The iris recognition process begins with video-based image acquisition that locates the eye and iris - the colored portion that surrounds the pupil. The boundaries of the pupil and limbus are defined, eyelid occlusion and specular reflection are discounted, and quality of image is determined for processing.
The iris pattern is processed and encoded into a 512 byte IrisCode® record, which is stored and used for recognition in any transaction when a live iris is presented for comparison. Eyeglasses and contact lenses are accommodated easily.
Typically, identification time averages about two seconds. A key differentiator for iris recognition is its ability to perform identification using a one-to-many search of a database, with no limitation on the number of IrisCode records contained therein.
The IrisCode is a 512-byte digitized record that is created from the video image produced after an individual glances into the camera. Because it exists digitally, the IrisCode can be stored in hexadecimal code in a database like any other information. Once in the database, an IrisCode can be used as a basis for identification, enabling comparison between an IrisCode captured at an access point or a desktop PC against IrisCode records stored in the database.
Iris identification uses standard video
cameras — the same kind you would use to videotape your family- to take a
picture of the iris of your eye. It does not use lasers (like the ones
used in bar code scanners you might see at the grocery store) and
therefore has none of the inherent risks associated with lasers.
Iridian Technologies™ product lines (such as the
Authenticam™, and products that appear in physical access systems and
ATMs) are in compliance with American National Standard ANSI / IESNA
RP-27.1-96 and International Standard IEC 60825-1, Class 1 LED. These are
the latest worldwide standards for eye safety.
Iridian Technologies™ has developed a biometric recognition system capable of positively recognizing and/or verifying the identity of individuals without physical contact or human decision-making. Personal recognition has historically been based on what a person possesses (a card); knows (a Personal Identification Number, or PIN); or is (an inherent physiological or behavioral characteristic). Facial features (both infra-red signatures and geometry), fingerprints, hand geometry, vein patterns, retinal patterns, voice patterns, and signature dynamics have all been explored as biometric identifiers with varying levels of success. All but voice and facial recognition require contact or have been characterized by some as invasive or intrusive. Many have suffered from high cost and unsatisfactory error rates. Our Technology, which uses unique patterns of the human iris, overcomes previous shortcomings and provides positive recognition of an individual without contact or invasion, at extremely high confidence levels.
The video-based system locates the eye and iris; evaluates the degree of occlusion by eyelid and spectral reflection; determines the quality of image focus; and determines the center and boundary of the pupil and the limbus (outer edge of the iris) for processing. The iris is zoned, and the features therein measured and encoded into a 512 byte IrisCode® for enrollment or recognition. The presented biometric is compared to an extensive database for recognition, or to a referenced IrisCode for verification. Computations and decisions are accomplished at extremely high rates of speed, resulting in processing times of less than two seconds.
The process is based on the unique nature and the extreme richness of the human iris. The multiple contraction furrows, collagenous fibers, crypts, coronas, striations, serpentine vasculature, freckles, rifts, and pits produce a non-duplicable organ with more than 400 measurable variables. The Iridian Technologies process uses about 240 of these {Degrees of Freedom} to create a code which can be compared to an entire database in milliseconds, producing a positive recognition with "imposter odds" averaging as high as 1 in 1048. Six years of operational experience in real world environments has confirmed early theoretical work, and has demonstrated the practicality of such recognition technology.