ABSTRACT

In the present day world, 4. NEED FOR BIOMETRICS IN

online shopping using WAP enabled MOBILE PHONES
mobile phone has widely come into
use. Credit cards serve as the currency 5. FUTURE MOBILE PHONE
during e-business and
e-Shopping. 6. FACE RECOGNITION:
As technology has advanced in
the negative side also hackers and 7. VOICE RECOGNITION
spoofers steal misuse credit card
numbers, even though the network has 8. FINGERPRINT ACQUISITION
been made secure.
9. CONCLUSION
So, in this paper, we have
proposed a multi-biometric model 10. REFERENCES
(integrating voice, fingerprint and
facial scanning) that can be embedded
in a mobile phone, this making e-
1. INTRODUCTION:
transactions more secure. The model is
Mobile phones have
very cost effective as we have tried to
ceased to be exclusive status of the
use the hardware already present in the
high class and, today has become an
phone.This paper uses for image
indispensable electronic gadget in the
processing or facial recognization and
life of many. The main reason for their
finger print. We have also simulated a
higher market penetrations in recent
few graphs for voice recognition and
days is their incredible array of
facial verification using MATLAB 6.0
functions at an affordable cost. Apart
from setting remainders and sending e-
mails, they are also used in
CONTENTS:  e-business
1. INTRODUCTION  SMS messaging
 Chatting
2. BIOMETRICS
 Telemedicine and
teleconferencing
3. MULTIBIOMETRICS
 Thus, these phones with wide involves confirming or denying a
roaming facility prove to be a really person’s claiming identity.
versatile device.
3. MULTIBIOMETRICS:
2. BIOMETRICS: A multi-biometrics system is
A biometric system is a obtained by the integration of multiple
recognition system, which makes a individual biometrics models. A
personal identification by determining numbers of models integrating hand
the authenticity of a specific geometry, keystroke dynamics, face
physiological or behavioral and iris recognition system have
characteristic possessed by the user. flooded the markets in recent years.
This method of identification is Here we present a multimodal
preferred over traditional methods system that can be embedded in a
involving passwords and PIN numbers mobile phone, which integrates
for various reasons: fingerprint, voice and facial scanning.
 The person to be identified is It shuts down the problem of high
required to be physically False Rejection Rate of facial scanners,
present at the point of eliminates the fooling of fingerprint
identification. scanners and overshadows the
 Identification based on disadvantage of voice recognition
biometric techniques eliminates models.
the need to remember a
password or carry an identity. 4. NEED FOR BIOMETRICS IN
MOBILE PHONES:
Depending on the context on Nowadays, shopping
which a biometric system through the internet has become very
works, it can be popular and surely, a WAP enabled
Either classified as an identification mobile phone provides the facilities to
system or a verification consumers to shop online. Credit cards
(authentication) system identification continue to be an efficient tool for
involves in establishing a person’s online money transactions. But, on the
identify whereas in verification other hand, credit card’s number can
be stolen on its way to its destination
and can be misused by hackers. Thus,
-Business through a mobile phone Facial recognition is
becomes insecure. considered to be one of the most
Also, a report inwww.download.com tedious among all scans. Further,
stated that much anti-fraud Software, difficulty in acquisition of face and
like those provided by ArticSoft and cost of equipments make it more
ISC, created a back door entry and complex.
were largely involved in data spoofing. However, some WAP
In addition to this, many user and enabled phones like CX 400K and LG-
companies were prone to the attack of SD1000 manufactured by LG
many viruses and Trojan horses. electronics, have built in camera that
With so much of problems can acquire images and can be
faced, the service provide turned their transmitted over internet. This it is sent
attention towards biometrics to prevent to the credit card company to verify the
data spoofing and to provide secure e- face received matches with the face in
Transactions their database. If it matches, the goods
are sent, else the order is rejected.
5. FUTURE MOBILE PHONE:

Customer id,
Amount &
Biometric Data

Customer

Orders with
Amount request and Customer id
subsequent sanction

Retailer

We in our IMAGE PROCCESSING

LAB took two faces with small
differences (you see a small dot in the
6. FACE RECOGNITION:
forehead of second face) and
programmed MATLAB to find the
difference between the two. The output
is place below:

Difference between two images can

be found by MATLAB.
Figure 1

The above simulations shows that

even two persons having almost
similar face with minute difference can
also be differentiated.
Now, there arises a problem.
A man, without bread, make as a
transaction successfully .A week later
he makes another transaction with
some hair grown on his chin and go for
acquiring images of any part of the
face like forehead, nose, ear etc.
Hence, this type of facial
scanning system can be used as a part
Figure 2
of the multi-biometric system we have
presented above.

7. VOICE RECOGNITION:
The speaker-specific
characteristics of speech are due to
difference in physiological and
behavioral aspects of the speech
production system in humans. The
main physiological aspect of the
human speech production system is the
vocal tract shape. The vocal tract
modifies the spectral content of an
acoustic wave as it passes through it,
thereby producing speech. Therefore, it
is common in speaker verification
systems to make use of features
derived only from the vocal tract.
The microphone in the
mobile phone captures the speech.
Then, using cepstral analysis, an
utterance may be represented as a
sequence of feature vectors. We recorded a person saying the letter
Utterances, spoken by the same person ‘a’ directly into a sound recorder and
but at difference times, result in similar plotted the graph1. This was
yet a different sequence of features simultaneously recorded in a tape
vectors. So, the irrespective of the recorder and
mood of the consumer, his transaction Graph2 was plotted. The above graph
is accepted or rejected. The following shows some minute differences which
algorithm may be used in voice prove that this system cannot be fooled
verification. by imitation.

Flowchart for Voice verification

 ENROLLMENT MODULE
Face
Extractor

Identity claim
Minutiae
Database browser Extractor

Extractor
Image acquisition Cepstral analysis
Module

Template Database

Face locator Eigenspace

Comparator
Accept/
Minutiae Minutiae Decision Reject
Extractor Matching Fusion

Cepstral HMM
Speech acquisition Analyzer Scoring
module

VERFICATION MODULE
 fingerprints are classified as whorl,
right loop, left loop, arch, and arch.
Recently researchers and scientists
achieved a great feat by improving the
fingerprint classification to 94%.
In today’s world,
fingerprint matching techniques can be
placed into two categories: minutiae-
based and correlation based. In
minutiae based technique, the minutiae
As every mobile phone have an in- points are found and their relative
built microphone and some have video placement are mapped on the finger
camera, the need for an extra hardware whereas in correlation based technique,
for the speech and image acquisition is the fingerprint acquired from the
eliminated. A proposal for the display person is checked for certain points
screen to act as a fingerprint previously stored in the database. If
acquisition is dealt later. both matches, the person is given
authentication, else he is denied
8. FINGERPRINT ACQUISITION: permission.
Finger based scanning
is one of the oldest methods used for
verification. Fingerprints, unique and
immunable for all are made of series of
ridges and furrows on the surface of
the finger. These ridges and furrows
determine the uniqueness of the
fingerprints. Apart from these, minute
points (i.e. local ridge characteristics
that occur at either a ridge bifurcation
or a ridge ending also play role in fool-
proofing this biometric technique.
Transaction scanner embedded
To reduce the search time and the
above display screen
computational complexity, fingerprint
classification is undertaken and thus
 The scanner here is a
transparent layer above the screen. The
scanner consists of arrays of capacitors
of the size of 0.03m. capacitors with
such a small size can be manufactured
with MEMS technology. When the
consumer places his thumb on the
scanner, the points at which his
fingerprint touches the screen get
discharged whereas others remain
charged. Thus the fingerprint is
scanned and is then sent for further
process

9.CONCLUSION:
Thus, this mobile multi-
biometrics can be embedded in mobile
phone. Phone is cost effective since no
special hardware in required and is
highly secured. Thus, this mobile
phone becomes a reality will provide
more e-Business and
E-Transactions
.

10.REFERENCES:
1)”Biometrics” by Samir Nanavathi,
Dreamtech Wiley Publications.
2)”Biometrics made easy for you” by
John walker.
3)”Science and Technology” a
supplementary of “The HINDU”