Fuzzy logic decision in partial fingerprint recognition

Most of the fingerprint recognition systems rely on minutiae matching algorithms. Although minutiae based techniques are widely used because of their temporal performances, 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 to pre-stored templates, a different approach is needed. This paper proposes to discriminate between high quality inputs and partial ones and to apply different matching technique for each category. In the case of complete fingerprints a core-minutiae-based structure matching algorithm is proposed. On the other hand, a fuzzy logic algorithm based on correlating a minutiae set and regions between ridges is proposed for matching partial fingerprints.