Presentation Attack Detection Using Wavelet Transform and Deep Residual Neural Net

Abstract

Biometric authentication is becoming more prevalent for secured authentication systems. However, the biometric systems can be deceived by the imposters in several ways. Among other imposter attacks, print attacks, mask-attacks, and replay-attacks fall under the presentation attack category. The biometric images, especially iris and face, are vulnerable to different presentation attacks. This research applies deep learning approaches to mitigate the presentation attacks in a biometric access control system. Our contribution in this paper is two-fold: first, we applied the wavelet transform to extract the features from the biometric images. Second, we modified the deep residual neural net and applied it on the spoof datasets in an attempt to detect the presentation attacks. This research applied deep learning technique on three biometric spoof datasets: ATVS, CASIA two class, and CASIA cropped image sets. The datasets used in this research contain images that are captured both in a controlled and uncontrolled environment along with different resolution and sizes. We obtained the best accuracy of 93% on the ATVS Iris dataset. For CASIA two class and CASIA cropped datasets, we achieved test accuracies of 91% and 82%, respectively.