Iris recognition is a method of biometrics for the purpose of authenticating or identifying individuals. For this purpose, images of the iris of the eye are taken with special cameras, the characteristic features of the respective iris are identified using algorithmic methods, converted into a set of numerical values (feature vector, or “template”) and stored for recognition by a classification algorithm such as a neural network or with one or more templates that have already been stored.
The original concept of using iris images for biometric recognition was developed and patented in 1987. The expiration of the patent in 2006 has since led to increased research efforts worldwide. The currently most widely used method and template in commercial use is the iris code, which is based on algorithms developed by mathematician John Daugman. Since January 2015, EyeLock has been offering the first iris scanner with a USB port that is compatible with the U2F protocol of the FIDO Alliance.
Features of Iris Recognition
Commercial recognition methods capture about 260 individual optical features of the iris. These traits develop from a random, morphogenetic process in the first few months of a person’s life and remain largely unchanged throughout the rest of their lives. Even identical twins do not have an identical iris structure. The outstanding feature of iris recognition in practical use is its extremely low number of false positives compared to other biometric methods, i.e. the probability of confusing an iris code with that of another person’s eye is almost zero. This makes iris recognition suitable as a reliable identification method even in large databases with millions of personal records, as well as for identification in access control situations without a primary identification feature, i.e. without ID cards or RFID tags.
---
False negatives Results (false non-matches), i.e. cases of not recognizing a person who has actually been recorded, can occur in particular in the case of unfavorable viewing conditions of the eye, for example if the iris is insufficiently visible due to the edges of glasses, reflections on spectacle lenses or the narrow eyelids typical of mostly Far East Asians). Another characteristic is the low need for computational resources for iris comparison. Therefore, iris recognition and recording is particularly suitable for mobile use in PDA-sized devices.
Application of Iris Recognition and Data Protection Issues
For forensic purposes, iris recognition is only suitable to a limited extent, as its iris structures decay just a few minutes after a person’s death. In mobile phones, iris recognition is used to unlock the phone instead of a PIN code or fingerprint. However, it may be easier to fool the system than PIN or fingerprint.
Currently the world’s largest project with biometric iris recognition is the Indian “Aadhaar” program. It is used to record all approximately 1.2 billion people residing in the country in order to be able to assign them a unique personal identification number for state and legal purposes. A combination of iris and fingerprint recognition is intended to enable the identification and avoidance of multiple or false identities.
What today’s commercial devices for iris recognition have in common is that the distance between the sensor (camera) and the eye is limited to about 0.2 to 1 meter and the recognition requires cooperation by the user – he must actively look in the direction of the camera – but this can also be provoked voluntarily by hiding the sensor in an object that acts as an “eye-catcher”. for example, an attractive advertising poster or an information board.
The feature film Minority Report describes a fictitious future in which iris recognition systems automatically identify passers-by at a distance of several meters. It is feared that in the future, totalitarian states or organized crime could misuse the identification capabilities of iris recognition for dishonest purposes. There are considerations regarding the need to place the proliferation of such devices under legal control.
