Abu Dhabi UAE, September 3rd 2005 – The Abu Dhabi Police General Headquarters in the United Arab Emirates and Cambridge University announced today the results of a joint study conducted on the collected IrisCodes in the United Arab Emirates over the past three years. UAE Minister of Interior H.R.H. Sheikh Saif Bin Zayyed graciously consented to make the enrollment database of IrisCodes available to the University of Cambridge for detailed analysis, and for the results to be disseminated in this study for the benefit of all.
In the summer of 2001 the Abu Dhabi Police launched a national border-crossing security programme that is today deployed at all 17 of the UAE's air, land, and sea ports. It is based upon mathematical analysis of the random patterns visible in the iris of a person's eye (iris recognition), using algorithms developed by Professor John Daugman of Cambridge University, and a networked server and communications architecture called IrisFarm developed by IrisGuard Inc. for reliable and rapid matching and enrollment functions, with unlimited scalability to national populations (http://www.irisguard.com)
In the UAE border-crossing deployment, nearly 2 trillion (2 million-million) iris comparisons have been performed to date, as foreign nationals visiting the UAE have their irises compared against all the IrisCodes (mathematical descriptions of registered iris patterns) stored in a central database. Some 46,000 persons have thereby been caught trying to re-enter the UAE with false travel documents since this deployment began.
The Abu Dhabi Directorate of Police report that so far there have been no False Matches; yet it was desired to exploit the large enrollment database to understand better the statistical powers of iris recognition technology. For example, by computing the similarities between all possible pairings of different irises in the database, much could be learned about the robustness of the algorithms against making any False Matches when there are such vast numbers of opportunities. This would help to illuminate the technology's potential for even larger-scale national deployments.
In this study, statistical results are presented for biometric recognition of persons by their iris patterns, based on 200 billion cross-comparisons between different eyes. The database consisted of 632,500 iris images acquired in the UAE, using the Daugman algorithms for iris recognition.
A total of 152 different nationalities were represented in this database, which is the largest iris database in the world. Statistical analysis of the 20
