Fingerprint recognition system design

Abstract

In this study, a minutiae-based fingerprint recognition system is implemented which includes normalization, enhancement, thinning, extraction of minutiae, elimination of false minutiae, orientation estimation, core point detection, finding reference points and matching processes. Accordingly, the effects of enhancement and elimination of false minutiae processes, methods of reference point determination and low quality fingerprint images on system performance are analyzed using two different fingerprint databases. As a result, it is shown that the recognition rate is greatly improved by enhancement and elimination of false minutiae processes. Vector triangle method, used to determine the reference point, is shown to perform better than the core point or the minutia point that is determined according to the core point. Some low quality fingerprint images are observed to have negative effects on the performances of minutiae-based fingerprint recognition systems. Yet, about 90% recognition accuracy is obtained from the developed fingerprint recognition system.