Fingerprint Presentation Attack Detection Using A Novel Multi-Spectral Capture Device and Patch-Based Convolutional Neural Networks

On the Effectiveness of Laser Speckle Contrast Imaging and Deep Neural Networks for Detecting Known and Unknown Fingerprint Presentation Attacks

“…Having access to a large enough number of training samples is a critical issue for training deep neural networks. Given that our LSCI dataset is limited to 3957 images, sim- Folds Bona fide Conductive paper Conductive silicone Transparency Silicone-I Silicone-II Dragon-skin train test val train test val train test val train test val train test val train test val train test val Fold#0 1986 1240 517 6 3 2 34 20 8 14 9 3 42 26 11 7 4 2 14 9 4 Fold#1 1985 1254 504 6 4 1 33 21 8 14 8 4 42 27 10 7 4 2 14 9 4 Fold#2 1978 1249 516 6 4 1 33 21 8 14 9 3 42 26 11 6 5 2 14 9 4 ilar to the prior FPAD works [12,4,22], we adopt a patchbased approach in our pipeline. Each input sample is split into a set of small patches by sliding a window over the region of interest (ROI).…”

“…We use the architecture proposed by Hussein et al [12] as our baseline network (BaseN). As shown in Figure 3(a), BaseN consists of six consecutive 2D convolution (Conv) layers, where each 2D Conv is connected to a ReLu module.…”

Anomaly Detection With Convolutional Autoencoders for Fingerprint Presentation Attack Detection

“…In the case that the material of the PAI is thin enough for the laser to still penetrate into the skin below, bona fide properties are captured and thus the PAI is not detected. Finally, Mirzaalian et al [22] applied deep learning methods Given the promising concepts of SWIR and LSCI data for fingerprint PAD, fusions of both approaches have been published in [19], [20], [25]. These multimodal approaches prove that PAD benefits from additional sensors.…”

“…Finally, we are interested in the best fusion of both AE types, based on SWIR and laser data, since previous approaches [19], [20], [25] show a significant improvement in PAD performance. For this reason, we compute different weighted fusions and compare the results in order to find the one best suited for our fingerprint PAD approach.…”

Presentation Attack Detection for Finger Recognition

“…Combining SWIR and LSCI, Hussein et al [37] use a patch-based CNN to classify multi-spectral samples from both domains. For both techniques, low error rates are reported and a combined fusion achieves a perfect detection performance over a database compromising 551 bona fides and 227 PAs, including 17 different PAI species.…”