Face spoofing detection with local binary pattern network

Nowadays, face biometric based access control systems are becoming ubiquitous in our daily life while they are still vulnerable to spoofing attacks. So developing robust and reliable methods to prevent such frauds is unavoidable. As deep learning techniques have achieved satisfactory performances in computer vision, they have also been applied to face spoofing detection. However, the numerous parameters in these deep learning based detection methods cannot be updated to optimum due to limited data. Local Binary Pattern (LBP), effective features for face recognition, have been employed in face spoofing detection and obtained promising results. Considering the similarities between LBP extraction and convolutional neural network (CNN) that the former can be accomplished by using fixed convolutional filters, we propose a novel end-to-end learnable LBP network for face spoofing detection. Our network can significantly reduce the number of network parameters by combing learnable convolutional layers with fixed-parameter LBP layers that are comprised of sparse binary filters and derivable simulated gate functions. Compared with existing deep leaning based detection methods, the parameters in our fully connected layers are up to 64x savings. Conducting extensive experiments on two standard spoofing databases, i.e., Relay-Attack and CASIA-FA, our proposed LBP network substantially outperforms the state-of-the-art methods.