Learning Generalized Deep Feature Representation for Face Anti-Spoofing

Li, Haoliang; He, Peisong; Wang, Shiqi; Rocha, Anderson; Jiang, Xinghao; Kot, Alex C.

doi:10.1109/tifs.2018.2825949

Cited by 163 publications

(73 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In most of the cases, texture features extracted from color channels performed the best. Li et al [29] proposed a 3D CNN architecture, which utilizes both spatial and temporal nature of videos. The network was first trained after data augmentation with a cross-entropy loss, and then with a specially designed generalization loss, which acts as a regularization factor.…”

Section: B Cnn Based Approaches For Face Padmentioning

confidence: 99%

Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network

George

Mostaani

Geissenbuhler

et al. 2020

IEEE Trans.Inform.Forensic Secur.

188

186

View full text Add to dashboard Cite

Face recognition is a mainstream biometric authentication method. However, vulnerability to presentation attacks (a.k.a spoofing) limits its usability in unsupervised applications. Even though there are many methods available for tackling presentation attacks (PA), most of them fail to detect sophisticated attacks such as silicone masks. As the quality of presentation attack instruments improves over time, achieving reliable PA detection with visual spectra alone remains very challenging. We argue that analysis in multiple channels might help to address this issue. In this context, we propose a multi-channel Convolutional Neural Network based approach for presentation attack detection (PAD). We also introduce the new Wide Multi-Channel presentation Attack (WMCA) database for face PAD which contains a wide variety of 2D and 3D presentation attacks for both impersonation and obfuscation attacks. Data from different channels such as color, depth, near-infrared and thermal are available to advance the research in face PAD. The proposed method was compared with feature-based approaches and found to outperform the baselines achieving an ACER of 0.3% on the introduced dataset. The database and the software to reproduce the results are made available publicly.

show abstract

Section: B Cnn Based Approaches For Face Padmentioning

confidence: 99%

Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network

George

Mostaani

Geissenbuhler

et al. 2020

IEEE Trans.Inform.Forensic Secur.

188

186

View full text Add to dashboard Cite

show abstract

“…where l(:, :) is a loss function, N is the number of samples, y is the one-hot encoding label vector. Backbone Deep Networks CNNs have been successfully applied to face anti-spoofing [25], [26], [47]- [49]. Most existing works trained their CNN models from scratch using the existing face anti-spoofing databases, which are quite small and captured in unitary environments.…”

Section: B Two Stream Convolutional Neural Network (Tscnn)mentioning

confidence: 99%

Attention-Based Two-Stream Convolutional Networks for Face Spoofing Detection

Chen

Lei

et al. 2020

IEEE Trans.Inform.Forensic Secur.

137

View full text Add to dashboard Cite

“…Generalization has been specifically addressed with no success from different perspectives: i) applying domain adaptation techniques [17]; ii) reformulating the problem as an anomaly detection [21] scenario; iii) learning generalized deep features [13,16,17]; or even iv) using generative models [13]. Besides, there is still a lack of unified benchmark and representative datasets, that might mitigate the constant improvement of Presentation Attack Instruments (PAIs) with more sophisticated strategies (e.g.…”

Section: Generalized Presentation Attack Detectionmentioning

confidence: 99%

Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal

Costa‐Pazo

Jiménez‐Cabello

Vázquez-Fernández

et al. 2019

2019 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

Over the past few years, Presentation Attack Detection (PAD) has become a fundamental part of facial recognition systems. Although much effort has been devoted to anti-spoofing research, generalization in real scenarios remains a challenge. In this paper we present a new opensource evaluation framework to study the generalization capacity of face PAD methods, coined here as face-GPAD. This framework facilitates the creation of new protocols focused on the generalization problem establishing fair procedures of evaluation and comparison between PAD solutions. We also introduce a large aggregated and categorized dataset to address the problem of incompatibility between publicly available datasets. Finally, we propose a benchmark adding two novel evaluation protocols: one for measuring the effect introduced by the variations in face resolution, and the second for evaluating the influence of adversarial operating conditions.

show abstract

Learning Generalized Deep Feature Representation for Face Anti-Spoofing

Cited by 163 publications

References 58 publications

Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network

Biometric Face Presentation Attack Detection With Multi-Channel Convolutional Neural Network

Attention-Based Two-Stream Convolutional Networks for Face Spoofing Detection

Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal

Contact Info

Product

Resources

About