Multi-Modal Fingerprint Presentation Attack Detection: Evaluation On A New Dataset
share
Fingerprint presentation attack detection is becoming an increasingly challenging problem due to the continuous advancement of attack preparation techniques, which generate realistic-looking fake fingerprint presentations. In this work, rather than relying on legacy fingerprint images, which are widely used in the community, we study the usefulness of multiple recently introduced sensing modalities. Our study covers front-illumination imaging using short-wave-infrared, near-infrared, and laser illumination; and back-illumination imaging using near-infrared light. Toward studying the effectiveness of our data, we conducted a comprehensive analysis using a fully convolutional deep neural network framework. We performed our evaluations on two large datasets collected at different sites. For examining the effects of changing the training and testing sets, a 3-fold cross-validation evaluation was followed. Moreover, the effect of the presence of unseen attacks is studied by using a leave-one-out cross-validation evaluation over different attributes of the utilized presentation attack instruments. To assess the effectiveness of the studied sensing modalities compared to legacy data, we applied the same classification framework on legacy images collected for the same participants in one of our collection sites and achieved improved performance. Furthermore, the proposed classification framework was applied on the LivDet2015 dataset and outperformed existing state-of-the-art algorithms. This indicates that the power of our approach stems from the nature of the captured data rather than just the employed classification framework. Therefore, the extra cost for hardware-based (or hybrid) solutions is justifiable by its superior performance, especially for high security applications. One of the dataset collections used in this study will be publicly released upon the acceptance of this manuscript.
READ FULL TEXT