ADAPTABLE FINGERPRINT MINUTIAE EXTRACTIONudALGORITHM BASED-ON CROSSING NUMBERudMETHOD FOR HARDWARE IMPLEMENTATIONudUSING FPGA DEVICE

摘要

In this article. a main perspective of developing and implementing fingerprint extraction and matchingudalgorithms as a pari of fingerprint recognition system is focused. First, developing a simple algorithm toudextract fingerprint features and test this algorithm on Pc. The second thing is implementing this algorithmudinto FPGA devices. The major research topics on which the proposed approach is developing andudmodifying fingerprint extraction feature algorithm. This development and modification are using crossingudnumber method on pixel representation value '0'. In this new proposed algorithm, it is no need a processudconcerning ROI segmentation and no trigonometry calculation. And specially in obtaining their parametersudusing Angle Calculation Block avoiding floating points calculation. As this method is local feature thatudusually involve with 60-100 minutiae points, makes the template is small in size. Providing FAR. FRR andudEER, performs the performance evaluation of proposed algorithm. The result is an adaptable fingerprintudminutiae extraction algorithm into hardware implementation with 14.05 % of EEl?, better than referenceudalgorithm, which is 20.39 % . The computational time is 18 seconds less than a similar method, which takesud60-90 seconds just for pre-processing step. The first step of algorithm implementation in hardwareudenvironment (embedded) using FPGA Device by developing IP Core without using any soft processor isudpresented.