Biometric Sensor and Match-On-Card Evaluation platform

Biometric systems are increasingly used to check or determine the identity of an individual. IT Industry is very interesting to this authentication solution in order to embed it in daily life products. The need of the evaluation of biometric sensors and Match-On-Card (MOC) algorithms is more more important to help them to choose the best system for a specific product. Among the different biometric systems, which one provides the best False Rejection Rate (FRR) given the False Acceptance Rate (FAR) set to a specific value ? How much time is needed to achieve a biometric verification on a smartcard ? Researchers are also interested to improve their MOC algorithm an also to compare it with the ones in the state of the art. These aspects become to be crucial for many applications like e-payment, physical access control... The purpose of this paper is to propose an evaluation platform on biometric sensors and MOC for testing their performance and security. This platform allows to perform tests given scenarios and benchmarks for comparing MOCs, and permit to test fake biometric data. We illustrate the usefulness of this platform on a commercial MOC, four commercial sensors and attacks on fingerprint (fake and dead fingers). The paper is organized as follows. Section 2 is devoted to the state of the art on the evaluating platform. Section 3 describes the proposed platform and its different modules. In Section 4, we describe the sensor acquisition platform and attacks on sensor. In section 5, we illustrate results on a commercial sensor and MOC. We conclude and give some perspectives on this work in Section 6.