Iris image quality assessment based on ISO/IEC 29794-6:2015 standard

Abstract

The iris biometric recognition process is one of the most consistent biometric technology among others that are currently available. However, its efficiency and accuracy can be affected by lowquality iris images used as input to a recognition system, thus, the global performance is decreased. In this context, this paper proposes an evaluation study to determine the impact of the iris image quality on the iris biometric system performance, using the key metrics presented in the ISO/IEC 29794-6:2015 standard. The experimental tests are performed using an iris image database and the OSIRIS biometric recognition software, both of them widely accepted and referenced in the latest research. Experimental results show the interval values of each quality metric and the number of images that accomplish the minimum required values. The performance of the biometric system is assessed by True-Match (TM) and False Non-Match (FNM) parameters; thus, it was possible to identify that the higher the level of image quality, the smaller the FNM value; therefore, the system performance is improved.