An Efficient Algorithm for Human Identification Based on Fingerprint Biometrics

Abstract

This paper proposes an efficient algorithm for
fingerprint matching based human identification. Fingerprint
biometrics finds its special position in biometric based identification due to the fact that they are easy to obtain and most importantly they are scientifically unique, reliable and universally accepted. A major approach in fingerprint recognition now-a-days is based on the
distance metrics based minutiae matching. One important problem is false spurious minutiae in the finger features. One main reason for these false minutiae is presence of noise. In our proposed system we remove the noise by adaptive wiener filtering technique. Morphological thinning plays a main role in proposed system for thinning the ridges. We have also presented an accurate fingerprint identification technique for minutia extraction and a minutia matching. For minutia marking we considered two steps in post processing to remove false minutia and for minutiae matching we considered alignment based relax box matching method. MATLAB
7.9 is used for system verification. Experimental results show that this method achieves a much better and efficient matching performance.