Applying FFT Features for Fingerprint Matching

Abstract

In this paper, a feature extraction method based on the fast Fourier transform (FFT) is proposed for the use of fingerprint matching. The performance of our approach is evaluated by the amount of time required in the features extracting and feature matching processes. The recognition rate obtained from the proposed method is also evaluated by the k-NN classifier. The experimental results show that, by using our approach, the processing time in the features extraction and searching & matching processes is reduced by up to 34.95 times, and decreased by up to 0.39 milliseconds, respectively, compared to the method proposed in [6]. Furthermore, with our proposed method, the fingerprint recognition rate can be improved by 1.1% to 13.19%.