signalspot.com

Humans have traditionally identified each other by their appearance, by the sound and content of their speech, and by context. If the other person is neither visible nor audible, e.g. when receiving their email, we either simply accept their asserted identity, allow it to establish itself by shared knowledge and context, or rely on special secret knowledge such as encryption keys. With the arrival of automation, identification of persons has continued to rely largely on special possessions (magnetic or optical stripe cards) and on secrets (computer login password, or cash point PIN number).The fundamental problem with traditional methods of identification — whether between human strangers, or identification of persons by machines — took on new urgency on 11 September, 2001. Some of the terrorist hijackers who crashed the aero planes into buildings were on FBI "watch lists," but they were using false passports. With no reliable mechanism to confirm any connection between a passport (or other identity device) and its holder, 11 September was a catastrophe waiting to happen.

To solve some of the problems faced by security systems and identification process a technology called "biometrics" (from biological measurement) introduced some new type of security and identification systems based on some of human parts which differ from one person to other. These could be anatomical, physiological, or even behavioral. The sounds of a person’s voice, or they way in which they sign their name, are examples of behavioral biometrics. Their blood type or markers in their tissue or fluid samples (including DNA itself) are examples of physiological biometrics, although these would be used more typically in forensic applications rather than in real-time, live applications. Most currently used biometrics are anatomical: facial appearance, hand geometry, fingerprints, retinal vein patterns, and iris patterns. But the most efficient method is the iris recognition method.

WHAT IS IRIS?

The iris is an internal organ of the eye — perhaps the only internal organ of the body that is routinely visible from outside — and its patterns are resolvable with good video cameras from distances of up to about a meter. The iris is located behind the cornea of the eye, and behind the aqueous humour, but in front of the lens. Its only physiological purpose is of course to control the amount of light that enters the eye through the pupil, by the action of its dilator and sphynctor muscles that control pupil size, but its construction from elastic connective tissue gives it a complex, fibrillous pattern.

WHY IRIS ONLY?

Though we have other biometric traits we go for iris technology because of its uniqueness. This is because iris patterns have a high degree of randomness in their structure. This is what makes them unique. Every biometric depends upon random variation amongst different persons in the chosen measurements, in order to guarantee that a particular pattern is unique to just one person and thus can serve as a reliable automatic identifier of them. The greater the degree of randomness, the greater the likelihood of uniqueness. This can be measured mathematically by the number of "degrees-of-freedom" in the template. This is essentially a count of the number of independent forms of variation, or the dimensions of variability, that are spanned by the biometric across different persons.

For the case of iris patterns, there are about 250 degrees-of-freedom; for fingerprints it is about 35, and for faces it is about 20. A good analogy (both for the connective tissue of the iris and also for this mathematical measure!) is throwing down a plate of sticky noodles. The sticky noodles will fall into a random pattern, whose complexity (and therefore whose uniqueness) depends on how many noodles there were in the plateful. An iris pattern is a bit like a plate of 250 sticky noodles, and so the combinatorics of possible patterns that the pectinate ligament in the trabecular meshwork of the iris can form is truly astronomical. More precisely, its combinatorics is binomial — described by binomial distributions, as are the possible outcomes from tossing a coin 250 times in a row. The likelihood of getting all "heads" is 0.5 raised to the 250th power, which is roughly 10 raised to the minus 75th power.

From the table below we can see different biometric traits and their security levels.

Method	Coded Pattern	Misidentification rate	Security	Applications
Iris Recognition	Iris pattern	1/1,200,000	High	High-security facilities
Fingerprinting	Fingerprints	1/1,000	Medium	Universal
Hand Shape	Size, length and thickness of hands	1/700	Low	Low-security facilities
Facial Recognition	Outline, shape and distribution of eyes and nose	1/100	Low	Low-security facilities
Signature	Shape of letters, writing order, pen pressure	1/100	Low	Low-security facilities
Voice printing	Voice characteristics	1/30	Low	Telephone service

Iris Scan Technology

With new technologies the eyes are more than “windows to your soul.” People are carrying with them a living key or password that will never be forgotten and will always be there. The technology is available now through work in computer vision, pattern recognition, and man-machine interface to create a reliable lock that a person’s iris pattern will open. The randomness of iris patterns has a very high dimensionality making recognition decisions reliable with a high level of confidence.

The purpose of iris recognition products is to provide real-time, high-confidence recognition of a person’s identity through mathematical analysis of random patterns in the iris. Irises (pigmented, round, contractile membranes in the eyes) are unique in each individual. The iris is a protected internal organ whose random texture is stable and unchanging, from about one year of age until death. It is the most individually distinctive feature of the human body. No two irises are alike, not even among twins. In fact, left and right irises of one individual are not identical. The statistical probability that two irises would ever be exactly the same is estimated at 1 in 1072. Iris recognition is statistically more accurate than DNA testing.

All iris recognition systems are based on the algorithms. This development allows one to read and map the rich data in a person’s iris. This data includes rifts, pits, freckles, striations, contraction furrows, crypts, coronas, serpentine vasculature, and collagenous fibersand remains stable throughout a person’s lifetime.

WORKING:

Iris recognition begins with a video picture of the eye and iris within it. A monochrome CCD is the type of camera used. The boundaries of the pupil and limbus (the outer edge of the iris) are defined, eyelid occlusion and reflections are discounted, and the image is readied for processing. Recording 240 degrees of freedom (DOF) or independent characteristics of an iris distinguish one iris from another. This information is encoded into a 512 byte-digitized record from that glance at the camera. Typically both eyes are enrolled. The digital record can be stored in hexadecimal code in a data base like any other information. This recorded iris pattern can then be used for recognition when a live iris is presented for comparison. Eyeglasses and contact lenses, even colored contacts, do not obscure the iris so the system is able to perform through them. Enrollment in the system is usually accomplished in three minutes or less. Depending on the lens design and ambient illumination the subjects stand between 8 to 30 inches from the Optical Unit. A powerful search engine does an exhaustive search to compare the iris presented to ones encoded in the data base. A recognition decision is made in real-time, seconds, not days, hours, or minutes required by other biometrics operations. Without use of a person making a final judgment a positive recognition decision can be made with “imposter odds” of 1 in 1048. Stated another way, the probability that a recognition is wrong is an extraordinarily low in this technology. Anyplace that currently relies on keys, cards, badges, documents, passwords, or PIN numbers is a possible candidate for iris recognition use. Some of these are financial transactions, e-commerce, entitlement payments, passport control, police, and forensic applications. With escalating treats of identity theft the need for accurate recognition decisions increases. Other biometrics recognition systems include fingerprinting, palm prints, hand geometry, nailbed identification, facial recognition, and retinal scan. Behavioral characteristics used for identification are signature dynamics, keyboard dynamics, and voice recognition. Iris and retina scans are the most accurate of all biometric techniques and, currently, the most costly. The entire biometrics market is projected to reach $2.6 billion by 2004.

Generating an Iris Code

Now that we have Gabor wavelets, let’s do something interesting with them. Lets start with an image of an eye and then unroll it (map it to Cartesian coordinates) so we have something like the following:

What we want to do is somehow extract a set of unique features from this iris and then store them. That way if we are presented with an unknown iris, we can compare the stored features to the features in the unknown iris to see if they are the same. We’ll call this set of features an "Iris Code."

Any given iris has a unique texture that is generated through a random process before birth. Filters based on Gabor wavelets turn out to be very good at detecting patterns in images. We’ll use a fixed frequency 1D Gabor filter to look for patterns in our unrolled image. First, we’ll take a one pixel wide column from our unrolled image and convolve it with a 1D Gabor wavelet. Because the Gabor filter is complex, the result will have a real and imaginary part which is treated separately. We only want to store a small number of bits for each iris code, so the real and imaginary parts are each quantized. If a given value in the result vector is greater than zero, a one is stored; otherwise zero is stored. Once all the columns of the image have been filtered and quantized, we can form a new black and white image by putting all of the columns side by side. The real and imaginary parts of this image (a matrix), the iris code, are shown here:

Now that we have an iris code, we can store it in a database, file or even on a card. What happens though if we want to compare two iris codes and decide how similar they are?

Comparing Iris Codes

The problem of comparing iris codes arises when we want to authenticate a new user. The user’s eye is photographed and the iris code produced from the image. It would be nice to be able to compare the new code to a database stored codes to see if this user is allowed or to see who they are. To perform this task, we’ll attempt to measure the Hamming distance between two iris codes. The Hamming distance between any two equal length binary vectors is simply the number of bit positions in which they differ divided by the length of the vectors. This way, two identical vectors have distance 0 while two completely different vectors have distance 1. Its worth noting that on average two random vectors will differ in half their bits giving a Hamming distance of 0.5. The Hamming distance is mathematically defined in this equation: D=

A?

length(A)

In theory, two iris codes independently generated from the same iris will be exactly the same. In reality though, this doesn’t happen vary often for reasons such as imperfect cameras, lighting or small rotational errors. To account for these slight inconsistencies, two iris codes are compared and if the distance between them is below a certain threshold we’ll call them a match. This is based on the idea of statistical independence. The iris is random enough such that iris codes from different eyes will be statistically independent (i.e.: have a distance larger than the threshold) and therefore only iris codes of the same eye will fail the test of statistical independence. Empirical studies with millions of images have supported this assertion. In fact, when these studies used the threshold used in our method (.3) false positive rates fell below 1 in 10 million.

Iris Recognition Results

Our implementation of the iris recognition algorithm is broken up into several components, each of which has its strengths and weaknesses. The pupil recognition algorithm appears to be 98% effective in detecting the pupil center when tested against a database of 50 images. This is due to the extremely uniform black color of the pupil and strong contrast to the iris and virtual all other features in the image. Although the assumptions that the algorithm is founded break down in extreme cases, such as when there are other large black spots in the image, these cases can be detected by other means and discarded. The iris detection algorithm proved to be rather hit-or-miss. In it’s current form, it has a 50% success rate in detecting the iris correctly within an image of the eye. This large error lies mostly in the ’guessing’ scheme used to make an initial prediction about the radius of the iris. This guessing scheme can be expanded to make higher precision, higher accuracy guesses at the expensive of algorithm execution speed. Also, the iris-sclera transition boundary of the eye can be more intensively processed by a multi-scale edge detection kernel (the implementation in this project uses a single-scale Haar wavelet kernel).

Each isolated iris pattern is then demodulated to extract its phase information using quadrature 2-D Gaborwavelets. This encoding process is illustrated in Fig above. 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 2-D Gabor wavelets:

where h _{{Re, Im}} can be regarded as a complex-valued bit whose real and imaginary parts are either 1 or 0 (sgn) depending on the sign of the 2-D integral; I (?, ?) is the raw iris image in a dimensionless polar coordinate system that is size- and translation- invariant and which corrects for pupil dilation ? and ? are the multiscale 2-D wavelet size parameters, spanning an eight-fold range from 0.15 to 1.2 mm on the iris; ? is wavelet frequency, spanning three octaves in inverse proportion to ? ; and (r₀,?₀ represent the polar coordinates of each region of iris for which the phasor coordinates h_{Re,Im}are computed. Such a phase quadrant coding sequence is illustrated for one iris by the bit stream shown graphically in Fig above .A desirable feature of the phase code portrayed in Fig is that it is a cyclic, or gray code: in rotating between any adjacent phase quadrants, only a single bit changes, unlike a binary code in which two bits may change, making some errors arbitrarily more costly than others. Altogether, 2048 such phase bits (256 bytes) are computed for each iris, but in a major improvement over the author’s earlier algorithms, now an equal number of masking bits are also 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 (SNR) 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 phase bit settings which code the sequence of projection quadrants as shown in Fig capture the information of wavelet zero-crossings, as is clear from the sign operator in (2). The extraction of phase has the further advantage that phase angles remain defined regardless of how poor the image contrast may be, as illustrated by the extremely out-of-focus image in Fig. 3. Its phase bit stream has statistical properties such as run lengths similar to those of the code for the properly focused eye image in Fig. The benefit which arises from the fact that phase bits are set also for a poorly focused image as shown here, even if based only on random CCD thermal noise, is that different poorly focused irises 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 can be confused with each other by appearance-based face recognition algorithms.

Motivation: There is a strong scientific demand for the proliferation of systems, concepts and algorithms for iris recognition and identification. This is mostly because of the comparatively short time that iris recognition systems have been around. In comparison to face, fingerprint and other biometric traits there is still a great need for substantial mathematical and computer-vision research and insight into iris recognition. One evidence for this is the total lack of publicly available adequate datasets of iris images.

Following the tradition of the face recognition and the face detection this is intended to be an information pool for the iris recognition community. Its goal is to provide an entry point for the starter as well as a centralized information resource to concentrate iris recognition and related scientific efforts.

An iris-based biometric, on the other hand, involves analyzing features found in the colored ring of tissue that surrounds the pupil. Iris scanning, undoubtedly the less intrusive of the eye-related biometrics, uses a fairly conventional camera element and requires no close contact between the user and the reader. In addition, it has the potential for higher than average template-matching performance. Iris biometrics work with glasses in place and is one of the few devices that can work well in identification mode. Ease of use and system integration has not traditionally been strong points with iris scanning devices, but you can expect improvements in these areas as new.

Algorithm for unwrapping the iris region.

The newly introduced IRISPASS-WG system is a succeeding version of the IRISPASS-S. It maintains the accurate iris recognition function of the previous model, while enhancing the user-operability with newly developed software that automatically detects the position of the human eyes. An individual’s iris patterns can be registered or identified by simply standing in front of the identification device. The required time for authentication is about three seconds. The system enables accurate, high-speed authentication of the iris even while wearing glasses.

The system consists of a system management device and registration device, both of which are located at the customer’s control center, and identification devices, which are installed at entrances. The system allows connection to as many as 127 identification devices per system. The system management device has various functions, including iris information registration, management of individual information and authentication history, status monitoring of identification devices, and remote gate-management. The security of the entire system is also enhanced by the addition of functions to allow the iris authentication of the system administrators, who access the system management device and prevent unauthorized operations on a PC connected to the device. The identification device incorporates functions enabling identified data to work with monitoring cameras and guard systems, which allows customers to establish comprehensive security systems.

Major characteristics of iris recognition:

1. The iris, being a human organ, renders forgery difficult.
2. It uses cameras to capture images of the iris, and the system does not require physical contact with the equipment, thereby freeing users from possible hygienic concerns.
3. Since the iris pattern is more complex and random than other biometric patterns, it offers a highly precise method for individual authentication with a false-acceptance error rate of less than 1 in 1.2 million.
4. The iris pattern remains unchanged after the age of two and does not degrade over time or with the environment, therefore the initially registered data may be used throughout the individual’s entire life.

National Geographic’s Afghan Girl Positively Identified by Iris Recognition

Iridian Technologies, the leading provider of authentication software based on its exclusive, patented iris recognition technology, announced that its technology was the iris recognition technique used to positively identify the mysterious "Afghan Girl" who graced the cover of National Geographic magazine in 1985. The process of finding her and verifying her identity was by using this iris recognization technology. Iridian was asked by National Geographic to compare photographs taken in 1984 with photographs from 2002. Iridian’s commercially available iris recognition cameras and software contain advanced security measures to detect and reject photographs. Therefore, Iridian’s Research Lab scanned the photographic images into digital format and used development software to process the digital image, disabling the security measures normally used to detect photographs. Because the photographs were not taken with iris recognition cameras, the Research Lab had further to discount for light reflection and adjust for the quality of the image.

The experts at Iridian spent several days reconfiguring their software to suit the specific needs and Iridian finally succeeded in identifying her.

Despite the challenges of working with photographs, rather than live subjects, the strength of Iridian’s core algorithms allowed for a conclusive determination that Sharbat Gula was indeed the same person as the individual who was photographed in 1984.

The match of Sharbat Gula’s eyes to the eyes on the 1985 cover photo was irrefutable, as it was achieved a 1 in 100 million probability of a false match.

Compare to other system

Other biometrics recognition systems include fingerprinting, palm prints, hand geometry, nailbed identification, facial recognition, and retinal scan. Behavioral characteristics used for identification are signature dynamics, keyboard dynamics, and voice recognition. Iris and retina scans are the most accurate of all biometric techniques and, currently, the most costly.

Accuracy

In a comprehensive study conducted by Britain’s National Physical Laboratory (NPL) iris recognition technology decisively outperformed six other biometrics systems – facial recognition, fingerprint, hand geometry, and vein and voice recognition. Tested to positively identify users in an office environment iris recognition technology registered a false match rate of zero in 2,735,529 comparisons and a 0.0 percent failure-to-acquire rate. Iris recognition had a false rejection rate of 0.0188, the lowest of all systems rested. Four of the other biometrics systems registered a false rejection rate of 10-25 percent. Only retina scanning comes close to the accuracy rate of iris recognition. The few system problems that have been encountered almost exclusively reflect lighting, focus, or image degradation issues. There has to be a certain degree of lighting to allow the camera to acquire the image of the iris. Unusual lighting hinders this and causes problems.

Speed

Iris recognition systems can cycle through 1,500,000 matches per minute, which is 20 times greater processing speed than any other biometrics systems. In real-life applications this translates into an identity decision being made in seconds. The enrollment process is also speedily accomplished, typically in three minutes or less.

Safety and Perceived Invasiveness

Enrollment and use of an iris recognition system requires no contact, only cooperation of the user. That cooperation involves the enrollee being still, and looking at a certain spot. Although iris scanning is less difficult than retina scanning some subjects may still find compliance with the system annoying. The optimum distance between the user and the camera is steadily enlarging as camera resolution increases. The devices capture images of the eye from a comfortable distance without bright lights or lasers.

The Iris Code is hashed and encrypted as a security measure to prevent theft. If a person feels their recognition patterns have been compromised, re-enrollment is possible an infinite number of times by using a permuted Iris Code. Iris recognition because it looks at the exterior part of the eye, unlike retinal scans that look at vascular patterns inside the eye, is not invasive. Also, there is no possibility of gathering information such as medical conditions, a possibility with retinal scans. Both irises and retinas are stable throughout a lifetime, except in the case of degenerative diseases that may affect the retina. There is no need to remove glasses or contact lenses during identification. As long as they do not obscure the iris, recognition can be made through them. Iris recognition can be hampered by partially occluded or drooping eyelids.

Costs

Iris scanning can increase profitability by minimizing both costs and vulnerabilities associated with password and password management. Research indicates US businesses spend an average of $200 per person a year on password management. The value proposition of implementing an iris recognition system is three-dimensional. Cost, accuracy, and ease of use are all important considerations. Recent advances in camera technology is bringing down the cost of iris recognition. Camera prices have gone down while processing ability has gone up. The size of the camera has decreased also. With a strategic partnership with Panasonic, the costs have gone down significantly. Both iris scanning and retina scanning are at the upper end of the scale in cost compared to other biometric systems.

Ease of Use

Many of the users who have already encountered iris-scanning technology consider it a convenience rather than an intrusion, speeding the process of identity verification. Glasses or contact lens use does not affect it. Most eye surgeries do not change the iris. In the few, such as iridotomy and iridectomy, both associated with glaucoma, re-enrollment may be necessary. These technologies can be integrated into existing business systems easing the installation requirements. In this instance, retina scanning has an advantage over iris scanning in that retina scanning utilizes a very compact template. Retina scanning requires 96 bytes while iris scanning uses 512 bytes. A greater number of templates can be stored in a standalone device if retina scanning is employed.

No contact need be made to enroll or be recognized by the system. Subsequent to enrollment users need little or no instruction to become proficient enough to perform recognition scans without a system operator present. Because of the shorter time the eye must be still to be recognized iris scanning is easier to use than retina scanning, which requires a subject to repeatedly focus on a small point for several seconds at a time. Some candidates will need assistance or instruction to enroll. Unlike other biometrics iris recognition requires no real-time human decision making to complete the recognition process.

Legitimate users will never again forget their password, lose their key, or be locked out, as long as the system is functioning properly, but as with any system there will be times when things are not working. Network crashes, power outages, and hardware and software glitches are a few of the scenarios that might cause the system to become inoperable. The backup plan may be seriously compromised because users accustomed to iris recognition may not carry the necessary identification.

FUTURE:

The market for iris recognition is growing rapidly. Iris scanning can be engaged in numerous pilot programs worldwide for immigration and border control, controlling access to restricted areas, and simplifying passenger travel.

CONCLUSION:

As with almost every new technology that seeks to find its place in everyday life, iris recognition has both the potential to be a convenience enhancer (including an access enhancer), but also the potential to be an obstacle or excluder if improperly configured or installed without consultation and guidance from disabled persons. Because it allows hands-free, automatic, rapid and reliable identification of persons, it can facilitate access for persons unable to engage in the standard mechanical transactions of access. But it must not presume universal uniformity among persons and their bodies.

BIBLIOGRAPHY:

1.WWW.EYETICKET.COM

2.WWW.THEREGISTER.CO.UK

3.http://www.cl.cam.ac.uk/users/jgd1000

4.WWW.IRIDIANTECH.COM

5.WWW.TECH.GENSSOFT.COM