FPGA implementation of a minutiae extraction fingerprint algorithm

Fingerprint recognition is one of the most common techniques used for biometric identification. Currently fingerprint technology is suitable to recognize users with high accuracy and low execution times using microprocessors able to solve algorithms with high-computational cost. However, the microprocessorpsilas cost could make the use of fingerprint biometric conditional on specific applications. This paper presents the implementation of a whole minutiae extraction fingerprint algorithm using a Spartan-3 FPGA, as an appropriate solution for portable devices and for the low-cost consumer market. The internal architecture of the proposed embedded system is based on a soft-core microprocessor and several dedicated coprocessors designed in order to accelerate the resolution of the algorithm. Experimental results show as minutiae of fingerprint are obtained in 988 ms when an image of 256 times 256 pixels is analyzed.