Bio Metrics in Secure

8/8/2019 Bio Metrics in Secure

1/20

BIOMETRICS IN SECURE

E-TRANSACTION

Presented byA.V.RAM PRAKASH

R.GOPINATH


2/20

INTRODUCTION In the present day world, online shopping

using WAP enabled mobile phone has widelycome into use.

In this paper, we have proposed a multi-

biometric model (integrating voice,fingerprint and facial scanning) that canbe embedded in a mobile phone, thusmaking the e-transactions more secure.

The model is very cost effective as we havetried to use the hardware already present inthe phone.


3/20

WHY BIOMETRICS?The person to be identified is required to be

physically present at the point ofidentification.

Identification based on biometric techniqueseliminates the need to remember apassword or carry an identity.

Token-based identification methods such as passports and drivers licenses may be forged, stolen, or lost.


4/20

WHAT IS BIOMETRICS?o Biometrics refers to the automatic

identification of a person based on his or herphysiological or behavioral characteristics

o

o Physical characteristics are fingerprint,facialrecognition/face location,hand geometry,irisscan,retinal scan,vascular patterns.

o

o Behavioral characteristics aresignature/handwriting, keystroke/patterning,

speaker/voice recognition

o


5/20

multi-biometrics It is obtained by the integration of multiple

individual biometrics models.

Here we present a multimodal system that can beembedded in a mobile phone, which integrates

fingerprint, voice and facial scanning. It shuts down the problem of high False Rejection Rate of facial scanners,

eliminates the fooling of fingerprint scanners

and overshadows the disadvantage of voicerecognition models.


6/20

NEED FOR BIOMETRICS INMOBILE PHONES

Nowadays, shopping through the internet hasbecome very popular.

WAP enabled mobile phone provides the facilitiesto consumers to shop online.

Credit cards continue to be an efficient tool foronline money transactions. But, on the otherhand, credit cards number can be stolen on itsway to its destination and can be misused byhackers

Many user and companies were prone to theattack of many viruses and Trojan horses.

With so much of problems faced, the serviceproviders turned their attention towards

biometrics to prevent data spoofing and toprovide secure e-Transactions.


7/20

MODULES

Face Recognition

Voice Recognition

Finger print Acquisition


8/20

FUTURE MOBILE PHONE


9/20

FACE RECOGNITION Facial recognition is considered to be one of

the most tedious among all scans.

some WAP enabled phones like CX 400K andLG-SD1000 manufactured by LG electronics,

have built in camera that can acquireimages and can be transmitted overinternet.

This is sent to the credit card company to

verify the face received matches with theface in their database. If it matches, thegoods are sent, else the order is rejected.


10/20

PROTOCOL IN FACE RECOGNITION


11/20

CONT.

In o ur IMAGE PROCCESSING LAB to o k two fac e swith small differences (you can see a small dotin the forehead of second face) andprogrammed MATLAB to find the difference

between the two. The output is showm below:


12/20

CONT..

The above simulations shows that even twopersons having almost similar face with minutedifference can also be differentiated.


13/20

VOICE RECOGNITIONThe speaker-specific characteristics of speech

are due to difference in physiological andbehavioral aspects of the speech productionsystem in humans.

The main physiological aspect of the humanspeech production system is the vocal tractshape

The microphone in the mobile phone capturesthe speech.

Using cepstral analysis, an utterance may berepresented as a sequence of featurevectors.

Utterances, spoken by the same person but atdifferent times, result in similar yet adifferent sequence of features vectors.


14/20


15/20

CONT.


16/20

FINGERPRINT ACQUISITION Fingerprints are unique and immutable for

all ,are made of series of ridges and furrowson the surface of the finger.

These ridges and furrows determine the

uniqueness of the fingerprints. Apart from these, minutiae points i.e. local

ridge characteristics that occur at either aridge bifurcation or a ridge ending also play

role in fool-proofing this biometric technique fingerprints are classified as whorl, right loop,

left loop, and arch.


17/20

CONT....

Fingerprint matching techniques can beplaced into two categories: minutiae-basedand correlation based.

In minutiae based technique, the minutiae

points are found and their relativeplacement are mapped on the finger .

correlation based technique, the fingerprintacquired from the person is checked for

certain points previously stored in thedatabase


18/20

TRANSACTION SCANNER EMBEDDEDABOVE DISPLAY SCREEN

The scanner here is a transparent layer abovethe screen

The scanner consists of arrays of capacitorsof the size of 0.03mm


19/20

ADVANTAGES Cost effective

No special hardware is needed

Highly secured

It reduces fraud by employing hard-to-forgetechnologies and materials.

It eliminates problems caused by lost IDs orforgotten passwords by using physiologicalattributes.


20/20

20Japanese

Hebre

w

Thank You

Englis

h

MerciFrenc

h

Russian

DankeGerman

GrazieItalia

n GraciasSpanish

Obrigado

Portuguese

Arabic

Simplified Chinese

Traditional Chinese

Tami

l

Thai

Korean

Documents

Bio Metrics in Secure