Real Time Implementation of Multi-modal Biometric System

 

Generally, uni-modal biometric recognition system depends on a single unique biometric feature. Due to this dependency these systems are vulnerable to variety of problems such as noisy data, non-universality, spoofing, intra- class variations and inter-class similarities. These problems leads to considerably lack of performance, high false acceptance rate (FAR) and false rejection rate (FRR), limited discrimination capability and upper bound in performance. A multi-modal biometric system should overcome the aforementioned limits by integrating two or more biometric features.

 

Although, there has been substantial amount of work on combining dierent biometrics for a variety of purposes but not much work has focused on the implementation of multi-modal biometric system, in resources-constrained embedded system for real-time performance, as it is poses great challenge. Therefore, it is least developed area. The basic aim of this project is to implement dierent multi-modal biometric techniques on FPGA’s and to find out an optimized solution for future biometric applications.