Minimizing the impact of spoof fabrication material on fingerprint liveness detector

Fingerprint liveness detection algorithms have been used to disambiguate live fingerprint samples from spoof (fake) fingerprints fabricated using materials such as latex, gelatine, etc. Most liveness detection algorithms are learning-based and dependent on the fabrication materials used to generate spoofs during the training stage. Consequently, the performance of a liveness detector is significantly degraded upon encountering fabrication materials that were not used during the training stage. The aim of this work is to design a simple pre-processing scheme that can improve the interoperability of liveness detectors across different fabrication materials - including those not observed during the training stage. Such a generalization ability is desirable in liveness detectors. Experiments on the LivDet 2011 fake fingerprint dataset suggest that (a) different fabrication materials when used in the training stage impart different degrees of generalization ability to the liveness detector and (b) the proposed pre-processing scheme improves generalization performance by upto 44%.