On the uniqueness of fingerprints via mining of statistically rare features

A new method for automatically identifying rare features in fingerprints based on a combination of level 1 features and minutia-based triangular descriptors is described. A feature is considered rare if it is statistically uncommon; for example, such a rare feature should be unique among N>1000 randomly sampled prints. A fingerprint feature that is rare has higher discriminatory power when it is identified in a print (latent or otherwise), and multiple rare features in a single print can increase discriminatory power dramatically. In the case of latent matching, such information can be significant for reaching a decision. The new approach was tested experimentally using the NIST SD-27 database and an FBI database of 11,036 unique fingerprints. The results indicated that every randomly selected fingerprint from the composite database has a small set of highly distinctive statistically rare features, some of with occurrence of 1 in 1000 fingerprints.