Improving Face Anti-Spoofing by 3D Virtual Synthesis

Guo, Jianzhu; Zhu, Xiangyu; Xiao, Jinchuan; Lei, Zhen; Wan, Genxun; Li, Stan Z.

doi:10.1109/icb45273.2019.8987415

Cited by 28 publications

(9 citation statements)

References 35 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, most of existing face recognition systems are easily to be spoofed through presentation attacks (PAs) ranging from printing a face on paper (print attack) to replaying a face on a digital device (replay attack) or bringing a 3D-mask (3D-mask attack). Therefore, not only the research community but also the industry has recognized face anti-spoofing [18,19,4,33,39,11,23,55,1,29,12,49,45,54,21] as a critical role in securing the face recognition system. In the past few years, both traditional methods [14,42,9] and CNN-based methods [35,38,20,24,46] have shown effectiveness in discriminating between the living and spoofing face.…”

Section: Introductionmentioning

confidence: 99%

Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing

Wang¹,

Zhao

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

179

View full text Add to dashboard Cite

Face anti-spoofing is critical to the security of face recognition systems. Depth supervised learning has been proven as one of the most effective methods for face antispoofing. Despite the great success, most previous works still formulate the problem as a single-frame multi-task one by simply augmenting the loss with depth, while neglecting the detailed fine-grained information and the interplay between facial depths and moving patterns. In contrast, we design a new approach to detect presentation attacks from multiple frames based on two insights: 1) detailed discriminative clues (e.g., spatial gradient magnitude) between living and spoofing face may be discarded through stacked vanilla convolutions, and 2) the dynamics of 3D moving faces provide important clues in detecting the spoofing faces. The proposed method is able to capture discriminative details via Residual Spatial Gradient Block (RSGB) and encode spatio-temporal information from Spatio-Temporal Propagation Module (STPM) efficiently. Moreover, a novel Contrastive Depth Loss is presented for more accurate depth supervision. To assess the efficacy of our method, we also collect a Double-modal Anti-spoofing Dataset (DMAD) which provides actual depth for each sample. The experiments demonstrate that the proposed approach achieves state-of-the-art results on five benchmark datasets including OULU-NPU, SiW, CASIA-MFSD, Replay-Attack, and the new DMAD. Codes will be available at https://github.com/clks-wzz/ FAS-SGTD.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing

Wang¹,

Zhao

et al. 2020

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

179

View full text Add to dashboard Cite

show abstract

“…Methods based on motion analysis attempt to detect vital movements such as eye blinking or movements of the lips and head. Texture-based methods aim to exploit the distinctions in patterns between live and fake faces [20]. The use of video footage by the attacker is more realistic compared to using photos and is more difficult to be detected by systems that control vital characteristics such as eye movements to identify attempted attacks.…”

Section: "Anti-spoofing" Methods In Biometric Facial Recognition Systemsmentioning

confidence: 99%

Anti-spoofing methods in face recognition

Bezas

Filippidou²

2023

ijcs

View full text Add to dashboard Cite

Biometric data are personal data that result from specialized processing techniques and are associated with physical, biological, or behavioral characteristics of a natural person that allow for or confirm their unquestionable identification. These characteristics or identifiers are permanent and unique. This paper refers to the biometric characteristics used by systems, their mode of operation, and the categories they are distinguished in. The types of attacks that they may be subjected to are then analyzed, along with the anti-spoofing methods proposed in some studies specifically for systems that use the face as a biometric feature. Finally, numerical data is presented regarding the scientific interest that the topic of anti-spoofing methods in biometric systems has shown in the last decade.

show abstract

“…Among these cue-based methods, liveness cues are not suitable for frame-based PAD methods. Therefore, texture and 3D geometry cue-based methods [17][18][19][20] are more popular for detecting liveness from a frame. Depth or pseudo-depth signals are the most popular signals for 3D geometry cue-based methods to distinguish presentation attacks from real attempts.…”

Section: Related Workmentioning

confidence: 99%

Deep patch‐wise supervision for presentation attack detection

2022

View full text Add to dashboard Cite

Face recognition systems have been widely deployed in various applications, such as online banking and mobile payment. However, these systems are vulnerable to face presentation attacks, which are created by people who obtain biometric data covertly from a person or through hacked systems. In order to detect these attacks, convolutional neural networks (CNN)‐based systems have gained significant popularity recently. CNN‐based systems perform very well on intra‐data set experiments, yet they fail to generalise to the data sets that they have not been trained on. This indicates that they tend to memorise data set‐specific spoof traces. To mitigate this problem, the authors propose a Deep Patch‐wise Supervision Presentation Attack Detection (DPS‐PAD) model approach that combines pixel‐wise binary supervision with patch‐based CNN. The authors’ experiments show that the proposed patch‐based method forces the model not to memorise the background information or data set‐specific traces. The authors extensively tested the proposed method on widely used PAD data sets—Replay‐Mobile and OULU‐NPU—and on a real‐world data set that has been collected for real‐world PAD use cases. The proposed approach is found to be superior on challenging experimental setups. Namely, it achieves higher performance on OULU‐NPU protocol 3, 4 and on inter‐data set real‐world experiments.

show abstract

Improving Face Anti-Spoofing by 3D Virtual Synthesis

Cited by 28 publications

References 35 publications

Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing

Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing

Anti-spoofing methods in face recognition

Deep patch‐wise supervision for presentation attack detection

Contact Info

Product

Resources

About