Exploiting temporal and depth information for multi-frame face anti-spoofing

Abstract

Face anti-spoofing is significant to the security of face recognition systems. Previous works on depth supervised learning have proved the effectiveness for face antispoofing. Nevertheless, they only considered the depth as an auxiliary supervision in the single frame. Different from these methods, we develop a new method to estimate depth information from multiple RGB frames and propose a depth-supervised architecture which can efficiently encodes spatiotemporal information for presentation attack detection. It includes two novel modules: optical flow guided feature block (OFFB) and convolution gated recurrent units (ConvGRU) module, which are designed to extract short-term and long-term motion to discriminate living and spoofing faces. Extensive experiments demonstrate that the proposed approach achieves state-of-the-art results on four benchmark datasets, namely OULU-NPU, SiW, CASIA-MFSD, and Replay-Attack.

Searching Central Difference Convolutional Networks for Face Anti-Spoofing

“…In contrast, auxiliary depth supervised FAS methods [4,36] are introduced to learn more detailed information effectively. On the other hand, several video level CNN methods are presented to exploit the dynamic spatio-temporal [56,62,33] or rPPG [31,36,32] features for PAD. Despite achieving state-of-the-art performance, video level deep learning based methods need long sequence as input.…”

“…For the loss function, mean square error loss L M SE is utilized for pixel-wise supervision. Moreover, for the sake of fine-grained supervision needs in FAS task, contrastive depth loss L CDL [56] is considered to help the networks learn more detailed features. So the overall loss L overall can be formulated as L overall = L M SE + L CDL .…”

“…Dense face alignment PRNet [18] is adopted to estimate the 3D shape of the living face and generate the facial depth map with size 32 × 32. More details and samples can be found in [56]. To distinguish living faces from spoofing faces, at the training stage, we normalize living depth map in a range of [0, 1], while setting spoofing depth map to 0, which is similar to [36].…”

“…Most existing state-of-the-art FAS methods [36,56,62,32] need multiple frames as input to extract dynamic spatiotemporal features (e.g., motion [36,56] and rPPG [62,32]) for PAD. However, long video sequence may not be suitable for specific deployment conditions where the decision needs to be made quickly.…”

Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition

“…D URING the past few decades, the noise robust face recognition (FR) problem has been a vibrant topic due to the increasing demands in law enforcement and biometric applications [1], [2], [3], [4], [5]. Promising performance has been achieved under controlled conditions where the acquired face region contains sufficient discriminative information [6], [7], [8], [9], [10], [11], [12]. Nevertheless, in real surveillance scenes, the desired unambiguous high-resolution (HR) face images may not be always available because of the large distances between cameras and subjects.…”