Iris recognition is a method of biometric authentication that uses pattern recognition techniques based on high-resolution images of the irides of an individual's eyes. This method uses camera technology, and subtle IR illumination to reduce specular reflection from the convex cornea to create images of the detail-rich, intricate structures of the iris. These unique structures converted into digital templates, provide mathematical representations of the iris that yield unambiguous positive identification of an individual.
Iris Recognition however is not the same as a Retina Scan. Although both essentially use characteristics of the eye as a biometric marker, they are very different systems in sense that iris recognition uses camera technology, with subtle IR illumination reducing specular reflection from the convex cornea, to create images of the detail-rich, intricate structures of the iris, a retinal scan uses the unique patterns on a person's retina to identify them.
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. The only biometric authentication technology designed for use in a one-to many search environment, a key advantage of iris recognition is its stablity, or template longevity as, barring trauma, a single enrollment can last a lifetime.
Breakthrough work to create the iris recognition algorithms required for image acquisition and one-to-many matching was pioneered by John G. Daugman, Ph.D, OBE (University of Cambridge Computer Laboratory. These were utilized to effectively debut commercialization of the technology in conjunction with an early version of the IrisAccess system designed and manufactured by Korea's LG Electronics. Daugman's algorithms are the basis of almost all currently (as of 2006) commercially deployed iris-recognition systems.
Commercial Iris Recognition System from LG
Anatomy of Iris
The iris consists of pigmented fibrovascular tissue known as a stroma. It is the most forward portion of the eye and the only one seen on superficial inspection. The stroma connects a sphincter muscle (sphincter pupillae), which contracts the pupil, and a set of dilator muscles (dilator pupillae) which open it. The back surface is covered by a heavily pigmented epithelial layer two cells thick (the iris pigment epithelium), but the front surface has no epithelium. The high pigment content is to block light from passing through the iris and restrict it to the pupil. The outer edge of the iris, known as the root, is attached to the sclera and the anterior ciliary body. The iris and ciliary body together are known as the anterior uvea. Just in front of the root of the iris is the region through which the aqueous humour constantly drains out of the eye, with the result that diseases of the iris often have important effects on intraocular pressure, and indirectly on vision. Depending on the amount of light, the iris makes the pupil larger or smaller.
The human iris begins to form in the third month of gestation and the structure is complete by the eight month, even though the color and pigmentation continue to build through the first year of birth. After that, the structure of the iris remains stable throughout a person’s life, except for direct physical damage or changes caused by eye surgery. The iris hence parallels the fingerprint in uniqueness but enjoys a further advantage that it is an internal organ and less susceptible to damages over a person’s lifetime. It is composed of several layers which gives it its unique appearance. This uniqueness is visually apparent when looking at its rich and small details seen in high resolution camera images under proper focus and illumination. The iris is the ring-shape structure that encircles the pupil, the dark centered portion of the eye, and stretches radially to the sclera, the white portion of the eye, it shares high-contrast boundaries with the pupil but less-contrast boundaries with the sclera. The iris contains many collagenous fibers, contraction furrows, coronas, crypts, color, serpentine vasculature, striations, freckles, rifts, and pits. Measuring the patterns of these features and their spatial relationships to each other provides other quantifiable parameters useful to the identification process.
Principle
The iris identification system is to automatically recognize the identity of a person from a new image by comparing it to the human iris patterns annotated with identity in a stored database. A general iris recognition system is composed of four steps. Firstly, an image containing the user’s eye is captured by the system. Then, the image is preprocessed to normalize the scale and illumination of the iris and localize the iris in the image. Thirdly, features representing the iris patterns are extracted. Finally, decision is made by the iris identification system is to automatically recognize the identity of a person from a new image by comparing it to the human iris patterns annotated with identity in a stored database.A general iris recognition system is composed of four steps. Firstly, an image containing the user’s eye is captured by the system. Then, the image is preprocessed to normalize the scale and illumination of the iris and localize the iris in the image. Thirdly, features representing the iris patterns are extracted. Finally, decision is made by means of matching. There are four key parts in the iris recognition system: iris image acquisition,preprocessing, feature extraction, and classifier design.
Iris patterns have a high degree of randomness in their structure making 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, so the combinatorics of possible patterns that the pectinate ligament in the trabecular meshwork of the iris can form is truly astronmical. More precisely, its combinatorics are 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 (10^-75).
Daugman’s algorithms encode the iris pattern into an abstract mathematical description called an "IrisCode," which is the bar-code like bit stream shown in the top-left corner. This process relies upon two-dimensional wavelets (mathematical functions that are like restricted Fourier components, i.e. sinewaves multiplied by Gaussian envelopes to give them locality). In Daugman's algorithms, all amplitude information is discarded, and the resulting 2048 bits that represent an iris consist only of the complex sign bits of the Gabor-domain representation of the iris image. Discarding the amplitude information ensures that the template remains largely unaffected by changes in illumination and virtually negligibly by iris color, which contributes significantly to the long-term stability of the biometric template. The result of the wavelet analysis is that any piece of an iris can be said to have a certain phase. The extraction of phase information across the entire iris is called demodulation. The phase coordinates of every part of the iris are quantized to just two bit accuracy -- i.e. only the identity of a quadrant of the complex plane is encoded as the representation for each small piece of structure seen in the iris. This "phase sequence" allows an iris pattern to be encoded in a total of 512 bytes worth of information. Whenever a person presents his/her eye to a camera, its IrisCode is computed within a second or less, and then this is compared with all previously enrolled IrisCodes in the relevant database to see whether any of them match. . To authenticate via identification (one-to many template matching) or verification (one-to one template matching) a template created by imaging the iris, is compared to a stored value template in a database. If the Hamming distance (In information theory, the Hamming distance between two strings of equal length is the number of positions for which the corresponding symbols are different.) is below the decision threshold, a positive identification has effectively been made An important point is that the person does not need to assert any identity; the algorithms are powerful enough (and fast enough) to discover their identity, if they have been seen before and enrolled. The speed of database search is about 100,000 IrisCodes per second. This ability to be recognized without having first to assert an identity -- e.g. by swiping a card, or by typing in a name or a PIN number -- is one potential advantage of iris identification for persons who have limited use of arms or hands. This "hands-free" use of iris recognition is possible because the probability of False Matches is so low that the algorithms can "afford" to search large databases exhaustively, rather than just answering a single yes/no question about a claimed identity. In many millions of IrisCode comparisons that have been done in tests by independent laboratories (e.g. the UK's NPL Labs), so far there has never been a single False Match reported.
Limitations
The potential limitations of iris recognition for persons with various disabilities include the following:
1. A person must of course have an eye, with an iris. According to the US National Eye Institute the condition of aniridia (lack of an iris) occurs in 18 of 1,000,000 births. Aniridia is a rare congenital condition characterized by the underdevelopment of the eye's iris. This usually occurs in both eyes. It is associated with poor development of the retina at the back of the eye preventing normal vision development.
Because it is genetically linked, the condition usually affects both eyes according to the UK's Royal National Institute for the, but its incidence covers a wide spectrum of partial conditions such as just chronically enlarged pupils. Iris recognition requires the pupil to have a diameter less than about 75% of the isis.
2. Blind persons may have difficulty in getting themselves aligned with the iris camera at arm's length, because some such systems rely on visual feedback via a mirror or LCD display to guide the user into alignment with the camera. (Other more sophisticated iris cameras are mounted on automatic pan and tilt platforms that actively home in on an eye, including autozoom and autofocus, so very little cooperation from a user, or indeed vision, is needed.)
3. Persons with pronounced nystagmus (tremor of the eyes) may have difficulty in presenting a stable image; however, some iris cameras now use stroboscopic (flashed infrared) illumination with very fast camera integration times, on the order of milliseconds, so tremor becomes unimportant for image capture.
4. the most important disability issue involving iris recognition arises with wheelchair bound persons, because a wall-mounted iris camera presumes that a person's head is within a particular range of heights. All fixed cameras are swivel mounted to adjust for height, but still their "capture box" is limited to about 18" in height variation. Wheelchair access requires either that the entire unit can move up or down (e.g. on a sliding pole installations at airports such as Heathrow and Charlotte), or else that a tethered, handheld camera be used which a person picks up like a telephone handset and brings to the appropriate level of their eyes, within arm's length.
5. A practical problem of iris recognition is that the iris is usually partially covered by eye lids and eyelashes. In order to reduce the false-reject risk in such cases, additional algorithms are needed to identify the locations of eye lids and eyelashes, and exclude the bits in the resulting code from the comparison operation. Studies show that the iris-locating algorithm based on integro-differential operator suffers from bright spots of the illumination inside the pupil, so the optimized Daugman’s algorithm overcome this problem an gives a successful results for iris localization process
Advantages
Iris recognition is an attractive technology for identity authentication for several reasons.
The smallest outlier population of all biometrics. Few people can't use the technology, as most individuals have at least one eye. In a few instances even blind persons have used iris recognition successfully, as the technology is iris pattern-dependent, not sight dependent.
Iris pattern and structure exhibit long-term stability. Structural formation in the human iris is fixed from about one year in age and remains constant (barring trauma, certain rare diseases, or possible change from special some ophthalmologic surgical procedures) over time. So, once a individual is enrolled, re-enrollment requirements are infrequent. With other biometric technologies, changes in voice timbre, weight, hairstyle, finger or hand size, cuts or even the effect of manual labor can trigger the need for re-enrollment.
Ideal for Handling Large Databases. Iris recognition is the only biometric authentication technology designed to work in the 1-n or exhaustive search mode. This makes it ideal for handling applications requiring management of large user groups, such as a National Documentation application might require. Large databases are accommodated without degradation in authentication accuracy.
Unmatched Search Speed in the one to many search mode is unmatched by any other technology, and is limited not by database size, but by hardware selected for server management.
Versatile for the One to Many, One to One, Wiegand and Token Environments. While initially designed to work in one-to-many search mode, iris recognition works well in 1-1 matching, or verification mode, making the technology ideal for use in multifactor authentication environments where PINs, or tokens like prox or smartcards are used. In a token environment, many privacy issues related to biometric database management are moot, as the user retains control of biometric data – a small template of 512 bytes per iris
Safety and Security Measures In Place. Iris recognition involves nothing more than taking a digital picture of the iris pattern (from video), and recreating an encrypted digital template of that pattern. 512-byte iris templates are encrypted and cannot be re-engineered or reconstituted to produce any sort of visual image. Iris recognition therefore affords high level defense against identity theft, a rapidly growing crime. The imaging process involves no lasers or bright lights and authentication is essentially non-contact
Convenient, Intuitive User Interface. Using the technology is an almost intuitive experience, requiring relatively little cooperation from subjects. Proximity sensors activate the equipment, which incorporates mirror-assisted alignment functionality. Audio auto-positioning prompts, automated image capture, and visual and audio authentication decision-cueing completes the process.
Disadvantages
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.
Security Considerations
Like with most other biometric identification technology, a still not satisfactorily solved problem with iris recognition is the problem of "live tissue verification". The reliability of any biometric identification depends on ensuring that the signal acquired and compared has actually been recorded from a live body part of the person to be identified, and is not a manufactured template. Many commercially available iris recognition systems are easily fooled by presenting a high-quality photograph of a face instead of a real face, which makes such devices unsuitable for unsupervised applications, such as door access-control systems. The problem of live tissue verification is less of a concern in supervised applications (e.g., immigration control), where a human operator supervises the process of taking the picture.
Methods that have been suggested to provide some defence against the use of fake eyes and irises include:
* Changing ambient lighting during the identification (switching on a bright lamp), such that the pupillary reflex can be verified and the iris image be recorded at several different pupil diameters
* Analyzing the 2D spatial frequency spectrum of the iris image for the peaks caused by the printer dither patterns found on commercially available fake-iris contact lenses
* Analyzing the temporal frequency spectrum of the image for the peaks caused by computer displays
* Using spectral analysis instead of merely monochromatic cameras to distinguish iris tissue from other material
* Observing the characteristic natural movement of an eyeball (measuring nystagmus, tracking eye while text is read, etc.)
* Testing for retinal retroreflection (red-eye effect)
* Testing for reflections from the eye's four optical surfaces (front and back of both cornea and lens) to verify their presence, position and shape
* Using 3D imaging (e.g., stereo cameras) to verify the position and shape of the iris relative to other eye features
Current Applications
* United Arab Emirates Homeland Security Border Control has been operating an expellee tracking system in the United Arab Emirates (UAE) since 2001 when the UAE launched a national border-crossing security initiative. Today all of the UAE’s Land, Air and Sea ports of entry are equipped with systems.
* One of three biometric identification technologies internationally standardized by ICAO for use in future passports (the other two are fingerprint and face recognition)
* Pakistan Iris recognition technology has been implemented by BioID Technologies SA in Pakistan for UNHCR repatriation project to control aid distribution for Afghan refugees. Refugees are repatriated by UNHCR in cooperation with Government of Pakistan and they are paid for their travel. To make sure people do no get paid more than once their Iris is scanned and the system will detect the refugees on next attempt. By database size has more than 1.3 million Iris code templates and around 4000 registrations per day. The one-many iris comparison takes place within 1.5 second against 1.3 million iris codes.
* At Schiphol Airport, Netherlands, iris recognition has permitted passport free immigration since 2001
* UK's IRIS - Iris Recognition Immigration System
* Used to verify the recognition of the "Afghan Girl" (Sharbat Gula) by National Geographic photographer Steve McCurry.
* In a number of US and Canadian airports, as part of the NEXUS program that facilitates entry into the US and Canada for pre-approved, low-risk travellers.
* In several Canadian airports, as part of the CANPASS Air program that facilitates entry into Canada for pre-approved, low-risk air travellers.
