Universal Material Translator: Towards Spoof Fingerprint Generalization

Abstract

Spoof detectors are classifiers that are trained to distinguish spoof fingerprints from bonafide ones. However, state of the art spoof detectors do not generalize well on unseen spoof materials. This study proposes a style transfer based augmentation wrapper that can be used on any existing spoof detector and can dynamically improve the robustness of the spoof detection system on spoof materials for which we have very low data. Our method is an approach for synthesizing new spoof images from a few spoof examples that transfers the style or material properties of the spoof examples to the content of bonafide fingerprints to generate a larger number of examples to train the classifier on. We demonstrate the effectiveness of our approach on materials in the publicly available LivDet 2015 dataset and show that the proposed approach leads to robustness to fingerprint spoofs of the target material.

Fingerprint Presentation Attack Detection Based on Local Features Encoding for Unknown Attacks

“…Gajawada perspective in [16]. They propose a so-called deep learning based "Universal Material Translator" (UMT).…”

“…However, it should be noted that this method does require some samples (i.e., five) of the analysed unknown PAI species. Finally, by assuming that unknown PAIs species share texture (style) information with known PAIs, Chugh and Jain [17] extended the work in [16] by combining texture styles of pre-defined PAI species to generate new synthetic unknown PAIs. Those synthetic data could, in turn, be employed as training to enhance the generalisation capability of any end-to-end PAD approach.…”

“…Those synthetic data could, in turn, be employed as training to enhance the generalisation capability of any end-to-end PAD approach. To that end, the authors proposed an "Universal Material Generator" (UMG), which, unlike [16], required no unknown PAI species to train. The experimental protocol reported a slight detection performance improvement against the proposed baseline and LivDet 2017 winner [31] (i.e., an average accuracy of 95.88% vs. 95.44% for the baseline and 94.01% for the LivDet winner).…”

“…Chugh & Jain (FSB-v2) [13] MobileNet trained for classifying ACER = 1.11% ACER = 2.93% ACER = 14.59% ACER = 17.91% minutiae-centred local patches Chugh & Jain [14] Selection of the most feasible PAI species -BPCER500 = 24.76% -to cover the deep feature space Engelsma & Jain [15] Ensemble of several GANs -BPCER500 = 50.20% --Gajawada et al [16] Universal Material Translator (UMT) to generate -BPCER1000 = 21.96% -synthetic PAIs, thereby improving PAD generalisation Chugh & Jain (FSG) [17] Universal Material Generator (UMG)…”

Finger-Vein Recognition Using Heterogeneous Databases by Domain Adaption Based on a Cycle-Consistent Adversarial Network

“…Kute et al used the Bregman divergence regularization method to reduce the distribution gap between domains; the researchers used Fisher linear discriminant analysis (FLDA) subspace learning algorithm to find a subspace through a projection matrix between fully heterogeneous data and then used the subspace to perform recognition using a support vector machine and K-nearest neighbor classifier [ 12 ]. Gajawada et al performed domain adaptation between spoof attack databases to perform augmentation to improve the generality of a fingerprint spoof attack detector [ 13 ]. Here, a synthetic spoof attack patch was created using a universal material translator wrapper.…”