Effect of Facial Shape Information Reflected on Learned Features in Face Spoofing Detection

Abstract

Face recognition is a convenient and non-contact biometric method used widely for secure personal authentication. However, the face is an exposed body part, and face spoofing attacks, which compromise the security of systems that use face recognition for authentication, are frequently reported. Previous face spoofing attack detection studies proposed texture-analysis-based methods using handcrafted features or learned features to prevent spoofing attacks. However, it is unclear whether spoofing attack images reflect the face distortion resulting from failing to reflect the three-dimensional structure of a real face. To resolve this problem, we compared and analyzed the face spoofing attack detection performances of two typical convolutional neural network models, namely ResNet-18 and DenseNet-121. CASIA-FASD, Replay-Attack, and PR-FSAD were used as the training data. The classification performance of the model was evaluated based on four protocols. DenseNet-121 exhibited better performance in most scenarios. DenseNet-121 reflected facial shape information well by uniformly applying the learned features of both the initial and final layers during training. It is expected that this study will support the realization of spoofing technology with enhanced security.