Homeland Security


Retina and Iris Identification

Iris recognition today combines technologies from several fields including, computer vision (CV), pattern recognition, statistical interference, and optics. The goal of the technology is near-instant, highly accurate recognition of a person's identity based on a digitally represented image of the scanned eye. The technology is based upon the fact that no two iris patterns are alike (the probability is higher than that of fingerprints). The iris is a protected organ which makes the identification possibilities life long. The iris can therefore serve as a life long password which the person must never remember. Confidence in recognition and identification facilitates exhustive searches through nation-sized databases.

Iris recognition technology looks at the unique characteristics of the iris, the colored area surrounding the pupil. While most biometrics have 13 to 60 distinct characteristics, the iris is said to have 266 unique spots. Each eye is believed to be unique and remain stable over time and across environments (e.g., weather, climate, occupational differences).

Iris recognition systems use small, high-quality cameras to capture a black and white high-resolution photograph of the iris. Once the image is captured, the iris' elastic connective tissue-called the trabecular meshwork-is analyzed, processed into an optical "fingerprint," and translated into a digital form. Figure 12 depicts the process of generating an iris biometric. Given the stable physical traits of the iris, this technology is considered to be one of the safest, fastest, and most accurate, noninvasive biometric technologies. This type of biometric scanning works with glasses and contact lenses in place. Therefore, iris scan biometrics may be more useful for higher risk interactions, such as building access. Improvements in ease of use and system integration are expected as new products are brought to market.

The iris is differentiated by several characteristics including ligaments, furrows, ridges, crypts, rings, corona, freckles, and a sigzag collarette.

Iris recognition technologies are now seen in a wide array of identification systems. They are used in passports, aviation security, access security (both physical and electronic), hospitals, and national watch lists. Iris recognition alogithms can be seen in more and more identification systems relating to customs and immigration. Future applications will include, e-commerce, information security (infosec), authorisation, building entry, automobile ignition, forensic applications, computer network access, PINs, and personal passwords.

Advantages of the Iris for Identification

  • Highly protected, internal organ of the eye
  • Externally visible; patterns imaged from a distance
  • Iris patterns possess a high degree of randomness
    • variability: 244 degrees-of-freedom
    • entropy: 3.2 bits per square-millimeter
    • 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 IrisCodes per second on 300MHz CPU

Disadvantages of the Iris for Identification

  • Small target (1 cm) to acquire from a distance (1 m)
  • Moving target ...within another... on yet another
  • 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 (Orwellian) connotations

Retina recognition technology captures and analyzes the patterns of blood vessels on the thin nerve on the back of the eyeball that processes light entering through the pupil. Retinal patterns are highly distinctive traits. Every eye has its own totally unique pattern of blood vessels; even the eyes of identical twins are distinct. Although each pattern normally remains stable over a person's lifetime, it can be affected by disease such as glaucoma, diabetes, high blood pressure, and autoimmune deficiency syndrome.

The fact that the retina is small, internal, and difficult to measure makes capturing its image more difficult than most biometric technologies. An individual must position the eye very close to the lens of the retina-scan device, gaze directly into the lens, and remain perfectly still while focusing on a revolving light while a small camera scans the retina through the pupil. Any movement can interfere with the process and can require restarting. Enrollment can easily take more than a minute. The generated template is only 96 bytes, one of the smallest of the biometric technologies.

One of the most accurate and most reliable of the biometric technologies, it is used for access control in government and military environments that require very high security, such as nuclear weapons and research sites. However, the great degree of effort and cooperation required of users has made it one of the least deployed of all the biometric technologies. Newer, faster, better retina recognition technologies are being developed.



NEWSLETTER
Join the GlobalSecurity.org mailing list