Automatic adaptation of fingerprint liveness detector to new spoof materials

A fingerprint liveness detector is a pattern classifier that is used to distinguish a live finger from a fake (spoof) one in the context of an automated fingerprint recognition system. Most liveness detectors are learning-based and rely on a set of training images. Consequently, the performance of a liveness detector significantly degrades upon encountering spoofs fabricated using new materials not used during the training stage. To mitigate the security risk posed by new spoofs, it is necessary to automatically adapt the liveness detector to new spoofing materials. The aim of this work is to design a scheme for automatic adaptation of a liveness detector to novel spoof materials encountered during the operational phase. To facilitate this, a novel-material detector is used to flag input images that are deemed to be made of a new spoofing material. Such flagged images are then used to retrain the liveness detector. Experiments conducted on the LivDet 2011 database suggest (i) a 62% increase in the error rate of existing liveness detectors when tested using new spoof materials, and (ii) upto 46% improvement in liveness detection performance across spoof materials when the proposed adaptive approach is used.