An ensemble of one-class SVMs for fingerprint spoof detection across different fabrication materials

A fingerprint recognition system is vulnerable to spoof attacks, where a fake fingerprint is used to circumvent the system. To counter such attacks, an automated spoof detector is used to distinguish images of fake fingerprints from those of real live fingerprints. Most spoof detectors adopt a machine learning approach, where a classifier is trained to distinguish between “spoof” and “live” samples. Such approaches require training samples from both classes. However, there are two fundamental concerns. Firstly, the number of spoof samples available during the training stage is typically much less than the number of live samples, resulting in imbalanced training sets. Secondly, the spoof detector may encounter spoofs fabricated using materials that were not “seen” in the training set, thereby failing to detect them. In order to alleviate some of these concerns, we adopt a One Class Support Vector Machine (OC-SVM) approach that predominantly uses training samples from only a single class, i.e., the live class, to generate a hyper sphere that encompasses most of the live samples. The goal is to learn the concept of a “live” fingerprint. The boundary of the hyper sphere is refined using a small number of spoof samples. The proposed method uses an ensemble of such OC-SVMs based on different feature sets. Experimental results on the LivDet2011 database show the advantages of the proposed ensemble of OC-SVMs for detecting spoofs generated from previously “unseen” materials.