Towards Contactless Fingerprint Presentation Attack Detection using Algorithms from the Contact-based Domain

In this work, we investigate whether contact-based fingerprint Presentation Attack Detection (PAD) methods can generalize to the contactless domain. To this end, we selected a state-of-the-art patch-based fingerprint PAD algorithm which achieved high detection performance in the contact-based domain and adapted it for contactless fingerprints. We train and test the method using three contactless fingerprint databases and evaluate its generalization capabilities using Leave-One-Out (LOO) pro-tocols. Further, we acquired a new PAD database and use it in a cross-database evaluation. The adopted method shows low error rates in most scenarios and can generalize to unseen contactless presentation attacks.