Deep face recognition: A survey

Face anti-spoofing (a.k.a. presentation attack detection) has recently emerged as an active topic with great significance for both academia and industry due to the rapidly increasing demand in user authentication on mobile phones, PCs, tablets, and so on. Recently, numerous face spoofing detection schemes have been proposed based on the assumption that training and testing samples are in the same domain in terms of the feature space and marginal probability distribution. However, due to unlimited variations of the dominant conditions (illumination, facial appearance, camera quality, and so on) in face acquisition, such single domain methods lack generalization capability, which further prevents them from being applied in practical applications. In light of this, we introduce an unsupervised domain adaptation face anti-spoofing scheme to address the real-world scenario that learns the classifier for the target domain based on training samples in a different source domain. In particular, an embedding function is first imposed based on source and target domain data, which maps the data to a new space where the distribution similarity can be measured. Subsequently, the Maximum Mean Discrepancy between the latent features in source and target domains is minimized such that a more generalized classifier can be learned. State-of-the-art representations including both hand-crafted and deep neural network learned features are further adopted into the framework to quest the capability of them in domain adaptation. Moreover, we introduce a new database for face spoofing detection, which contains more than 4000 face samples with a large variety of spoofing types, capture devices, illuminations, and so on. Extensive experiments on existing benchmark databases and the new database verify that the proposed approach can gain significantly better generalization capability in cross-domain scenarios by providing consistently better anti-spoofing performance.

Unsupervised Domain Adaptation for Face Anti-Spoofing

In this paper, we propose a novel framework leveraging the advantages of the representational ability of deep learning and domain generalization for face spoofing detection. In particular, the generalized deep feature representation is achieved by taking both spatial and temporal information into consideration, and a 3D convolutional neural network architecture tailored for the spatial-temporal input is proposed. The network is first initialized by training with augmented facial samples based on cross-entropy loss and further enhanced with a specifically designed generalization loss, which coherently serves as the regularization term. The training samples from different domains can seamlessly work together for learning the generalized feature representation by manipulating their feature distribution distances. We evaluate the proposed framework with different experimental setups using various databases. Experimental results indicate that our method can learn more discriminative and generalized information compared with the state-of-the-art methods.

Learning Generalized Deep Feature Representation for Face Anti-Spoofing

Face recognition systems are susceptible to presentation attacks such as printed photo attacks, replay attacks, and 3D mask attacks. These attacks, primarily studied in visible spectrum, aim to obfuscate or impersonate a person's identity. This paper presents a unique multispectral video face database for face presentation attack using latex and paper masks. The proposed Multispectral Latex Mask based Video Face Presentation Attack (MLFP) database contains 1350 videos in visible, near infrared, and thermal spectrums. Since the database consists of videos of subjects without any mask as well as wearing ten different masks, the effect of identity concealment is analyzed in each spectrum using face recognition algorithms. We also present the performance of existing presentation attack detection algorithms on the proposed MLFP database. It is observed that the thermal imaging spectrum is most effective in detecting face presentation attacks.

/pdf/face-presentation-attack-with-latex-masks-in-multispectral-30ug76occ6.pdf

Face Presentation Attack with Latex Masks in Multispectral Videos

Deep neural network (DNN) architecture based models have high expressive power and learning capacity. However, they are essentially a black box method since it is not easy to mathematically formulate the functions that are learned within its many layers of representation. Realizing this, many researchers have started to design methods to exploit the drawbacks of deep learning based algorithms questioning their robustness and exposing their singularities. In this paper, we attempt to unravel three aspects related to the robustness of DNNs for face recognition: (i) assessing the impact of deep architectures for face recognition in terms of vulnerabilities to attacks, (ii) detecting the singularities by characterizing abnormal filter response behavior in the hidden layers of deep networks; and (iii) making corrections to the processing pipeline to alleviate the problem. Our experimental evaluation using multiple open-source DNN-based face recognition networks, and three publicly available face databases demonstrates that the performance of deep learning based face recognition algorithms can suffer greatly in the presence of such distortions. We also evaluate the proposed approaches on four existing quasi-imperceptible distortions: DeepFool, Universal adversarial perturbations, $$l_2$$
 , and Elastic-Net (EAD). The proposed method is able to detect both types of attacks with very high accuracy by suitably designing a classifier using the response of the hidden layers in the network. Finally, we present effective countermeasures to mitigate the impact of adversarial attacks and improve the overall robustness of DNN-based face recognition.

Detecting and Mitigating Adversarial Perturbations for Robust Face Recognition

In movies, film stars portray another identity or obfuscate their identity with the help of silicone/latex masks. Such realistic masks are now easily available and are used for entertainment purposes. However, their usage in criminal activities to deceive law enforcement and automatic face recognition systems is also plausible. Therefore, it is important to guard biometrics systems against such realistic presentation attacks. This paper introduces the first-of-its-kind silicone mask attack database which contains 130 real and attacked videos to facilitate research in developing presentation attack detection algorithms for this challenging scenario. Along with silicone mask, there are several other presentation attack instruments that are explored in literature. The next contribution of this research is a novel multilevel deep dictionary learning-based presentation attack detection algorithm that can discern different kinds of attacks. An efficient greedy layer by layer training approach is formulated to learn the deep dictionaries followed by SVM to classify an input sample as genuine or attacked. Experimental are performed on the proposed SMAD database, some samples with real world silicone mask attacks, and four existing presentation attack databases, namely, replay-attack, CASIA-FASD, 3DMAD, and UVAD. The results show that the proposed algorithm yields better performance compared with state-of-the-art algorithms, in both intra-database and cross-database experiments.

Detecting Silicone Mask-Based Presentation Attack via Deep Dictionary Learning

This is the first work to explore template aging in 3D face recognition. We use a dataset of images representing 16 subjects with 3D and 2D face images, and compare short-term and long-term time-lapse matching accuracy. We find that an ensemble-of-regions approach to 3D face matching has much greater accuracy than whole-face 3D matching, or than a commercial 2D matcher. We observe a drop in accuracies with increased time lapse, most with whole-face 3D matching followed by 2D matching and the 3D ensemble of regions approach. Finally, we determine whether the difference in match quality arising with an increased time lapse is statistically significant.

Ishan Manjani

Papers

Detecting Silicone Mask-Based Presentation Attack via Deep Dictionary Learning

Template aging in 3D and 2D face recognition