Iris Recognition

Iris recognition uses the unique patterns of the human iris to verify identity, offering one of the lowest false-acceptance rates of any biometric technology.

Iris-scan biometrics employs the unique characteristics and features of the human iris to verify the identity of an individual. The iris is the area of the eye where the pigmented, coloured circle — usually brown or blue — rings the dark pupil of the eye.

The iris-scan process begins with a photograph. A specialized camera, typically very close to the subject (no more than three feet away), uses an infrared imager to illuminate the eye and capture a very high-resolution photograph. This process takes only one to two seconds and provides the details of the iris that are mapped, recorded and stored for future matching and verification.

Eyeglasses and contact lenses present no problems for image quality, and iris-scan systems test for a live eye by checking for the normal, continuous fluctuation in pupil size.

The inner edge of the iris is located by an iris-scan algorithm, which maps the iris's distinct patterns and characteristics. An algorithm is a series of directives that tell a biometric system how to interpret a specific problem. Algorithms have a number of steps and are used by the biometric system to determine whether a biometric sample matches a stored record.

Irises are formed before birth and, barring an injury to the eyeball, remain unchanged throughout an individual's lifetime. Iris patterns are extremely complex, carry an astonishing amount of information, and have over 200 unique spots. The fact that an individual's right and left eyes differ, and that patterns are easy to capture, establishes iris-scan technology as one of the biometrics most resistant to false matching and fraud.

The false-acceptance rate for iris recognition systems is 1 in 1.2 million — statistically better than the average fingerprint recognition system. The real benefit lies in the false-rejection rate, a measure of authenticated users who are wrongly rejected. Fingerprint scanners have a 3 percent false-rejection rate, whereas iris-scanning systems achieve rates near 0 percent.

Iris-scan technology has been piloted in ATM environments in England, the US, Japan and Germany since as early as 1997. In these pilots, the customer's iris data became the verification tool for access to the bank account, eliminating the need for the customer to enter a PIN or password. When the customer presented their eye to the ATM and identity verification succeeded, access was granted to the bank account. These applications were very successful, eliminated concerns over forgotten or stolen passwords, and received very high customer approval ratings.

Airports have begun using iris-scanning for functions as diverse as employee identification and verification for movement through secure areas, and enabling registered frequent airline passengers a system that provides fast and easy identity verification to expedite their path through passport control.

Other applications include monitoring prison transfers and releases, as well as projects designed to authenticate online purchasing, online banking, online voting and online stock trading, to name just a few. Iris-scan offers a high level of user security, privacy and general peace of mind for the consumer.

A highly accurate technology such as iris-scan holds great appeal because the inherent argument for any biometric is, of course, increased security.

• The iris is a thin membrane on the interior of the eyeball. Iris patterns are extremely complex.
• Patterns are individual (even in fraternal or identical twins).
• Patterns are formed by six months after birth and stable after a year. They remain the same for life.
• Imitation is almost impossible.
• Patterns are easy to capture and encode.

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
Voiceprinting	Voice characteristics	1/30	Low	Telephone service

Source: AIM Japan, Automatic Identification Seminar, Sept. 14, 2001

Dr. John Daugman's work in iris recognition, published on his research website, forms the basis of the information presented below.

Iris recognition leverages the unique features of the human iris to perform identification and, in certain cases, verification.

Iris recognition is based on visible (via regular and/or infrared light) qualities of the iris. A primary visible characteristic is the trabecular meshwork (permanently formed by the 8th month of gestation), a tissue that gives the iris the appearance of being divided in a radial fashion. Other visible characteristics include rings, furrows, freckles, and the corona, to name only the more familiar.

Put simply, iris recognition technology converts these visible characteristics, expressed as a phase sequence, into a 512-byte IrisCode, a template stored for future identification attempts. From the iris's 11mm diameter, Dr. Daugman's algorithms extract 3.4 bits of data per square mm. This density of information means each iris can be said to have 266 "degrees of freedom," compared to 13-60 for traditional biometric technologies. This "266" figure is cited in most iris recognition literature; after accounting for the algorithm's correlative functions and for characteristics common to most human eyes, Dr. Daugman concludes that 173 "independent binary degrees of freedom" can be extracted by his algorithm — an exceptionally large number for a biometric. A key differentiator of iris-scan technology is that 512-byte templates are generated for every iris, which enables fast matching (capable of matching over 500,000 templates per second).

The first step is locating the iris using a dedicated camera no more than 3 feet from the eye. Once the camera situates the eye, the algorithm narrows in from the right and left of the iris to locate its outer edge. This horizontal approach accounts for obstruction caused by the eyelids. It simultaneously locates the inner edge of the iris (at the pupil), excluding the lower 90 degrees because of inherent moisture and lighting issues.

Iris-scan technology requires reasonably controlled and cooperative user interaction — the enrollee must hold still in a certain spot, even if only momentarily. Many users struggle to interact with the system until they become accustomed to its operation. In applications with frequent user interaction (e.g. employee physical access), the technology becomes easier to use over time; however, applications where user interaction is infrequent (e.g. national ID) may encounter ease-of-use issues. Over time, as acquisition devices improve, this issue should become less of a problem.

The accuracy claims associated with iris-scan technology may overstate real-world performance. Because the claimed equal error rates are derived from assessing and matching ideal iris images (unlike those acquired in the field), actual results may not live up to the impressive projections provided by leading suppliers of the technology.

Lastly, since iris technology is designed as an identification technology, fallback procedures may not be as fully developed as in a verification deployment (users accustomed to identification may not carry the necessary ID, for example). While these issues do not reduce the effectiveness of iris recognition technology, they should be kept in mind by any company considering an iris-based solution.

Iris-scan technology has traditionally been deployed in high-security, employee-facing physical access implementations, although 2002 saw a number of novel, high-profile iris-scan deployments in new applications. Iridian — the technology's primary developer — is dedicated to moving the technology to the desktop, and has had some success in small-scale logical access deployments. The most prominent recent deployments of iris-scan technology have been passenger authentication programs at airports in the U.S., U.K., Amsterdam and Iceland; the technology is also used in corrections applications in the U.S. to identify inmates. A number of developing countries are considering iris-scan technology for national ID and other large-scale 1:N applications, although to date the largest deployed Iridian database is still believed to span under 100,000 enrollees. Notable iris-scan applications include the following.

Project Description	Location	Vertical Sector	Horizontal Application	Application Description	Additional Description
Iris in Pakistan	Pakistan	Government	Civil ID	Tracking	Afghan refugees receive assistance package on first enrollment through UNHCR
Iris Pilot - Logan	US-MA	Travel and Transportation	Phys Acc/T&A	Physical Access	Iris piloted for employee access to security office (LG3000)
JFK Iris Pilot	US-NY	Travel and Transportation	Phys Acc/T&A	Physical Access	1 door to tarmac protected
City Hospital of Bad Reichenhall in Bavaria	Germany	Health care	Phys Acc/T&A	Physical Access	Access control to infant center to prevent kidnappings
Singapore Border Crossing	Singapore	Government	Travel and Transportation	Physical Access	50k day workers enter Singapore from Malaysia daily by motorcycle. Iris-scan does 1:N
UK Passport Office Iris Pilot	UK	Government	Civil ID	Passport	Opt-in pilot to test iris acceptance, part of 6-mo public comment period
Venerable Bede (UK) School - Iris	UK	Education	Retail/ATM/POS	POS	900-pupil school to use Iridian for library check-out and cafeteria payment

Though it is one of the later-emerging technologies in the biometric market, iris-scan is set to grow substantially through 2007. Iris-scan offers low false-match rates and hands-free operation, and is the only viable alternative to fingerprint technologies in 1:N applications where a single record must be located. Iris-scan's resistance to false matches is offset somewhat by the level of training required to use the system effectively.

As such, iris-scan will primarily be used in applications that require high levels of security, although convenience-driven deployments (e.g. Privium) will continue. Iris-scan revenues are projected to grow from $16.2m in 2002 to $210.2m in 2007. Iris-scan revenues are expected to comprise approximately 5% of the entire biometric market.

Legacy links (no longer active) (2)

• http://www.iris-recognition.org
• http://www.lirmm.fr/bibli/Document.htm&numrec=031976924915870