Comparative Analysis of Orientation Field Descriptors Used for Detecting Altered Fingerprints

In recent years, due to the computing capability, fingerprint identification is one of the most used and known biometrics. Individuals, in order to avoid automatic identification based on fingerprints, altered them by various means such as abrading, burning, cutting or through transplantations. Therefore, methods to detect altered fingerprints were developed in order to be distinguished from the natural ones. The most used methods for altered fingerprint detection are based on orientation field descriptors able to find singular regions generated by alterations. The aim of this paper is to comparatively test and assess the performance of three orientation field descriptors used for detecting the altered fingerprints. These descriptors have been tested against a non-altered fingerprint and two different fingerprint alterations by simulated central rotation: the first by cutting square regions and the second circular regions. The comparative analysis highlighted the descriptors ability to find altered fingerprints and the accuracy with which the detection is done.