Iris Recognition Based on Human-Intrepretable Features


Irisrec Icon 250

I agree to the terms of the Non-Commercial, Research Use license agreement.  Software can be downloaded once you read and agree to the license.

Please obtain the Product Authorization Code from the technology contact listed below

Contact the Office of Technology Transfer for all other license opportunities 


Free, with Product Authorization Code

Technology Contact: Jianxu Chen -

lab webpage link:


The iris is a stable biometric trait that has been widely used in various security and identification applications.  This software code develops iris features for use in forensic and law enforcement applications where positive identification requires a human-in-the-loop solution.  Iris features (i.e., crypts) are extracted and presented to the user for positive matching in the similar manner as fingerprint analysis.  Iris crypts are detected and matched between images automatically. The matching scheme is robust even when topological changes occur to the detection of the same crypts across multiple acquisitions. This software allow for the quantitative matching of iris images which is both transparent and can be supervised by a human providing a means for the user to exercise judgement in making a positive identification.

For further details and results of this program, please reference the following journal paper:

J. Chen, F. Shen, D.Z. Chen, P.J. Flynn, "Iris Recognition Based on Human-Interpretable Features," IEEE Transaction on Information Forensics and Security, vol. 11, no. 7, pp. 1476-1485, July 2016