Submitted by G.SRIVIDHYA R.VIJAYALAKSHMI

BIO METRICS






IRIS RECOGNITION







Submitted by




G.SRIVIDHYA


vidhu91bhuvana@gmail.com





R.VIJAYALAKSHMI


viji22raja@gmail.com




2
nd

year, B.E Bio
-
Medical Engineering,


Rajalakshmi Engineering College,


Thandalam.





August 2009





A Typical Iris



Abstract:




Biometrics refers to automatic recognition of individuals based on
their physiological and behavioral characteristics. Iris recognition is based on
the
physiological character, random pattern of the iris.

In this paper, we
propose an efficient method for personal identification by analyzing iris
patterns that have a

high level of stability and distinctiveness.

Iris pattern
differs for every individual and

thus making it a good biometric.

Introduction:




Among various physiological characteristics iris patterns have

attracted a lot of attention for th
e last few decades in biometric
technology
because they have stable and distincti
ve features

for personal identification.
They are unique to people and

stable with age [2,3]. The difference even
exists between

identical twins and between the left and the right eye of the

same person
. A general iris recognition system is composed of

fo
ur steps.
Firstly an image containing the eye is captured then

image is preprocessed to
extract the iris. Thirdly eigenirises

are used to train the system and fin
ally
decision is made by
means of matching.


Anatomy of Iris:














A blue iris








Iris is an opaque structure and a visible coloured porti
on of the
eye. The ciliary body continues to form the iris which is pigmented.
The
iris

is
responsible for controlling the amount of light reaching the
retina
.

The iris
consists of two layers,

the front
pigmented

fibrovascular tissue

known as a
stroma

and beneath the stroma are pigmented epithelial cells. The iris can be
green, blue, or brown. In some cases it can be hazel.

It is the most forward
portion o
f the eye and the only one seen on superficial inspection.

Iris color is
a highly complex phenomenon consisting of the combined effects of texture,
pigmentation, fibrous tissue and blood vessels within the iris stroma
.

The iris
and ciliary body together ar
e known as the anterior uvea. Just in front of the
root of the iris is the region referred to as the trabecular meshwork
1
.




1

The
trabecular meshwork

is an area of tissue in the
eye

located around the base of the
cornea
.



Review of the Past:




The idea of using patterns for personal identificati
on was
originally proposed in 1936 by ophthalmologist Frank Burch.. In 1987, two
other ophthalmologists Aram Safir and Leonard Flom patented this idea and
in 1987 they asked John Daugman to try to create actual algorithms for this
iris recognition.




These algorithms which Daugman patented in 1994 are the
basis for all current iris recognition systems and products.

In 1995, first
commercial products came available. In 2005, broad patent covering the basic
concept of iris recogniti
on came out, providing marketing opportunities for
other companies that have developed their own algorithm for iris recognition.


IRIS RECOGNITION TECHNOLOGY:










SYNOPSIS




Image acquisition



Image processing



Image localization



Feature extraction



Numeric code



Pattern matching



Bar code storage
















Image acquisition
:





An image surrounding human eye region is obtained at a
distance

from a CCD camera
2

without any physical contact to the

device.
Figure 3 shows the device configuration for acquiring

human eye images. To
acquire more clear
images through a

CCD camera and minimize the effect of
the reflected lights

caused by the surrounding illumination, we arrange two
halogen

lamps as the surrounding lights, as the figure illustrates.

The size of
the image acquired under this circumstances i
s

320

X
240.








2

A
charge
-
coupled device

(
CCD
) is an
analog

shift register

that enables the transportation of analog signals
(electric cha
rges) through successive stages (capacitors), controlled by a
clock signal


Operator

Image

aquisition

Image



Iris

Localization


Feature

Extraction


N
umeric


code


Pattern


Matching


Bar code

Matching






Various iris Patterns



There are 3 important requisites for this process


a) It is desirable to acquire images of the iris with sufficient resolution and

sha
rpness to support recognition


b) It is important to have good contrast in the interior iris pattern without

restoring to a level of illumination that annoys the Operator, that is adequate

intensity of source constrained by operators comfort with brightnes
s.


c) These images must be well framed without unduly constraining the
operator.


The widely used recognition system is the
D
augmen system

which captures

images with the iris diameter typically between 100 and 200 pixels from a

distance of 15, 46 cm using

a 330 mm lens.




Image Processing:













Image of the Iris








An iris image contains some irrelevant parts (e.g., eyelid,

sclera,
pupil, etc.). Also, the size of an iris ma
y vary depending

on camera
-
to
-
eye
distance and lighting condition. Therefore,

the origi
nal image needs to be
processed.



In this stage, we should determine an iris part of the image

by
localizing the portion of the image derived from inside

the

limbus (outer
boundary) and outside the pupil (inner boundary),

and finally convert the iris
part into a suitable representation
.








Image localization:








To localize an iris, we should find the center of the pupil at

first, and then determine the inner and outer boundaries. Because

there is
some obvious difference in the intensity around

each boundary, an
edge
detection method

is eas
ily applied to

acquire the edge information. For every
two points of the edge

that may be regarded as the inner boundary by some
prior

knowledge of the images, we apply the bisection method to determine

the center of the inner boundary, which is also used
for

the reference point of
the following processes. By applying the

bisection method
3

to every two
points on the same edge, we can

get only one point in the ideal case which
crosses every perpendicular

line over the line connecting to two points, but
actua
lly

we cannot obtain only one point so we select the center

point as the most
frequently crossed point.









Localizing if the iris image




After determining the
center point, we find the inner

boundary

and the outer boundary by extending the radius of a virtual




3

he
bisection method

is a
root
-
finding algorithm

which repeatedly bisects an
interval

circle from the center of pupi
l.



The localized iris part from the image is transformed into
polar

coordination system in an ef
ficient way so as to facilitate the

next
process, the feature extraction process. The portion of the

pupil is excluded
from the conversion process because it has no

biological characteristics at all.
The distance between the inner

boundary and the outer bo
undary is
normalized into [0, 60] according

to the radius
r
.



Feature extraction:



Gabor transform
4

and
wavelet transform
5

are typically used
for analyzing the human iris patterns and extracting feature points from them.

Eac
h isolated iris pattern is then demodulated to

extract its phase information
using quadrature 2D Gabor

wavelets (Daugman
1985, 1988, 1994)
. It amounts
to

a patch
-
wise phase quantization of the iris pattern, by

identifying in which
quadrant of the complex p
lane

each resultant phasor lies when a given area of
the iris

is projected onto c
omplex
-
valued 2D Gabor wavelets.









4

The
Gabor transform

is a special case of the
short
-
time Fourier transform
. It is used to determine the
sinusoidal

frequency

and
phase

content of local sections of a signal as it changes over time.

5

a
wavelet series

is a representation of a
square
-
integrable

(
real
-

or
complex
-
valued)
function

by a certain
orthonormal

series

generated by a
wavelet













Feature extracted






Only phase information is used for recognizing

irises because
amplitude information is not very discriminating,

and it depends up
on
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
.


Numeric code:




Conve
rsion of an iris image into a numeric code that can be
easily manipulated is

essential to its use. This process developed by John
Daugman. Permits efficient

comparison of irises. Upon the location of the iris,
an iris code is computed based on the

informat
ion from a set of Gabor
wavelets. The Gabor wavelet is a powerful tool to make

iris recognition
practical. These wavelets are specialized filter banks that extract

information
from a signal at a variety of locations and scales. The filters are members of

a

family of functions developed by Dennis Gabor, that optimizes the

resolution in both

spatial and frequency domains. The 2
-
D Gabor wavelets
filter and map segments of iris

into hundreds of vectors. The wavelets of
various sizes assign values drawn from th
e

orientation and spatial frequency
of select areas, bluntly referred to as the “what” of the

sub
-
image, along with
the position of these areas, bluntly referred to as the “where”. The

“what” and
where are used to form the Iris Code. Not all of iris is use
d: a portion of the

top, as well as 450 of the bottom is unused to account for eyelids and

camera
—
light

reflections. The iris Code is calculated using 8 circular bands
that have been adjusted to

the iris and pupil boundaries.







Iris recognition technology converts the visible characteristics
of the iris into a

512 byte Iris Code, a template stored for future verification
attempts. 5l2 bytes is a fairly

compact size for a biometric template, but the
quantit
y of information derived from the

iris is massive. From the iris 11 mm
diameters, Dr. Daugman’s algorithms provide 3.4

bits of data per square mm.
This density of information is such that each iris can be said

to have 266
unique “spots”, as opposed to 13
-

60 for traditional biometric technology.

This 266 measurement is cited in all iris recognition literature, after allowing
for the

algorithms for relative functions and for characteristics inherent to
most human eyes. Dr.Daugman concludes that 173 “independ
ent binary
degrees of freedom can be extracted

from his algorithm
-
and exceptionally
large number fur a biometric, for future

identification, the database will not be
comparing images of iris, but rather hexadecimal

representations of data
returned by wavel
et filtering and mapping. The Iris Code for an

iris is
generated within one second. Iris Code record is immediately encrypted and
cannot

be reverse engineered.


Pattern matching:







When a live iris

is presented for comparison, the iris pattern is
processed and

encoded into 512 byte Iris Code. The Iris Code derived from
this process is compared

with previously generated Iris Code. This process is
called pattern matching. Pattern

matching evaluates th
e goodness of match
between the newly acquired iris pattern and

the candidate’s data base entry.
Based on this goodness of match final decision is taken

whether acquired data
does or doesn’t come from the same iris as does the database entry.




Pattern matching is performed as follows. Using integer XOR
logic in a single

clock cycle, a long vector of each to iris code can be XORed
to generate a new integer.

Each of whose bits represent mismatch between the
vectors being compared. The t
otal

number of 1s represents the total number of
mismatches between the two binary codes.

The difference between the two
recodes is expressed as a fraction of mismatched bits

termed as hamming
distance. For two identical Iris Codes, the hamming distance is

Zero.

For
perfectly unmatched Iris Codes, the hamming distance is 1. Thus iris patterns
are

compared. The entire process i.e. recognition process takes about 2
seconds. A key

differentiator for iris recognition is its ability to perform
identification usi
ng a one to

many search of a d
atabase, with no limitation on
the number of iris code records

contained there in.


Bar code storage:







Barcode is stored in the computer

data base. This bar code is
used for study about the individual in future.

To the iris code, individual’s
complete information is stored. This helps for the identification of the person
or an individual.



Advantage:





∙ Highly protected, internal organ o
f the eye




∙ Externally visible; patterns imaged from a distance




∙ Patterns apparently stable throughout life




∙ Encoding and decision
-
making are tractable




∙ Image analysis and encoding time: 1 second




∙ Search speed: 100,000 Iris Codes per second


Disad
vantages:




∙ Small target (1 cm) to acquire from a distance (1m)




∙ Located behind a curved, wet, reflecting surface




∙ Obscured by eyelashes, lenses, reflections




∙ Partially occluded by eyelids, often drooping




∙ Deforms non
-
elastically as pupil changes
size




∙ Illumination should not be visible or bright




∙ Some negative connotations



Applications:













Iris
-
based identification and verification technology has

gained
acceptance in a

number of different areas. Application of i
ris recognition
technology can b
e limited only

by imagination. The important applications are
those following:




∙ Computer login: The iris as a living password.




∙ National Border Controls:

The iris as a living password.




∙ Telephone call charging without cash, cards or PIN numbers.




∙ Ticket less air travel.




∙ Premises access control (home, office, laboratory etc.).




∙ Driving licenses and other personal certificates.




∙ Entitlements and b
enefits authentication.




∙ Forensics, birth certificates, tracking missing or wanted person




· “Biometric
—
key Cryptography “for encrypting/decrypting messages


REFERENCES


1. Daugman J (1999) "Wavelet demodulation codes, statistical independence,
and

patte
rn recognition." Institute of Mathematics and its Applications,
Proc.2
nd

IMA
-
IP
.
London: Albion, pp 244
-

260.

2. Daugman J (1999) "Biometric decision landscapes." Technical Report No
TR482,

University of Cambridge Computer Laboratory.

3. Daugman J and Dow
ning C J (1995) "Demodulation, predictive coding, and

spatial vision." Journal of the Optical Society of America A
,
vol. 12, no. 4, pp
641

-

660.

4. Daugman J (1993) "High confidence visual recognition of persons by a test
of

statistical independence." IEE
E Transactions on Pattern Analysis and
Machine

Intelligence
,
vol. 15, no. 11, pp 1148
-

1160.

5.“Complete discrete 2D gabor transforms by neural networks for

image
analysis and compression,”
IEEE Trans. Acoust., Speech, Signal

Processing
,
vol. 36, pp. 1169
–
1179, July 1988.


WEB SITE

∙
http://www.cl.cam.ac.uk/~jgd1000/

∙ http://en.wikipedia.org/wiki/Iris_recognition