A low-cost FPGA-based embedded fingerprint verification and matching system

The development of a fingerprint verification system on a low-cost embedded platform still remains an open issue in nowadays biometrics. In order to shed light on this field, the contribution shown in this manuscript describes a lowcost fingerprint minutiae extraction and matching system based on a Spartan3 field-programmable gate array (FPGA) with an embedded Leon2 open core processor. The proposed system architecture incorporates a floating point unit (FPU) and a discrete Fourier transform (DFT) coprocessor which accelerates the minutiae extraction process. The verification algorithm is based on the NFIS (NIST Fingerprint Image Software) version 2 open source software developed by the National Institute of Standards and Technology (NIST). A software enhancement algorithm has also been included to further accelerate the minutiae extraction process. The results on execution time reduction and FPGA occupation for different system configurations show that the proposed architecture improves substantially the performance of the baseline system.