Post on 28-Nov-2014
IRIS RECOGNITION SEMINAR REPORT 2011
Chapter1:INTRODUCTION
1.1:Biometric Technology
Biometrics is the science of establishing human identity by using physical or
behavioral traits such as face, fingerprints, palm prints, iris, hand geometry, and voice. Iris
recognition systems, in particular, are gaining interest because the iris’s rich texture offers a
strong biometric cue for recognizing individuals. Located just behind the cornea and in front
of the lens, the iris uses the dilator and sphincter muscles that govern pupil size to control the
amount of light that enters the eye. Near-infrared (NIR) images of the iris’s anterior surface
exhibit complex patterns that computer systems can use to recognize individuals. Because
NIR lighting can penetrate the iris’s surface, it can reveal the intricate texture details that are
present even in dark-colored irides. The iris’s textural complexity and its variation across
eyes have led scientists to postulate that the iris is unique across individuals. Further, the iris
is the only internal organ readily visible from the outside. Thus, unlike fingerprints or palm
prints, environmental effects cannot easily alter its pattern. An iris recognition system uses
pattern matching to compare two iris images and generate a match score that reflects their
degree of similarity or dissimilarity.
Iris recognition systems are already in operation worldwide, including an expellee
tracking system in the United Arab Emirates, a welfare distribution program for Afghan
refugees in Pakistan, a border-control immigration system at Schiphol Airport in the
Netherlands, and a frequent traveler program for preapproved low-risk travelers crossing the
US-Canadian border.
Iris recognition efficacy is rarely impeded by glasses or contact lenses. Iris technology
has the smallest outlier (those who cannot use/enroll) group of all biometric technologies.
Because of its speed of comparison, iris recognition is the only biometric technology well-
suited for one-to-many identification. A key advantage of iris recognition is its stability, or
template longevity, as, barring trauma, a single enrollment can last a lifetime.
Dept. Of Electronics and Communication Engineering, VKIT Page 1
IRIS RECOGNITION SEMINAR REPORT 2011
1.2.History and Development of Biometrics
The idea of using patterns for personal identification was originally proposed in 1936
by ophthalmologist Frank Burch. By the 1980’s the idea had appeared in James Bond films,
but it still remained science fiction and conjecture. 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.
Daugman algorithms are owned by Iridian technologies and the process is licensed to
several other Companies who serve as System integrators and developers of special platforms
exploiting iris recognition in recent years several products have been developed for acquiring
its images over a range of distances and in a variety of applications. One active imaging
system developed in 1996 by licensee Sensar deployed special cameras in bank ATM to
capture IRIS images at a distance of up to 1 meter. This active imaging system was installed
in cash machines both by NCR Corps and by Diebold Corp in successful public trials in
several countries during I997 to 1999. a new and smaller imaging device is the low cost
“Panasonic Authenticam” digital camera for handheld, desktop, e-commerce and other
information security applications. Ticket less air travel, check-in and security procedures
based on iris recognition kiosks in airports have been developed by eye ticket. Companies in
several, countries are now using Daughman’s algorithms in a variety of products.
1.2Classification of Biometrics
Dept. Of Electronics and Communication Engineering, VKIT Page 2
IRIS RECOGNITION SEMINAR REPORT 2011
Fig: Classification of Biometrics
Biometrics encompasses both physiological and behavioral characteristics. A
physiological characteristic is a relatively stable physical feature such as finger print, iris
pattern, retina pattern or a Facial feature. A behavioral trait in identification is a person’s
signature, keyboard typing pattern or a speech pattern. The degree of interpersonal variation
is smaller in a physical characteristic than in a behavioral one. For example, the person’s iris
pattern is same always but the signature is influenced by physiological characteristics.
Disadvantages
Even though conventional methods of identification are indeed inadequate, the
biometric technology is not as pervasive and wide spread as many of us expect it to be. One
of the primary reasons is performance. Issues affecting performance include accuracy, cost,
integrity etc.
Accuracy
Even if a legitimate biometric characteristic is presented to a biometric system,
correct authentication cannot be guaranteed. This could be because of sensor noise,
limitations of processing methods, and the variability in both biometric characteristic as well
as its presentation.
Cost
Cost is tied to accuracy; many applications like logging on to a pc are sensitive to
additional cost of including biometric technology.
Dept. Of Electronics and Communication Engineering, VKIT Page 3
HAND
SIGNATURE
IRIS
FACE FINGER
VOICE
COST
ACCURACY
RETINA
IRIS RECOGNITION SEMINAR REPORT 2011
FIGURE 2. COMPARISON BETWEEN COST AND ACCURACY
Chapter2:IRIS RECOGNITION
2.1 Anatomy of the Human Iris
The iris is a thin circular diaphragm, which lies between the cornea and the lens of the human
eye. A front-on view of the iris is shown in Figure 1.1. The iris is perforated close to its
center by a circular aperture known as the pupil. The function of the iris is to control the
amount of light entering through the pupil, and this is done by the sphincter and the dilator
muscles, which adjust the size of the pupil. The average diameter of the iris is 12 mm, and the
pupil size can vary from 10% to 80% of the iris diameter [2]. The iris consists of a number of
layers; the lowest is the epithelium layer, which contains dense pigmentation cells. The
stromal layer lies above the epithelium layer, and contains blood vessels, pigment cells and
the two iris muscles. The density of stromal pigmentation determines the colour of the iris.
The externally visible surface of the multi-layered iris contains two zones, which often differ
in colour [3]. An outer ciliary zone and an inner pupillary zone, and these two zones are
divided by the collarette – which appears as a zigzag pattern.
Fig 1.1 :A front-on view of the human eye
Formation of the iris begins during the third month of embryonic life . The unique pattern on
the surface of the iris is formed during the first year of life, and pigmentation of the stroma
takes place for the first few years. Formation of the unique patterns of the iris is random and
not related to any genetic factors . The only characteristic that is dependent on genetics is the
pigmentation of the iris, which determines its colour. Due to the epigenetic nature of iris
Dept. Of Electronics and Communication Engineering, VKIT Page 4
IRIS RECOGNITION SEMINAR REPORT 2011
patterns, the two eyes of an individual contain completely independent iris patterns, and
identical twins possess uncorrelated iris patterns
2.2History and development of IRIS
The human iris begins to form during the third month of gestation. The structures creating its
distinctive pattern are completed by the eighth month of gestation hut pigmentation continues
in the first years after birth. The layers of the iris have both ectodermic and embryological
origin, consisting of: a darkly pigmented epithelium, pupillary dilator and sphincter muscles,
heavily vascularized stroma and an anterior layer chromataphores with a genetically
determined density of melanin pigment granules. The combined effect is a visible pattern
displaying various distinct features such as arching ligaments, crypts, ridges and zigzag
collaratte. Iris color is determined mainly by the density of the stroma and its melanin
content, with blue irises resulting from an absence of pigment: long wavelengths are
penetrates and is absorbed by the pigment epithelium, while shorter wavelengths are reflected
and scattered by the stroma. The heritability and ethnographic diversity of iris color have
long been studied. But until the present research, little attention had been paid to the
achromatic pattern complexity and textural variability of the iris among individuals.
A permanent visible characteristic of an iris is the trabecular mesh work, a tissue
which gives the appearance of dividing the iris in a radial fashion. Other visible
characteristics include the collagenous tissue of the stroma, ciliary processes, contraction
furrows, crypts, rings, a corona and pupillary frill coloration and sometimes freckle. The
striated anterior layer covering the trabecular mesh work creates the predominant texture with
visible light.
2.3STAGES INVOLVED IN IRIS DETECTION
It includes Three Main Stages
2.3.1) Image Acquisition and Segmentation
2.3.2) Image Normalization
2.3.3) Feature Coding and Matching
Dept. Of Electronics and Communication Engineering, VKIT Page 5
IRIS RECOGNITION SEMINAR REPORT 2011
2.3.1 IMAGE ACQUISITION AND SEGMENTATION
IMAGE ACQUISITION
One of the major challenges of automated iris recognition is to capture a high-quality image
of the iris while remaining non invasive to the human operator.
Concerns on the image acquisition rigs
Obtained images with sufficient resolution and sharpness
Good contrast in the interior iris pattern with proper illumination
Well centered without unduly constraining the operator
Artifacts eliminated as much as possible
Fig :The Daugman image-acquisition System
Dept. Of Electronics and Communication Engineering, VKIT Page 6
IRIS RECOGNITION SEMINAR REPORT 2011
Fig:Wildes et al image-acquisition System
Segmentation
The first stage of iris recognition is to isolate the actual iris region in a digital eye image.
The iris region, shown in Figure 1.1, can be approximated by two circles, one for the
iris/sclera boundary and another, interior to the first, for the iris/pupil boundary. The eyelids
and eyelashes normally occlude the upper and lower parts of the iris region. Also, specular
reflections can occur within the iris region corrupting the iris pattern. A technique is required
to isolate and exclude these artifacts as well as locating the circular iris region.
This can be done by using the following techniques
Hough Transform
Daugman Integro- Differential operator
Hough Transform:
The Hough transform is a standard computer vision algorithm that can be used to
determine the parameters of simple geometric objects, such as lines and circles, present in an
image. The circular Hough transform can be employed to deduce the radius and centre
coordinates of the pupil and iris regions. An automatic segmentation algorithm based on the
circular Hough transform is employed by Wildes et al.Firstly, an edge map is generated by
calculating the first derivatives of intensity values in an eye image and then thresholding the
result. From the edge map, votes are cast in Hough space for the parameters of circles passing
through each edge point. These parameters are the centre coordinates xc and yc, and the
Dept. Of Electronics and Communication Engineering, VKIT Page 7
The Daugman image-acquisition rigThe Daugman image-acquisition rig
The Daugman image-acquisition rigThe Daugman image-acquisition rig
IRIS RECOGNITION SEMINAR REPORT 2011
radius r, which are able to define any circle according to the equation
A maximum point in the Hough space will correspond to the radius and centre coordinates of
the circle best defined by the edge points. Wildes et al. make use of the parabolic Hough
transform to detect the eyelids, approximating the upper and lower eyelids with parabolic
arcs, which are represented as;
In performing the preceding edge detection step, Wildes et al. bias the derivatives in the
horizontal direction for detecting the eyelids, and in the vertical direction for detecting the
outer circular boundary of the iris, this is illustrated in Figure shown below. The motivation
for this is that the eyelids are usually horizontally aligned, and also the eyelid edge map will
corrupt the circular iris boundary edge map if using all gradient data. Taking only the vertical
gradients for locating the iris boundary will reduce influence of the eyelids when performing
circular Hough transform, and not all of the edge pixels defining the circle are required for
successful localisation. Not only does this make circle localisation more accurate, it also
makes it more efficient, since there are less edge points to cast votes in the Hough space.
Figure 2.1– a) an eye image b) corresponding edge map c) edge map with only horizontal
gradients d) edge map with only vertical gradients.
Daugman’s Integro-differential Operator
Dept. Of Electronics and Communication Engineering, VKIT Page 8
IRIS RECOGNITION SEMINAR REPORT 2011
Daugman makes use of an integro-differential operator for locating the circular iris and pupil
regions, and also the arcs of the upper and lower eyelids. The integro-differential operator is
defined as
where I(x,y) is the eye image, r is the radius to search for, Gσ(r) is a Gaussian smoothing
function, and s is the contour of the circle given by r, x0, y0. The operator searches for the
circular path where there is maximum change in pixel values, by varying the radius and
centre x and y position of the circular contour. The operator is applied iteratively with the
amount of smoothing progressively reduced in order to attain precise localisation. Eyelids are
localised in a similar manner, with the path of contour integration changed from circular to an
arc.
Implementation of Image Acquisition
It was decided to use circular Hough transform for detecting the iris and pupil boundaries.
This involves first employing Canny edge detection to generate an edge map.
Eyelids were isolated by first fitting a line to the upper and lower eyelid using the linear
Hough transform. A second horizontal line is then drawn, which intersects with the first line
at the iris edge that is closest to the pupil. This process is illustrated in Figure shown below
and is done for both the top and bottom eyelids. The second horizontal line allows maximum
isolation of eyelid regions. Canny edge detection is used to create an edge map, and only
horizontal gradient information is taken.
Dept. Of Electronics and Communication Engineering, VKIT Page 9
IRIS RECOGNITION SEMINAR REPORT 2011
Figure - Stages of segmentation with original eye image Top right) two circles overlaid for
iris and pupil boundaries, and two lines for top and bottom eyelid Bottom left) horizontal
lines are drawn for each eyelid from the lowest/highest point of the fitted line Bottom right)
probable eyelid and specular reflection areas isolated (black areas)
2.3.2:Image Normalization
Once the iris region is successfully segmented from an eye image, the next stage is to
transform the iris region so that it has fixed dimensions in order to allow comparisons. The
dimensional inconsistencies between eye images are mainly due to the stretching of the iris
caused by pupil dilation from varying levels of illumination. Other sources of inconsistency
include, varying imaging distance, rotation of the camera, head tilt, and rotation of the eye
within the eye socket. The normalisation process will produce iris regions, which have the
same constant dimensions, so that two photographs of the same iris under different conditions
will have characteristic features at the same spatial location.
This is done by following Techniques
Dept. Of Electronics and Communication Engineering, VKIT Page 10
IRIS RECOGNITION SEMINAR REPORT 2011
Daugman’s Rubber Sheet Model
The homogenous rubber sheet model devised by Daugman [1] remaps each point within the
iris region to a pair of polar coordinates (r,θ) where r is on the interval [0,1] and θ is angle
[0,2π]
Fig: Daugman’s Rubber Sheet Model
The remapping of the iris region from (x,y) Cartesian coordinates to the normalised non-
concentric polar representation is modeled as
.
where I(x,y) is the iris region image, (x,y) are the original Cartesian coordinates, (r,θ) are the
corresponding normalised polar coordinates, and Xp,Yp and Xl,Yl are the coordinates of the
pupil and iris boundaries along the θ direction. The rubber sheet model takes into account
pupil dilation and size inconsistencies in order to produce a normalised representation with
constant dimensions. In this way the iris region is modelled as a flexible rubber sheet
anchored at the iris boundary with the pupil centre as the reference point.
Dept. Of Electronics and Communication Engineering, VKIT Page 11
IRIS RECOGNITION SEMINAR REPORT 2011
Fig : Illustration of the normalisation process for two images of the same iris taken under
varying conditions
Normalisation of two eye images of the same iris is shown in Figure . The pupil is smaller in
the bottom image, however the normalisation process is able to rescale the iris region so that
it has constant dimension. In this example, the rectangular representation is constructed from
10,000 data points in each iris region. Note that rotational inconsistencies have not been
accounted for by the normalisation process, and the two normalised patterns are slightly
misaligned in the horizontal (angular) direction. Rotational inconsistencies will be accounted
for in the matching stage.
2.3.3Feature Encoding and Matching
In order to provide accurate recognition of individuals, the most discriminating information
present in an iris pattern must be extracted. Only the significant features of the iris must be
encoded so that comparisons between templates can be made. Most iris recognition systems
make use of a band pass decomposition of the iris image to create a biometric template. The
Dept. Of Electronics and Communication Engineering, VKIT Page 12
IRIS RECOGNITION SEMINAR REPORT 2011
template that is generated in the feature encoding process will also need a corresponding
matching metric, which gives a measure of similarity between two iris templates. This metric
should give one range of values when comparing templates generated from the same eye,
known as intra-class comparisons, and another range of values when comparing templates
created from different irises, known as inter-class comparisons. These two cases should give
distinct and separate values, so that a decision can be made with high confidence as to
whether two templates are from the same iris, or from two different irises.
avelet Encoding Wavelets can be used to decompose the data in the iris region into
components that appear at different resolutions. Wavelets have the advantage over traditional
Fourier transform in that the frequency data is localised, allowing features which occur at the
same position and resolution to be matched up. A number of wavelet filters, also called a
bank of wavelets, is applied to the 2D iris region, one for each resolution with each wavelet a
scaled version of some basis function. The output of applying the wavelets is then encoded in
order to provide a compact and discriminating representation of the iris pattern.
Gabor Filters Gabor filters are able to provide optimum conjoint representation of a signal in
space and spatial frequency. A Gabor filter is constructed by modulating a sine/cosine wave
with a Gaussian. This is able to provide the optimum conjoint localisation in both space and
frequency, since a sine wave is perfectly localised in frequency, but not localised in space.
Modulation of the sine with a Gaussian provides localisation in space, though with loss of
localisation in frequency. Decomposition of a signal is accomplished using a quadrature pair
of Gabor filters, with a real part specified by a cosine modulated by a Gaussian, and an
imaginary part specified by a sine modulated by a Gaussian. The real and imaginary filters
are also known as the even symmetric and odd symmetric components respectively. The
centre frequency of the filter is specified by the frequency of the sine/cosine wave, and the
bandwidth of the filter is specified by the width of the Gaussian. Daugman makes uses of a
2D version of Gabor filters [1] in order to encode iris pattern data. A 2D Gabor filter over the
an image domain (x,y) is represented as
Dept. Of Electronics and Communication Engineering, VKIT Page 13
IRIS RECOGNITION SEMINAR REPORT 2011
where (xo,yo) specify position in the image, (α,β) specify the effective width and length, and
(uo, vo) specify modulation, which has spatial frequency .The odd symmetric and even
symmetric 2D Gabor filters are shown in Figure shown below
Fig : quadrature pair of 2D Gabor filters left) real component or even symmetric filter
characterised by a cosine modulated by a Gaussian right) imaginary component or odd
symmetric filter characterised by a sine modulated by a Gaussian.
Matching:
For matching, the Hamming distance was chosen as a metric for recognition, since bit-wise
comparisons were necessary. The Hamming distance algorithm employed also incorporates
noise masking, so that only significant bits are used in calculating the Hamming distance
between two iris templates. Now when taking the Hamming distance, only those bits in the
iris pattern that correspond to ‘0’ bits in noise masks of both iris patterns will be used in the
calculation. The Hamming distance will be calculated using only the bits generated from the
true iris region, and this modified Hamming distance formula is given as
Dept. Of Electronics and Communication Engineering, VKIT Page 14
IRIS RECOGNITION SEMINAR REPORT 2011
where Xj and Yj are the two bit-wise templates to compare, Xnj and Ynj are the
corresponding noise masks for Xj and Yj, and N is the number of bits represented by each
template. Although, in theory, two iris templates generated from the same iris will have a
Hamming distance of 0.0, in practice this will not occur. Normalisation is not perfect, and
also there will be some noise that goes undetected, so some variation will be present when
comparing two intra-class iris templates. In order to account for rotational inconsistencies,
when the Hamming distance of two templates is calculated, one template is shifted left and
right bit-wise and a number of Hamming distance values are calculated from successive
shifts. This bit-wise shifting in the horizontal direction corresponds to rotation of the original
iris region by an angle given by the angular resolution used. If an angular resolution of 180 is
used, each shift will correspond to a rotation of 2 degrees in the iris region. This method is
suggested by Daugman , and corrects for misalignments in the normalised iris pattern caused
by rotational differences during imaging. From the calculated Hamming distance values, only
the lowest is taken, since this corresponds to the best match between two templates. The
number of bits moved during each shift is given by two times the number of filters used,
since each filter will generate two bits of information from one pixel of the normalised
region. The actual number of shifts required to normalise rotational
inconsistencies will be determined by the maximum angle difference between two images of
the same eye, and one shift is defined as one shift to the left, followed by one shift to the
right. The shifting process for one shift is illustrated in Figure below.
Dept. Of Electronics and Communication Engineering, VKIT Page 15
IRIS RECOGNITION SEMINAR REPORT 2011
Fig: An illustration of the shifting process. One shift is defined as one shift left, and one shift
right of a reference template. In this example one filter is used to encode the templates, so
only two bits are moved during a shift. The lowest Hamming distance, in this case zero, is
then used since this corresponds to the best match between the two templates.
2.2.4Accuracy
The Iris Code constructed from these Complex measurements provides such a tremendous
wealth of data that iris recognition offers level of accuracy orders of magnitude higher than
biometrics. Some statistical representations of the accuracy follow:
Dept. Of Electronics and Communication Engineering, VKIT Page 16
IRIS RECOGNITION SEMINAR REPORT 2011
The odds of two different irises returning a 75% match (i.e. having Hamming
Distance of 0.25): 1 in 10 16.
Equal Error Rate (the point at which the likelihood of a false accept and false reject
are the same): 1 in 12 million.
The odds of two different irises returning identical Iris Codes: 1 in 1052
Other numerical derivations demonstrate the unique robustness of these algorithms. A
person’s right and left eyes have a statistically insignificant increase in similarity: 0.0048 on a
0.5 mean. This serves to demonstrate the hypothesis that iris shape and characteristic are
phenotype - not entirely; determined by genetic structure. The algorithm can also account for
the iris: even if 2/3 of the iris were completely obscured, accurate measure of the remaining
third would result in an equal error rate of 1 in 100000.
Iris recognition can also accounts for those ongoing changes to the eye and iris which
are defining aspects of living tissue. The pupil’s expansion and contraction, a constant
process separate from its response to light, skews and stretches the iris. The algorithms
account for such alteration after having located at the boundaries of the iris. Dr. Daugman
draws the analogy to a ‘homogenous rubber sheet” which, despite its distortion retains certain
consistent qualities. Regardless of the size of the iris at any given time, the algorithm draws
on the same amount or data, and its resultant Iris Code is stored as a 512 byte template. A
question asked of all biometrics is there is then ability to determine fraudulent samples. Iris
recognition can account for this in several ways the detection of pupillary changes, reflections
from the cornea detection of contact lenses atop the cornea and use of infrared illumination to
determine the state of the sample eye tissue.
Dept. Of Electronics and Communication Engineering, VKIT Page 17
IRIS RECOGNITION SEMINAR REPORT 2011
2.2.5 Decision Envirnoment
FIGURE 7. DECISION ENVIRONMENT
The performance of any biometric identification scheme is characterized by its
“Decision Environment’. This is a graph superimposing the two fundamental histograms of
similarity that the test generates: one when comparing biometric measurements from the
SAME person (different times, environments, or conditions), and the other when comparing
measurements from DIFFERENT persons. When the biometric template of a presenting
person is compared to a previously enrolled database of templates to determine the Persons
identity, a criterion threshold (which may be adaptive) is applied to each similarly score.
Because this determines whether any two templates are deemed to be “same” or “different”,
the two fundamental distributions should ideally be well separated as any overlap between
them causes decision errors.
One metric for “decidability”, or decision—making power, is d. This is defined as the
separation between the means of two distributions, divided by the square root of their average
variance. One advantage of using d’ for comparing, the decision-making power of biometrics
is the fact that it does not depend on any choice about the decision threshold used. Which of
course may vary from liberal to conservative when selecting the trade-off between the False
Dept. Of Electronics and Communication Engineering, VKIT Page 18
IRIS RECOGNITION SEMINAR REPORT 2011
Accept Rate (FAR) and False Reject Rate (FRR)? The d’ metric is a measure of the inherent
degree to which any decrease in one error rate must be paid for by an increase in the other
error rate, when decision thresholds are varied. It reflects the intrinsic separability of the two
distributions.
Decidability metrics such as d’ can he applied regardless of what measure of
similarity a biometric uses. In the particular case of iris recognition, the similarly measure is a
Hamming distance: the fraction of bits in two iris Codes that disagree. The distribution on the
left in the graph shows the result when different images of the same eye are compared:
typically about 10% of the bits may differ. But when Iris Codes from different eyes are
compared: With rations to look for and retain the best match. The distribution on the right is
the result. The fraction of disagreeing bits is very tightly packed around 45%. Because of the
narrowness of this right-hand distribution, which belongs to the family of binomial extreme-
value distributions, it is possible to make identification decisions with astronomical levels of
confidence. For example, the odds of two different irises agreeing just by chance in more
than 75 of their Iris Code bits, is only one in 10-to-the- 14 th power. These extremely low
probabilities of getting a False Match enable the iris recognition algorithms to search through
extremely large databases, even of a national or planetary scale, without confusing one Iris
Code for another despite so many error opportunities.
Dept. Of Electronics and Communication Engineering, VKIT Page 19
IRIS RECOGNITION SEMINAR REPORT 2011
Chapter 3:Uniqness of Iris Codes
The first test was to confirm the uniqueness of iris patterns. Testing the uniqueness of
iris patterns is important, since recognition relies on iris patterns from different eyes being
entirely independent, with failure of a test of statistical independence resulting in a match.
Uniqueness was determined by comparing templates generated from different eyes to each
other, and examining the distribution of Hamming distance values produced. This distribution
is known as the inter-class distribution. According to statistical theory, the mean Hamming
distance for comparisons between inter-class iris templates will be 0.5. This is because, if
truly independent, the bits in each template can be thought of as being randomly set, so there
is a 50% chance of being set to 0 and a 50% chance of being set to 1. Therefore, half of the
bits will agree between two templates, and half will disagree, resulting in a Hamming
distance of 0.5. The templates are shifted left and right to account for rotational
inconsistencies in the eye image, and the lowest Hamming distance is taken as the actual
Hamming distance. Due to this, the mean Hamming distance for inter-class template
comparisons will be slightly lower than 0.5, since the lowest Hamming distance out of
several comparisons between shifted templates is taken. As the number of shifts increases,
the mean Hamming distance for inter-class comparisons will decrease accordingly.
Uniqueness was also be determined by measuring the number of degrees of freedom
represented by the templates. This gives a measure of the complexity of iris patterns, and can
be calculated by approximating the collection of inter-class Hamming distance values as a
binomial distribution. The number of degrees of freedom, DOF, can be calculated by:
where p is the mean, and σ is the standard deviation of the distribution.
Dept. Of Electronics and Communication Engineering, VKIT Page 20
IRIS RECOGNITION SEMINAR REPORT 2011
Chapter4:Binomial Distribution of Hamming codes
The Histogram given below shows the outcomes of 2,307,025 comparisons between
different pairs of irises. For each pair comparison, the percentage of their Iris Code bits that
disagreed was computed and tallied as a fraction. Because of the zero-mean property of the
wavelet demodulators, the computed coding bits are equally likely to be 1 or 0. Thus when
any corresponding bits of two different Iris Codes are compared, each of the four
combinations (00), (01), (10), (11) has equal probability. In two of these cases the bits agree,
and in the other two they disagree. Therefore one would expect on average 50% of the bits
between two different Iris Codes to agree by chance. The above histogram presenting
comparisons between 2.3 million different pairings of irises shows a mean fraction of 0.499
of their Iris Code bits agreeing by chance.
FIGURE 9. BINOMIAL DISTRIBUTION OF IRISCODE HAMMING DISTANCES
The standard deviation of this distribution, 0.032, reveals the effective number of
independent bits (binary degrees of freedom) when Iris Codes are compared. Because of
correlations within irises and within computed Iris Codes, the number of degrees of freedom
is considerably smaller than the number of bits computed. But even correlated Bernoulli trials
(coin tosses) generate binomial distributions; the effect of their correlations is equivalent to
reducing the effective number of Bernoulli trials. For comparisons between different pairs of
Iris Codes, the distribution shown above corresponds to that for the fraction of "heads" that
one would get in runs of 244 tosses of a fair coin. This is a binomial distribution, with
Dept. Of Electronics and Communication Engineering, VKIT Page 21
IRIS RECOGNITION SEMINAR REPORT 2011
parameters p=q=0.5 and N=244 Bernoulli trials (coin tosses). The solid curve in the above
histogram is a plot of such a binomial probability distribution. It gives an extremely exact fit
to the observed distribution, as may be seen by comparing the solid curve to the data
histogram.
The above two aspects show that Hamming Distance comparisons between different
Iris Codes are binomially distributed, with 244 degrees of freedom. The important corollary
of this conclusion is that the tails of such distributions are dominated by factorial
combinatorial factors, which attenuate at astronomic rates. This property makes it extremely
improbable that two different Iris Codes might happen to agree just by chance in, say, more
than 2/3rds of their bits (making a Hamming Distance below 0.33 in the above plot). The
confidence levels against such an occurrence are the reason why iris recognition can afford to
search extremely large databases, even on a national scale, with negligible probability of
making even a single false match.
Dept. Of Electronics and Communication Engineering, VKIT Page 22
IRIS RECOGNITION SEMINAR REPORT 2011
Chapter6: Commensurability Of Iris codes ,
Advantages, Disadvantages
A critical feature of this coding approach is the achievement of commensurability
among iris codes, by mapping all irises into a representation having universal format and
constant length, regardless of the apparent amount of iris detail. In the absence of
commensurability among the codes, one would be faced with the inevitable problem of
comparing long codes with short codes, showing partial agreement and partial disagreement
in their lists of features. It is not obvious mathematically how one would make objective
decisions and compute confidence levels on a rigorous basis in such a situation. This
difficulty has hampered efforts to automate reliably the recognition of fingerprints.
Commensurability facilitates and objectifies the code comparison process, as well as the
computation of confidence.
5.1Adavntages
Highly protected, internal organ of the eye
Externally visible; patterns imaged from a distance
Iris patterns possess a high degree of randomness
o Variability: 244 degrees-of-freedom
o Entropy: 3.2 bits per square-millimeter
o Uniqueness: set by combinatorial complexity
Changing pupil size confirms natural physiology
Pre-natal morphogenesis (7th month of gestation)
Limited genetic penetrance of iris patterns
Patterns apparently stable throughout life
Encoding and decision-making are tractable
Image analysis and encoding time: 1 second
Decidability index (d-prime): d' = 7.3 to 11.4
Search speed: 100,000 Iris Codes per second
Dept. Of Electronics and Communication Engineering, VKIT Page 23
IRIS RECOGNITION SEMINAR REPORT 2011
5.Disadvantages of Iris Scanning
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
Iris scanning is a relatively new technology and is incompatible with the very
substantial investment that the law enforcement and immigration authorities of
some countries have already made into fingerprint recognition.
Iris recognition is very difficult to perform at a distance larger than a few meters
and if the person to be identified is not cooperating by holding the head still and
looking into the camera.
As with other photographic biometric technologies, iris recognition is susceptible
to poor image quality, with associated failure to enroll rates
As with other identification infrastructure (national residents databases, ID cards,
etc.), civil rights activists have voiced concerns that iris-recognition technology
might help governments to track individuals beyond their will.
Dept. Of Electronics and Communication Engineering, VKIT Page 24
IRIS RECOGNITION SEMINAR REPORT 2011
Chapter6: Applications
Iris-based identification and verification technology has gained acceptance in a
number of different areas. Application of iris recognition technology can he limited only by
imagination. The important applications are those following:
ATM’s and iris recognition: in U.S many banks incorporated iris recognition
technology into ATM’s for the purpose of controlling access to one’s bank
accounts. After enrolling once (a “30 second” process), the customer need only
approach the ATM, follow the instruction to look at the camera, and be recognized
within 2-4 seconds. The benefits of such a system are that the customer who
chooses to use bank’s ATM with iris recognition will have a quicker, more secure
transaction.
Applications of this type are well suited to iris recognition technology. First, being
fairly large, iris recognition physical security devices are easily integrated into the mountable,
sturdy apparatuses needed or access control, The technology’s phenomenal accuracy can be
relied upon to prevent unauthorized release or transfer and to identify repeat offenders re-
entering prison under a different identity.
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.
Dept. Of Electronics and Communication Engineering, VKIT Page 25
IRIS RECOGNITION SEMINAR REPORT 2011
Entitlements and benefits authentication.
Forensics, birth certificates, tracking missing or wanted person
Credit-card authentication.
Automobile ignition and unlocking; anti-theft devices.
Anti-terrorism (e.g.:— suspect Screening at airports)
Secure financial transaction (e-commerce, banking).
Internet security, control of access to privileged information.
“Biometric—key Cryptography “for encrypting/decrypting messages.
Chapter7: Iris Recognition Issues
Every biometric technology has its own challenges. When reviewing test results, it is
essential to consider the environment and protocols of the test. Much industry testing is
performed in laboratory settings on images acquired in ideal conditions. Performance in a real
world application may result in very different performance as there is a learning curve for
would-be user of the system and not every candidate will enroll properly or quickly the first
time. There are some issues which affect the functionality and applicability of iris recognition
technology in particular.
The technology requires a certain amount of user interaction the enroller must hold
still in a certain spot, even if only momentarily. It would be very difficult to enroll or identify
a non-cooperative subject. The eye has to have a certain degree of lighting to allow the
camera to capture the iris; any unusual lighting situation may affect the ability of the camera
to acquire its subject. Lastly, as with any biometric, a backup plan must be in place if the unit
becomes inoperable. Network crashes, power failure, hardware and software problems are but
a few of the possible ways in which a biometric system would become unusable. Since iris
technology is designed to be an identification technology, the fallback procedures may not be
as fully developed as in a recognition schematic. Though these issues do not reduce the
exceptional effectiveness of iris recognition technology, they must be kept in mind, should a
company decide to implement on iris-based solution.
Dept. Of Electronics and Communication Engineering, VKIT Page 26
IRIS RECOGNITION SEMINAR REPORT 2011
CONCLUSION
The technical performance capability of the iris recognition process far surpasses that
of any biometric technology now available. Iridian process is defined for rapid exhaustive
search for very large databases: distinctive capability required for authentication today. The
extremely low probabilities of getting a false match enable the iris recognition algorithms to
search through extremely large databases, even of a national or planetary scale. As iris
technology grows less expensive, it could very likely unseat a large portion of the biometric
industry, e-commerce included; its technological superiority has already allowed it to make
significant inroads into identification and security venues which had been dominated by other
biometrics. Iris-based biometric technology has always been an exceptionally accurate one,
and it may soon grow much more prominent.
Dept. Of Electronics and Communication Engineering, VKIT Page 27
IRIS RECOGNITION SEMINAR REPORT 2011
REFERENCES
1. Daugman J (1999) "Wavelet demodulation codes, statistical independence, and
pattern recognition." Institute of Mathematics and its Applications, Proc.2nd 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 Downing 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." IEEE Transactions on Pattern Analysis and Machine
Intelligence, vol. 15, no. 11, pp 1148 - 1160.
5. Daugman J (1985) "Uncertainty relation for resolution in space, spatial frequency, and
orientation optimized by two-dimensional visual cortical filters." Journal of the
Optical Society of America A, vol. 2, no. 7, pp 1160 - 1169.
6. . Sanderson, J. Erbetta. Authentication for secure environments based on iris scanning
technology. IEE Colloquium on Visual Biometrics, 2000.
7. J. Daugman. How iris recognition works. Proceedings of 2002 International
Conference on Image Processing, Vol. 1, 2002
8. R. Wildes, J. Asmuth, G. Green, S. Hsu, R. Kolczynski, J. Matey, S. McBride. A
system for automated iris recognition. Proceedings IEEE Workshop on Applications
of Computer Vision, Sarasota, FL, pp. 121-128, 1994.
9. Y. Zhu, T. Tan, Y. Wang. Biometric personal identification based on iris patterns.
Proceedings of the 15th International Conference on Pattern Recognition, Spain, Vol.
2, 2000.
SOURCE LINKS
www. irisscan.com
www.c1.cam.ac.Uk/users/jgd1000
www.sensar.com
Dept. Of Electronics and Communication Engineering, VKIT Page 28