Improved Personal Identification Method Based on Partial Fingerprints

Abstract

The most common fingerprint recognition systems are those that are based on minutiae matching. Latent fingerprints lifted from different objects are usually noisy and broken, resulting in small and partial usable areas. Minutiae based techniques are widely used because of their temporal performances, but they do not perform so well on low quality images and in the case of partial fingerprint they might not be used at all. Therefore, when comparing partial input fingerprints with pre-stored templates, a different approach is needed. This paper proposes a fuzzy logic algorithm based on correlating a minutiae set and the regions between ridges for matching partial fingerprints.