www.final-yearprojects.co.cc | www.troubleshoot4free.

com/fyp/

IRIS RECOGNITION SYSTEM

FOR AUTHENTICATION

ABSTRACT compared with the stored IrisCode for

Identification of a person to be himself the identification of the individual.

has been a historical concern. The The unique nature of the Iris guarantee

persons today get identified by their that the individual is recognized to be

signatures, PIN, passwords. But with the himself. No two persons have the same

increasing insecure environment, where Iris structure,not even the same person’s

a person does not know when his ID two eyes have the same structure of

card, password or signature will be iris.The recognition principle is the

stolen, there is an increased need for failure of a test of statistical

providing an identification system that independence on iris phase structure

recognize a person based on attributes encoded by multi-scale quadrature

that are impossible to steal. The Iris with wavelets.

its unique characteristics provides the The image of iris is captured with a

errorless way of recognizing individuals. black and white video camera in a well-

The Iris recognition system uses a video lit environment. The pattern is extracted

based system to locate the Iris in the eye. after elastic deformations are reversed

The information of the Iris is then mathematically,which is possible after

converted to the IrisCode, which then is localizing the inner and outer boundaries
of iris. After pseudo polar coordinate
 www.final-yearprojects.co.cc | www.troubleshoot4free.com/fyp/
mapping and using a method called
complex valued 2D Gabor wavelets,a bit
stream, typically total 256 bytes of
information, is obtained. The amount
and uniqueness of extracted information
make the False Accept probability
lowest of all known biometrics.
INTRODUCTION
Reliable, automatic recognition of
person has long been an attractive goal.
In this discussion one of the most
promising biometric technique called Iris
recognition system is described. It is the
most efficient of all the techniques used
for biometric authentication.
Iris recognition system uses the Iris of
the human to recognize him. Non-
invasive, non-contact and extremely fast,
high-resolution cameras are used to
capture the image of the iris, translating
it into an encrypted digital code, called
IrisCode. This is stored into the database
for future identification of the person.
When the person needs to prove his
identification, the same camera and
process is used to build the IrisCode.
The code previously stored in the
database is then used to compare with
the obtained code and the result is
informed. The complete process of
assessment may take not more than two
seconds thus avoiding the wastage of
time as is done in other techniques such
as Fingerprint recognition system. This
technology does not use the retinal scan
technology and no laser is projected in
the eye as in the retinal scan.
The False Acceptance Rate (FAR) and
False Rejection Rate (FRR) of the Iris
recognition system is very low compared
to the other biometric recognition system
such as fingerprint recognition system.
The Iris recognition system has
advantages such as speed, accuracy,
stability, non-invasiveness, and ability to
do one-to-many matching, etc over the
other identification technologies which
makes it a much sought-after method for
authentication of individuals.
IRIS :
Before discussing how the Iris
recognition system works let us know
about the Iris, which is used for
recognizing the person.
The Iris is a protected internal organ of
the eye, behind the cornea and the
aqueous humor. It is the only internal
organ of the human that is externally
visible. Although small (11 mm) and
sometimes problematic to image, the iris
has the great mathematical advantage
that its pattern variability among
 www.final-yearprojects.co.cc | www.troubleshoot4free.com/fyp/
different persons is enormous such that
no two persons have the same Iris
pattern. Even the identical twins have
different patterns for their irides.
As a planar object its image is relatively
insensitive to angle of illumination, and
changes in viewing angle cause only
reversible affine transformations; even
the non-affine pattern distortion caused
by pupillary dilation is readily
reversible. Finally, the ease of localizing
eyes in faces, and the distinctive annular
shape of the iris, facilitate reliable and
precise isolation of this feature and the
creation of a size-invariant
representation. These features of iris
give us the reason to use it for the
identification of the individuals and once
formed the Iris does not ever change.
This stability of Iris makes the Iris
recognition system to be independent of
the age. The iris pattern can easily be
taken without any problem in dark or in
lights. Also the iris is non-invasive, i.e.
using of the spectacles or lens does not
affect the performance of the system.
TECHNOLOGY BEHIND THE
SCENES:
Iris recognition technology identifies
humans by the unique physiological
patterns in the iris of the eye to a degree
of accuracy surpassing even DNA
matching.
Iris technology is based on pattern
recognition and the pattern-capturing
methodology based on video camera
technology similar to that found in
camcorders commonplace in consumer
electronics. Like these cameras, the
image capture process does not require
bright illumination or close-up imaging.
The complete system can be divided into
four important stages as
1. Finding an Iris in an image
2. Iris feature encoding with
wavelength demodulation
3. Storing into database.
4. Test of statistical
independence
FINDING IRIS IN AN IMAGE:
To capture the rich details of iris
patterns, an imaging system should
resolve a minimum of 50 pixels in iris
 www.final-yearprojects.co.cc | www.troubleshoot4free.com/fyp/
radius. In the field trials to date, a
resolved iris radius of 100
to 140 pixels has been more typical.
Monochrome CCD cameras (480 x 640)
will be been used because NIR (near
infrared) illumination in the 700nm -
900nm band was required for imaging to
be invisible to humans. Some imaging
platforms deployed a wide-angle camera
for coarse localization of eyes in faces,
to steer the optics of a narrow-angle
pan/tilt camera that acquired higher
resolution images of eyes. Imaging can
be done without active pan/tilt camera
optics, by exploiting visual feedback via
a mirror or video image to enable
cooperating Subjects to position their
own eyes within the field of view of a
single narrow-angle camera.
Focus assessment will be performed in
real-time (faster than video frame rate)
by measuring the total high-frequency
power in the 2D Fourier spectrum of
each frame, and seeking to maximize
this quantity either by moving an active
lens or by providing audio feedback to
Subjects to adjust their range
appropriately. Images passing a
minimum focus criterion will be then
analyzed to find the iris, with precise
localization of its boundaries using a
coarse-to-.fine strategy terminating in
single-pixel precision estimates of the
center coordinates and radius of both the
iris and the pupil. Once the coarse-to-
fine iterative searches for both these
boundaries have reached single pixel
precision, then a similar approach to
detecting curvilinear edges is used to
localize both the upper and lower eyelid
boundaries. The result of all these
localization operations is the isolation of
iris tissue from all other image regions,
as illustrated in Figure below.
IRIS FEATURE ENCODING
WITH WAVELET
DEMODULATION:
Each isolated iris pattern is then
demodulated to extract its phase
information using quadrature 2D Gabor
wavelets. It amounts to a patch-wise
phase quantization of the iris pattern, by
identifying in which quadrant of the
complex plane each resultant phasor lies
when a given area of the iris is projected
onto complex-valued 2D Gabor
 www.final-yearprojects.co.cc | www.troubleshoot4free.com/fyp/
wavelets.
Altogether 2,048 such phase bits are
computed for each iris. Also an equal
number of masking bits are computed to
signify whether any iris region is
obscured by eyelids, contains any
eyelash occlusions, specular reflections,
boundary artifacts of hard contact lenses,
or poor signal-to-noise ratio and thus
should be ignored in the demodulation
code as artifact.
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.The extraction of phase
has the further advantage that phase
angles are assigned regardless of how
low the image contrast may be.The
benefit, which arises from the fact that
phase bits are set also for, a poorly
focused image, even if based only on
random CCD noise, is that different
poorly focused irides never become
confused with each other when their
phase codes are compared. By contrast,
images of different faces look
increasingly alike when poorly resolved,
and may be confused with each other by
appearance-based face recognition
algorithms.
STORING INTO THE
DATABASE:
The feature extracted from the iris is
stored into a database for the future use
when the person is produced for the
identification. The database generally is
the central database as the Iris
recognition system works for
identification (one to many). The data
stored is 2048 bits (512 bytes) consisting
of 256 bytes of the iris pattern and 256
byte of masking pattern. The iris
recognition system works even for large
size database of around 1 million iris
pattern stored into the database.
TEST OF STATISTICAL
INDEPENDENCE:
The key to iris recognition is the failure
of a test of statistical independence,
which involves so many degrees-of-
 www.final-yearprojects.co.cc | www.troubleshoot4free.com/fyp/

freedom that this test is virtually correspond to those stored in the

guaranteed to be passed whenever the database.
phase codes for two different eyes are
compared, but to be uniquely failed
when any eye’s phase code is compared
with another version of itself. The test of
statistical independence is implemented
by the simple Boolean Exclusive-OR
operator (XOR) applied to the 2,048 bit
phase vectors that encode any two iris
patterns, masked (AND’ed) by both of
their corresponding mask bit vectors to The histogram of the 2.3 million best
prevent non-iris artifacts from HDs is shown in Fig below. The fact that
influencing iris comparisons. The XOR the minimum HD observed in all of
operator detects disagreement between these rotated comparisons was never
any corresponding pair of bits, while the smaller than 0.333 illustrates the extreme
AND operator ensures that the compared improbability that the phase sequences
bits are both deemed to have been for two different irises might disagree in
uncorrupted by eyelashes, eyelids, fewer than a third of their bits. This
specular reflections, or other noise. The suggests that in order to identify people
norms of the resultant bit vector and of by their iris patterns with high
the AND’ed mask vectors are then confidence, we need to demand only a
measured in order to compute a very forgiving degree of match (say, HD
fractional Hamming Distance (HD) as < 0.330).
the measure of the dissimilarity between
any two irides. A Hamming Distance of
zero would represent a perfect match.
The below equation describes the
process of finding the hamming distance.
CodeA and maskA corresponds to the
live IrisCode, and codeB and maskB
 www.final-yearprojects.co.cc | www.troubleshoot4free.com/fyp/

performance standards for this

technology, while an unmatched
EER (equal error rate) performance
of 1 in 1.2 million is delivered. Other
electronic authentication
technologies sometimes select a
number of templates that represent
"possible matches" - perpetuating the

ADVANTAGES: potential for error, in that final

Iris recognition has many advantages determination of identity relies on a

over the other forms of biometric human interpretation.

identification.  Fingerprints, facial recognition

1. Accuracy: and hand geometry have far less

Simply put, iris recognition is the most detailed input in template

accurate form of identification known to construction. In fact, it's probably

man. More accurate than even DNA fair to say that one iris template

matching. contains more data than is collected

 Due to the process of chaotic in creating templates for a finger, a

morphogenesis, every iris is unique face and a hand combined. This is

to a degree that the probability of 2 one reason why iris recognition can

irises being identical is 1 in 10 to the authenticate with confidence even

power of 78. Additionally, our iris when significantly less than the

recognition system captures over 249 whole eye is visible.

'degrees of freedom' or points of 2. Speed:

interest.  No other biometric technology is

 Another differentiator impacting designed to deliver 1-n searching of

accuracy is that no human large databases in real time. This

intervention is required to "set" technology has nearly 20 times more

thresholds for False Accept and matches per minute than its closest

False Reject performance. Instead, competitor. Looking at speed in

the human element plays no role in conjunction with accuracy, there's

 www.final-yearprojects.co.cc | www.troubleshoot4free.com/fyp/
simply no other technology that can
deliver high accuracy authentication in
anything close to the real-time
performance of iris recognition.
IDENTIFICATION VS
VERIFICATION:
Iris recognition identifies people rather
than verifying their identity.
Verification asks; is this person who
they say they are? This is one-to-one
matching which means a person must
first suggest their identity through a
password, card or name and the system
then seeks to determine whether or not
there is a match between the suggested
and true identities.
Identification asks; who is this person?
This is one-to-many matching meaning
that the person is not required to carry
anything or volunteer any information.
The system simply captures the iris
image, searches the entire database and
either finds their identity or reports that
they are unknown. This is obviously a
much more powerful form of
authentication as no information is
required from the user.
3. Stability
The iris image remains stable from the
age of about 10 months up until death.
This means that an iris image need only
be captured once and does not need to be
updated. Other biometric measures
change over time. Hands and fingers
grow, our voices change, our skin
degrades and other biometric measures
are subject to labor, health, genetics,
climate and age.
What this means is that the performance
of such systems is unreliable and
frequent re-enrolments are required to
accommodate these changes.
Non-invasive
 No bright lights or lasers are used
in the imaging and iris authentication
process. The user can stand as far as
10" away from the unit, and even
wear glasses or contact lenses
without compromising system
accuracy. Unlike some other popular
biometrics, iris authentication
involves no physical contact.
 It is also important to note that
iris recognition is a completely
separate technology to retinal
scanning. No bright lights or lasers
are beamed into the eye, only a
digital photograph is taken. This
means that not only is iris
recognition the most accurate
 www.final-yearprojects.co.cc | www.troubleshoot4free.com/fyp/

biometric technology, it is also the • Productivity enhancing applications

safest. like time and attendance.
IRIS RECOGNITION VS DNA CONCLUSION:
TEST:
Iris provides the highly accurate and
The birth rate of identical twins is 1 in
positive personal recognition technique
121 births or 0.82%. As identical twins
for authentication. This unique and
share the same DNA, the false
complex organ, which has more
acceptance rate for any DNA based
dimensions (measures) of variation than
system must be at least 0.82% due to the
any other biometric feature currently in
birth rate alone. DNA testing is an
use, remains stable throughout a lifetime
invasive technology with a cotton swab
and is readily available for sampling in
inserted into the mouth the most
non-intrusive way.
common method of obtaining a sample.
BIBLIOGRAPHY:
This makes iris recognition the most
preferred of all authentication system
• John Daugman PhD, OBE High
APPLICATIONS:
confidence Recognition of

The Iris recognition system covers a Persons by their Iris patterns

wide range of application in University of Cambridge, The

authenticating persons It can be Computer Laboratory,

deployed in: Cambridge CB2 3QG, U.K.

• Border control system • Ga’el Hacihez, Francois Koeune,

• Airports Jean-Jacques Quisquater:

• Biometric passports Biometrics, Access Control,

• Banking systems, ATM’s Smart Cards: A Not So Simple

• Authorized access to healthcare Combination. UCL Crypto

records, intellectual property, etc Group, University catholique de

• Identification of criminals Louvain, Belgium.

• In Govt. organization where • http://www.iridian.org/IrisCode

restricted access exists • http://www.lgIris.com/iris/

• http://www.biometricwatch.com
• http://biometric.cse.msu.edu