WASHINGTON (dpa-AFX) - There are a number of biometric identification systems like finger print scanners, retina scanners, voice recognition, face recognition and iris recognition systems that are used to authenticate a person's claimed identity. Of all the biometrics mechanisms, iris recognition is generally considered to be the most accurate and efficient in person identification because it has been assumed that the iris is a 'stable' biometric over a person's lifetime.
However, a new study by researchers from the University of Notre Dame have found that iris recognition systems are affected by an aging process that causes their recognition performance to deteriorate over a period of time. The finding challenges the popular notion of the iris being a stable biometric marker over a person's lifetime.
The system works by detecting a person's identity by mathematical analysis of the random patterns that are visible within the iris of an eye. The iris muscle is the colored ring around the pupil. Each iris muscle is unique as it exhibits a distinctive pattern. It regulates the size of the pupil, controlling the amount of light entering the eye.
As part of their study, researchers analyzed a large data set of images acquired over a period of time. Using their data, they were able to analyze year-to-year change over three successive years for one group of people.
Kevin Bowyer, Professor of Department of Computer Science and Engineering at the University of Notre Dame and lead author of the study said 'Our experimental results show that, in fact, the false non-match rate increases over time, which means that the single enrollment for life idea is wrong.'
He added 'The false non-match rate is how often the system says that two images are not a match when in truth they are from the same person.'
This is due to the template aging effect. A template aging effect occurs when the quality of the match between an enrolled biometric sample and a sample to be verified degrades over a period of time.
The researcher says systems can be put in place to handle this phenomenon. One possible solution for this is to re-enroll people into the system after certain time intervals. Another possibility is to put in place some type of rolling re-enrollment, a method by which a person is automatically re-enrolled each time he is recognized.
'The iris template aging effect will only be a problem for those who for some reason refuse to believe that it exists' said the researcher.
Iris recognition is used in airports and border crossings including the London airports, Schipol (Amsterdam) airport and border entry in the UAE. The highest application of iris biometrics at present is in the Unique ID program in India which has already enrolled 84 million people.
The research paper was presented at the Institute of Electrical and Electronics Engineers Computer Society Workshop on Biometrics.
Copyright RTT News/dpa-AFX