Video-Based Disguise Face Recognition Based on Deep Spiking Neural Network

摘要

Face is a vital biometric for personal identification. However, the current video-based face recognition methods could not cope with large variances such as heavy makeups, disguised faces with rubber/digital masks or faces with certain areas (eyes, nose, or mouth) invisible. In this paper, we proposed a deep spiking neural network (SNN) architecture with the dynamic facial movements (facial muscle changes caused by speaking) as the sole input for the video-based disguise face recognition application. An event-driven continuous spike-timing dependent plasticity (STDP) learning algorithm with adaptive thresholding has been applied to train the synaptic weights. The proposed video-based disguise face recognition (VDFR) learning method achieves 95% correct classification rate on our proposed video-based disguise face database (MakeFace DB).