NIST evaluated 92 different iris recognition algorithms from nine private companies and two university labs, all of which submitted software to an open competition held by NIST. The task was to identify individuals from a database of eye images taken from more than 2.2 million people.The article does a great job of showing that different solutions addressing the same problem perform differently. The article is about iris technology, but the same principles hold with all biometric modalities.
UPDATE: Here's the actual full report...
WARNING: Clicking this link (IREX III final Report) will probably cause your browser to automatically download a .zip file from The National Institute of Standards and Technology's .gov web site (not that there's anything wrong with that).
