Much! Iris recognition is often considered as solved. This is in some contrast to the scientific reality.
Important: If you don't see the navigation frame on the left hand side, please click here
In my opinion there are many things to be done. On the one hand, existing approaches must be assessed with the help of public datasets (remember FERET etc.?) in terms of error rates, running times and the like. On the other hand, new approaches have to be found that enable iris recognition to be ubiquitous.
The general acceptance of iris recognition and its ease of deployment in real-world scenarios has to be raised. Furthermore, iris recognition has to be related to other biometrics like face recognition, e.g. in the context of impostor detection or replay attack denial.
This site is maintained by Jan Ernst. All comments are welcome. If you want to submit relevant info please contact me.
Last updated: December 02, 2002