Iris recognition
Iris recognition is a method of biometrics for authentication or identification of individuals. But be using special cameras pictures of iris ( iris ) recorded the eye, identified with the algorithmic method, the characteristic features of each iris, in a set of numerical values ( feature vector, engl. "Template" ) stored converted and for the recognition or with a or more previously stored templates compared.
History of development
The original concept of using iris images for biometric recognition was developed in 1987 by Flom and Safir and patents pending. The expiry of the patent in 2006, has since led to increased research efforts worldwide.
The currently most widely used method and template (April 2007) in commercial use is based on the algorithms of the mathematician John Daugman iris code.
Properties
Commercial detection methods detect about 260 individual optical characteristics of the iris. These features develop from a randomized, morphogenetic process in the first months of life of a person and remain largely unchanged over the remaining life time. Even identical twins do not have identical iris structure. The outstanding feature of iris recognition in practical applications is their extremely low compared to other biometric method number of false positive comparison results (English " false matches" ), that is, the likelihood of confusion of an iris code with the one eye of another person is almost zero. As a result, the iris recognition is a reliable identification methods in large databases with millions of personal records, as well as for identification in access control situations without primary distinguishing feature, that is, without identification cards or RFID tags.
False negative results (English " false non -matches " ), ie cases of non- recognition of a person actually collected, can set up especially during unfavorable reception conditions of the eye, when the iris example, because of glasses edges, typical reflections on glasses or in some Asians is narrow eyelids insufficiently visible.
Another characteristic is the low demand for computing resources for iris comparison. Therefore, the iris recognition and uptake is particularly suitable for mobile use in PDA -sized devices.
Applications
Examples are the use of iris recognition by the UNHCR in Repatrisierung Afghan citizens in the border police immigration control in the UAE or in the control of protected areas in Iraq by the U.S. Army. In all these cases should be ensured by Iris recognition that none of the persons screened under different or false identities occurs. Other applications exist in access control to high security areas and in automated border controls ( eg airports Frankfurt, Schiphol, Heathrow).
The current (as of 2011 ) the largest project with biometric iris recognition is worldwide the Indian " Aadhaar " program. It is used to record all 1.2 billion people residing in the country in order to assign them to government and business purposes rather a unique personal identification number can. A combination of iris and fingerprint recognition is intended to enable the detection and avoidance of multiple or false identities.
The first mass application in the immigration control of the United Arab Emirates as of 2002 there were attempts of illegal entering the country to avoid the identification by iris scan. Using medical eye drops widens the pupil and the iris contracts, so that temporarily the recognition is prevented. Then, the system was changed so that an extended iris is automatically recognized as such and the iris scan is repeated on the person after a few hours.
Together with the face and fingerprint recognition is one of the iris recognition to those provided by the ICAO biometric forms for use in electronic passports ( e-passport ). To ensure the global, multi-vendor interoperability of data that specifies the ISO / IEC 19794-6 " exchange format based on iris images " further the relevant requirements in iris image capture and storage.
For forensic purposes, the iris recognition is of limited use, as even disintegrate their iris structures a few minutes after the death of a person.
Privacy Legal issues
Today's commercial devices for iris recognition is common that the distance between the sensor (camera) and the eye is limited to about 0.2 to 1 meter and detection requires cooperation by the user - he must actively look towards the camera - but what can be provoked voluntarily by the sensor is hidden in a as "eye - catcher" acting object, such as an attractive advertising poster or an information board. In the movie Minority Report a fictional future is described, identify automated iris recognition systems at a distance of several meters passersby. The development of such systems is in the form of feasibility studies and prototypes currently ( April 2007) in preparation. It is feared that in the future totalitarian states or organized crime could abuse the identification of the iris recognition capabilities for dishonest purposes. Therefore, consideration of the need exist to provide that disclosure of such devices under regulatory control.