Fingerprint classification using scale-invariant feature transform

In this paper an application of SIFT (scale-invariant feature transform) is presented. Even though the SIFT is a computer vision algorithm, its properties confirmed by the described algorithm allow for classification of the fingerprints. The described experiment was performed using FVC2004 fingerprints database. We obtained FRR (false rejection ratio) of about 15 % and FAR (false acceptance ratio) equal to 0 %. This result allows for application in the access control to restricted areas, i.e., if FAR has to be low. In general, SIFT can be considered as the first stage of classification of fingerprints in the database searching.