The BTAS Competition on Mobile Iris Recognition

The security of mobile devices has become an increasingly important issue especially for the mobile-payment application. Iris recognition is an emerging technology for mobile authentication owing to its high uniqueness and distinctiveness. However, it is a challenging problem because iris images acquired by mobile devices generally have low-quality and the computational resources of mobile devices are limited. In order to track the state-of-the-art algorithms in iris recognition on mobile devices under near infra-red (NIR) illumination, we organized the BTAS Competition on Mobile Iris Recognition (or MIR2016 shortly), which is the first mobile iris recognition competition of NIR images as far as we know. All the participants have to strictly comply with the evaluation protocol to assure fairness. In this competition, three participants submitted six algorithms in total and five algorithms from two participants were qualified. The submitted algorithms were trained on the newly constructed MIR-Train database and evaluated on the unpublished MIR-Test database. We rank the submitted algorithms by the evaluated results in terms of False Non-match Rate (FNMR) when False Match Rate (FMR) is 0.0001.