
unique facial characteristics. Unlike many other recognition
method such as finger-print, palm print and finger-vein
recognition, they do not need to require an individual to
directly contact with the sensor in order for recognition.
I. BIOMETRICS
A multimodal security solution uses two or more levels of
security (both external and internal). A multimodal solution
would, for example, consist of a swipe card in combination
with a PIN code. In contrast, a uni-modal solution would
involve the swipe card or use of a PIN code. It is also possible
to use a some part of building uni-modal security solution, and
in others a multimodal solution. For a multimodal system to
function well, it must use technology and different security
systems within each mode. In this way, the quality and
accuracy of the verification and authentication processes are
optimised. Whereas an impostor may be verified at one level
of security, the statistical probability of him or her being
verified at another level. The definition of a multimodal
security system can be further extended to include: “… a
biometric system that uses multiple biometric characteristics.”
II. OVERVIEW OF COMMONLY USED BIOMETRICS
Since there are number of biometric methods in use a brief
overview of various biometric characteristics will be given,
starting with newer technologies and then progressing to older
ones :
Infrared thermo gram (facial, hand or hand vein). It is possible
to capture the pattern of heat radiated by the human body with
in infrared camera. That pattern is unique for each person. It is
a non invasive method, but image acquisition is rather difficult
where there are other heat emanating surfaces near the body.
A related technology using near infrared imaging is used to
scan the back of a fist to determine hand vein structure, also
believed to be unique. Like face recognition, it must deal with
the extra issues of three-dimensional space and orientation of
the hand.
I.
Gait-Gait is one of the newer technologies.
Basically, gait is the peculiar way one walks and
it is a complex biometrics. It is not supposed to
be very distinctive but can be used in some lowsecurity applications. Gait is a behavioural
biometric and may not remain the same for a
long period of time, due to change in body
weight or serious brain damage .etc. KeystrokeIt is believed that each person types on a
keyboard in a characteristic way and have
different speed of typing. This is also not very
II.
III.
IV.
V.
VI.
VII.
distinctive but it is offers sufficient information
to permit identity verification. Keystroke
dynamics is a behavioural biometric; for some
individuals, one could expect to observe large
variations in typical typing patterns.
Odour-Each object spreads around an odour that
is characteristic of its chemical composition and
this could be used for differentiating various
objects. This would be done by chemical
sensors, each sensitive to a certain group of
compounds. Deodorants and perfumes could
lower the distinctiveness.
Hand geometry- It is one of the earliest
automated biometric system. Hand geometry is
the comparative dimensions of fingers and the
location of joints, shape and size of palm. The
technique is very simple, relatively easy to use
and inexpensive. Dry weather or individual
anomalies such as dry skin do not appear to have
any negative effects on the verification accuracy.
Fingerprint- A fingerprint is a pattern of ridges
and furrows located on the tip of each finger.
Fingerprints
were
used
for
personal
identification for many centuries and the
matching accuracy was very high . Patterns are
extracted by creating an inked impression of the
fingertip on the paper. Today, compact sensors
provide digital images of these patterns.
Fingerprint recognition for identification
acquires the initial image through live scan of
the finger by direct contact with a reader device
that can also check for validating attributes such
as temperature and pulse.
Face-Facial images are the most common
biometric characteristic used by humans to make
a personal recognition, hence the idea to use this
biometric in technology. Face verification
involves extracting a feature set from a twodimensional image of the user's face and
matching it with matter stored in a database.
The most popular approaches to face recognition
are based on shape of facial attributes such as
eyes, eyebrows, nose, lips and chin, and their
spatial relationships.
Retina-Retinal recognition creates an "eye
signature" from the vascular configuration of the
retina which is supposed to be a characteristic of
each individual and each eye. Since it is
protected in an eye itself, and since it is not easy
to change or replicate the retinal vasculature, this
is one of the most secure biometric.
Iris- Iris scanning is less intrusive than retinal
because the iris is easily visible from several
meters away. Responses of the iris to changes in
light can provide an important secondary
verification that the iris presented belongs to a
VIII.
IX.
X.
XI.
live subject. Irises of identical twins are
different, which is another advantage.
Palm print- Like fingerprints, palms of the
human hands contain unique pattern of ridges
and valleys. Since palm is larger then a finger,
palm print is expected to be even more reliable
than fingerprint. Palm print scanners need to
capture larger area with similar quality as
fingerprint scanners, so they are more expensive.
A highly accurate biometric system could be
combined by using a high-resolution palm print
scanner that would collect all the features of the
palm such as hand geometry, ridge and valley
features, principal lines, and wrinkles.
Voice-The features of an individual's voice are
based on physical characteristics such as vocal
tracts, mouth, nasal cavities and lips that are
used in creating a sound. These characteristics of
human speech are invariant for an individual, but
the behavioural part changes over time due to
age, medical conditions and emotional state.
Signature-Signature is a simple, concrete
expression of the unique variations in human
hand geometry. The way a person signs his or
her name is known to be characteristic of that
individual. Signatures are a behavioural
biometric that change over a period of time and
are influenced by physical and emotional
conditions of a subject.
DNA- Deoxyribonucleic acid (DNA) is probably
the most reliable biometrics. It is in fact a onedimensional code unique for each person.
Exception are identical twins. This method,
however, has some drawbacks:
I.
Contamination and sensitivity, since it
is easy to steal a piece of DNA from an
individual and use it for an ulterior
purpose.
II.
no real-time application is possible
because DNA matching requires
complex chemical methods involving
expert's skills, 3) privacy issues since
DNA sample taken from an individual
is likely to show susceptibility of a
person to some diseases. All this limits
the use of DNA matching to forensic
applications.
IV. APPLICATIONS OF BIOMETRIC SYSTEMS
The applications of biometrics can be divided into the
following three main groups:
I.
Commercial applications such as computer network
login, electronic data security, e- commerce, Internet
access, ATM, credit card, physical access control,
cellular phone, PDA, medical records management,
distance learning, etc.
II. Government applications such as national ID card,
correctional facility, driver’s license, social security,
welfare-disbursement, border control, passport
control, etc.
III. Forensic applications such as corpse identification,
criminal investigation, terrorist identification,
parenthood determination, missing children, etc.
V.
ADVANTAGES OF BIOMETRICES
I.
Increase security- Provide a convenient and low-cost
additional tier of security.
II. Reduce fraud by employing hard-to-forge
technologies and materials. for e.g. Minimise the
opportunity for ID fraud, buddy punching.
III. Eliminate problems caused by lost IDs or forgotten
passwords.
IV. Make it possible, automatically, to know WHO did
WHAT, WHERE and WHEN.
VI.
DISADVANTAGES OF BIOMETRICS
While biometric technologies are on the upswing and their use
is becoming widespread because of the advantages we have
outlined above, biometric technologies also have some
disadvantages.
Limitations: Because these technologies apply to human
beings, they are affected and are limited by many situations
that may affect the individual. For example, fingerprint
technology may not be effective if the subject has dirty,
deformed, or cut hands; iris technology may not be effective if
the subject has a bad eye; and voice technology may be
affected by infections. Also background noise can interfere
with voice recognition systems.
Affordability: Because biometric technologies are new
technologies, they tend to be rather expensive without
widespread use. For example, facial and voice recognition and
iris technologies are still not yet affordable.
Cannot replace a biometric that has been lost or
misappropriated. Once a biometric has been compromised, it
cannot be made right again. Biometrics evolve and degrade
over time and require constant updates of the reference
biometric.
VII.
CONCLUSION AND FUTURE WORK
Biometrics provides security benefits across the spectrum and
from security system developers to security system users. For
decades, many highly secure environments have used
biometric technology for entry access. Today, the primary
application of biometrics is in physical security: to control
access to secure locations (rooms or buildings).Biometric
system which rely on the evidence of multiple sources of
information for establishing identity are called Multimodal
biometric system. This paper presents an overview of
multimodal biometrics, challenges faced by multimodal
biometric system . It also discuss their applications to develop
the security system for high security areas. We also discuss
the application of biometric systems and their advantage over
unimodal biometric system. Biometrics permits unmanned
access control. Biometric devices, typically hand geometry
readers, are in office buildings, hospitals, useful for highvolume access control. . A lot of research work is still need in
this area. In near future combination of more than two
biometrics can apply to enhance the security of our system.
REFRENCES
1) L. I. Kuncheva, C. J. Whitaker, C. A. Shipp, and R. P. W.
Duin, “Is Independence Good for Combining Classifiers?”,
Proc. International Conference on Pattern Recognition
(ICPR), Vol. 2, pp. 168-171, Barcelona, Spain, 2001.
2) S. Prabhakar and A. K. Jain, “Decision-level Fusion in
Fingerprint Verification”, Pattern Recognition, Vol. 35, No. 4,
pp. 861-874, 2002.
3) J. L. Wayman, “Fundamentals of Biometric Authentication
Technologies”, International Journal of Image and Graphics,
Vol. 1, No. 1, pp. 93-113, 2001.
4) K.Kryszczuk, J. Richiardi, P.Prodanov, and A.Drygajlo,
"Reliability-Based Decision Fusion inMultimodal Biometric
Verification Systems", EURASIP Journal on Advances in
Signal Processing Volume 2007. 5) J. Kittler, M. Hatef, R. P.
W. Duin, and J. Matas, “On Combining Classifiers”, IEEE
Trans. on Pattern Analysis and Machine Intelligence, Vol. 20,
No. 3, pp. 226-239, Mar 1998. [21] S. Prabhakar and A. K.
Jain, “Decision-level Fusion in Fingerprint Verification”,
Pattern Recognition, Vol. 35, No. 4, pp. 861-874, 2002.
6) W. Zhao, R. Chellapra, P.J. Phillips, A. Rosenfeld, “Face
Recognition: A Literature Survey,” ACM Computing Surveys,
Vol. 35, No. 4, December 2003.
7) M.A. Turk, A.P. Pentland. “Face Recognition Using
Eigenfaces,” IEEE Conference on Computer Vision and
Pattern Recognition, pp.586--591, 1998.
8) P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman,
“Eigenfaces vs. Fisherfaces: Recognition using class specific
linear projection,” IEEE Trans. Pattern Anal. Machine Intell.,
vol. 19, pp. 711–720, May 1997.
9) M.S. Bartlett, J.R. Movellan, T.J. Sejnowski, “Face
Recognition by Independent Component Analysis”, IEEE
Trans. on Neural Networks, Vol. 13, No. 6, November 2002.