BIOMETRIC AUTHENTICATION

soilflippantΤεχνίτη Νοημοσύνη και Ρομποτική

17 Νοε 2013 (πριν από 3 χρόνια και 6 μήνες)

48 εμφανίσεις

BIOMETRIC
AUTHENTICATION


SUBMITTED BY:
--



SAYANI MONDAL


ROLL NO


10IT61K01

INFORMATION AND COMMUNICATION TECHNOLOGY


WHAT ARE BIOMETRICS ?






Biometrics are automated methods of identifying a person or
verifying the identity of a person based on a

physiological
or
behavioral

characteristic.










Fig:
-

Basic structure of a biometric system










A biometric system can be divided into two stages:



the
verification
module



the
identification

module


Before that
ENROLLMENT

should be done , in which a sample
of the biometric feature is captured, processed by a
computer, and stored for later comparison.




FIG:
-
ENROLLMENT


User interface

(name ,pin,
fingerprint)

Quality
checker

Feature
extractor


System
database



Verification

:
-
In

this

mode,

biometric

system

authenticates

a

person’s

claimed

identity

from

their

previously

enrolled

pattern
.

This

is

also

known

as

one

to

one

matching
.






Identification
:
-
In

this

mode,

the

biometric

system

identifies

a

person

from

the

entire

enrolled

information

by

searching

a

database

for

a

match
.

This

is

also

known

as

one

to

many

matching
.



User interface

(name ,pin,
fingerprint)

FEATURE
EXTRACTOR

FEATURE
EXTRACTER

MATCHER

MATCHER

SYSTEM
DB

SYSTEM
DB

User interface

(name ,pin,
fingerprint)

TRUE / FALSE

1 TEMPLATE

USERS IDENTITY

N TEMPLATE

CLAIMED IDENTITY

PHYSIOLOGICAL

BEHAVIORAL

FACE

FINGER PRINT

EYE

SIGNATURE

KEY STROKE

SPEECH


BIOMETRICS


CLASSIFICATION OF BIOMETRICS


Fingerprint Recognition

fingerprint authentication

refers to the automated method
of verifying a match between two human fingerprints.


Speech Recognition


speaker recognition uses the acoustic features of speech
that have been found to differ between individuals
.


Face Recognition

Identification of a person by their facial image can be done by
capturing an image of the face in the visible spectrum .

Signature is used to verify User Authentication


Signature



The
iris is a thin circular diaphragm, which lies between the cornea
and the lens of the human eye.



The
function of the iris is to control the amount of light entering
through the
pupil.



Since iris features are distinct from one person to another, these are
considered in iris
-
based recognition process.

UNDERSTANDING THE HUMAN IRIS

IRIS RECOGNITION


Fig:
-

enrollment process





Fig:
-

matching process

IRIS IMAGE
AQUISITION

IRIS IMAGE
AQUISITION

IRIS
LOCALIZATIO
N

IRIS
LOCALIZATION

IRIS
NORMALIZ
ATION

IRIS
NORMALI
ZATION

FEATURE
ENCODIN
G

DB

Feature
encoding

Matching

DB

Match

/reject

STAGES INVOLVED IN IRIS DETECTION



It includes Three Main Stages:
-



Image Acquisition and Segmentation


locating the iris region
in an eye image



Image Normalization


creating dimensionally consistent
representation of the iris region



Feature Coding and Matching


creating a template
containing only the most differentiating feature of the iris.




IMAGE ACQUISITION AND SEGMENTATION




The
Daugman

image
-
acquisition System
:
--

One of the major
challenges of automated iris recognition is to capture a high
-
quality image of the iris.




Obtained images with sufficient resolution and sharpness.



Good contrast in the interior iris pattern with proper
illumination.





SEGMENTATION

Daugman’s

Integro
-
differential Operator :
--


It is used to locate circular iris and pupil boundary regions and
also the arc of the upper and lower eye lids and this is done
by



Where I(
x,y
) is the eye image as the raw input , r is the
increasing radius and center coordinates (x0,y0), *
denotes convolution ,

(r) is a
Gaussian
smoothing
function, (x0,y0,r) define the path of the contour
integration

Isolation of the iris from the rest of the image. The white

graphical overlays signify detected iris boundaries resulting from

the segmentation process.

NORMALIZATION


Daugman’s

Rubber Sheet Model


The points between the inner and outer boundary contours are
interpolated linearly by a homogeneous rubber sheet model,
which automatically
changes the iris pattern deformations
caused by
pupillary

dilation or constriction.




The homogenous rubber sheet model assign to each point in the
iris a pair of dimensionless real coordinates (r, θ) where r lies in
the unit interval (0,1) & θ is the angle (0,2π).



The remapping or normalization of the iris image I(
x,y
) from raw
coordinates (
x,y
) to non concentric coordinate system (r, θ).



Where I(
x,y
) are original iris region Cartesian coordinates


(
x
p

(
θ
),
y
p
(
θ)
) are coordinates of pupil,(
x
s


(
θ
),
y
s


(
θ)
) are the
coordinates of iris boundary along the
θ direction.

FEATURE ENCODING


The iris is encoded to a
unique set of 2048 bits
which serve as the
fundamental identification
of that persons particular
iris.


The iris pattern is then
demodulated to extract the
phase information using


2D Gabor wavelets:
-






where h
{
Re;Im
} can be regarded as a complex
-
valued bit
whose
real and imaginary parts are either 1 or 0 depending on the sign
of the 2D integral; is the raw iris image in a dimensionless
polar coordinate system.




α

and
β

are the multi
-
scale 2D wavelet size parameters.



Only phase information is used for recognizing irises because
amplitude information is not very discriminating, and it depends
upon extraneous factors such as imaging contrast, illumination,
and camera gain.

MATCHING


For matching , a test of statistical independence is required which
helps to compare the phase codes for 2 different eyes.



Exclusive OR operator (XOR)
is applied to 2048 bit phase vectors
that
encode any 2 iris templates
, AND
ed

by both of their
corresponding mask bit vectors to prevent non iris artifacts from
influencing iris comparison.



The XOR operator detects
disagreement between any
corresponding pair of bits
, while AND operator ensures that the

compared bits are not corrupted by eyelashes .




The norms(|| ||) of resultant bit vector and the AND
ed

mask vector
are computed to determine a fractional Hamming distance.




Hamming distance is the measure of dissimilarity between any 2
irises.


HD= ||(code A XOR code B) AND (mask A AND mask B)||


||( mask A AND mask B)||


Where {code A, code B} are phase code vectors bit

And {mask A ,mask B} are mask bit vectors.




We can see that the numerator will be the number of differences
between the mutually non
-
bad bits of code A and code B and that
the denominator will be the number of mutually non
-
bad bits.



If HD result is 0 it is a perfect match.




Biometric System Performance

The following are used as performance metrics for biometric
systems:



false accept rate or false match rate (FAR or FMR)



false reject rate or false non
-
match rate (FRR or FNMR)



equal error rate or crossover error rate (EER or CER)



failure to enroll rate (FTE or FER)



failure to capture rate (FTC)

ADVANTAGES



It is an internal organ that is well protected against damage by a highly
transparent and sensitive membrane
.

This feature makes it
advantageous from finger print.




Flat , geometrical configuration controlled by 2 complementary muscles
control the diameter of the pupil makes the iris shape more predictable .



An iris scan is similar to taking a photograph and can be performed from
about 10 cm to a few meters away.



Encoding and decision
-
making are tractable .



Genetic independence no two eyes are the same.



DISADVANTAGES


The accuracy of iris scanners can be affected by changes in
lightning
.



Obscured by eyelashes, lenses, reflections.



Deforms non
-
elastically as pupil changes size.



Iris scanners are significantly more expensive than some
other form of biometrics.



APPLICATIONS


Used in ATM ’s for more secure transaction.



Used in airports for security purposes
.



Computer login: The iris as a living password



Credit
-
card authentication



Secure financial transaction (e
-
commerce, banking).



“Biometric

key Cryptography “for encrypting/decrypting messages


CONCLUSION


There are many mature biometric systems available now.
Proper design and implementation of the biometric system
can indeed increase the overall security.


There are numerous conditions that must be taken in account
when designing a secure biometric system.



First, it is necessary to realize that biometrics are not secrets.
This implies

that care should be taken and it is not secure to
generate any cryptographic keys from them.


Second, it is necessary to trust the input device and make the
communication link secure.



Third, the input device needs to be verified .

REFERENCES



1.
J. G.
Daugman
, “High confidence visual recognition of persons by a test of statistical
independence,”
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.
15, no. 11, pp. 1148

1161, 1993.


2
J. G.
Daugman
, “How iris recognition works,”
IEEE Transactions on Circuits and System
for Video Technology”, vol. 14, no. 1, pp. 21
-
30, 2004.


3. Amir
Azizi

and
Hamid

Reza
Pourreza
,, “
Efficient IRIS Recognition Through Improvement
of Feature Extraction and subset Selection
”, (IJCSIS) International Journal of Computer
Science and Information Security,
Vol. 2, No.1, June 2009.

4.
www.wikipedia.com


5.
Parvathi

Ambalakat
,” Security of Biometric Authentication Systems”.


6.
John
Daugman
, The Computer Laboratory, University of Cambridge, Cambridge CB3
0FD, UK,” The importance of being random: statistical principles of iris recognition”.


7.
Somnath

Dey

and
Debasis

Samanta
,” Improved Feature Processing for Iris Biometric
Authentication System”, International Journal of Electrical and Electronics Engineering
4:2 2010