A face anti-spoofing method based on optical flow field

Yin, Wenze; Ming, Yue; Lan, Tian

doi:10.1109/icsp.2016.7878043

Cited by 19 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the optical flow feature provides an effective method for extracting motion information from videos (Simonyan and Zisserman, 2014;Sun et al, 2016Sun et al, , 2019. Yin et al (2016) found motion cues of face fraud based on optical flow features. Pinto et al (2015) proposed a feature based on low-level motion features and mid-level visual encoding for face fraud detection.…”

Section: Related Workmentioning

confidence: 99%

Algorithm of face anti-spoofing based on pseudo-negative features generation

Ma,

Lyu,

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

IntroductionDespite advancements in face anti-spoofing technology, attackers continue to pose challenges with their evolving deceptive methods. This is primarily due to the increased complexity of their attacks, coupled with a diversity in presentation modes, acquisition devices, and prosthetic materials. Furthermore, the scarcity of negative sample data exacerbates the situation by causing domain shift issues and impeding robust generalization. Hence, there is a pressing need for more effective cross-domain approaches to bolster the model’s capability to generalize across different scenarios.MethodsThis method improves the effectiveness of face anti-spoofing systems by analyzing pseudo-negative sample features, expanding the training dataset, and boosting cross-domain generalization. By generating pseudo-negative features with a new algorithm and aligning these features with the use of KL divergence loss, we enrich the negative sample dataset, aiding the training of a more robust feature classifier and broadening the range of attacks that the system can defend against.ResultsThrough experiments on four public datasets (MSU-MFSD, OULU-NPU, Replay-Attack, and CASIA-FASD), we assess the model’s performance within and across datasets by controlling variables. Our method delivers positive results in multiple experiments, including those conducted on smaller datasets.DiscussionThrough controlled experiments, we demonstrate the effectiveness of our method. Furthermore, our approach consistently yields favorable results in both intra-dataset and cross-dataset evaluations, thereby highlighting its excellent generalization capabilities. The superior performance on small datasets further underscores our method’s remarkable ability to handle unseen data beyond the training set.

show abstract

Section: Related Workmentioning

confidence: 99%

Algorithm of face anti-spoofing based on pseudo-negative features generation

Ma,

Lyu,

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…A study conducted in [33] shows that the spontaneous blinking of a person provides an intrinsic detection cue to improve live face detection. A dense optical flow scheme is proposed to estimate the motion of two successive frames in [34]. The authors claimed that real and attack videos have different optical flow motion patterns which help to improve the PAD performance.…”

Section: Literature Reviewmentioning

confidence: 99%

Domain Generalization via Ensemble Stacking for Face Presentation Attack Detection

Usman¹,

Beddiar²,

Oussalah³

2023

Preprint

View full text Add to dashboard Cite

Face presentation attack detection (PAD) plays a pivotal role in securing face recognition systems against spoofing attacks. Although great progress has been made in designing face PAD methods, developing a model that can generalize well to an unseen test domain remains a significant challenge. Moreover, due to different types of spoofing attacks, creating a dataset with a sufficient number of samples for training deep neural networks is a laborious task. This work addresses these challenges by creating synthetic data and introducing a deep learning-based unified framework for improving the generalization ability of the face PAD. In particular, synthetic data is generated by proposing a video distillation technique that blends a spatiotemporal warped image with a still image based on alpha compositing. Since the proposed synthetic samples can be generated by increasing different alpha weights, we train multiple classifiers by taking the advantage of a specific type of ensemble learning known as a stacked ensemble, where each such classifier becomes an expert in its own domain but a non-expert to others. Motivated by this, a meta-classifier is employed to learn from these experts collaboratively so that when developing an ensemble, they can leverage complementary information from each other to better tackle or be more useful for an unseen target domain. Experimental results using half total error rates (HTERs) on four PAD databases CASIA-MFSD (6.97%), Replay-Attack (33.49%), MSU-MFSD (4.02%), and OULU-NPU (10.91%)) demonstrate the robustness of the method and open up new possibilities for advancing presentation attack detection using ensemble learning with large-scale synthetic data.

show abstract

“…Besides, optical flow is a useful tool to extract motion in a video [31]- [33]. Yin et al [34] investigated the optical flow to find the motion clues of face spoofing. Pinto et al [35] proposed a face spoofing detection method based on a lowlevel motion feature and a mid-level visual codebook feature.…”

Section: B General Face Spoofing Detectionmentioning

confidence: 99%

A Face Spoofing Detection Method Based on Domain Adaptation and Lossless Size Adaptation

2020

View full text Add to dashboard Cite

In this paper, a face spoofing detection method called the Fully Convolutional Network with Domain Adaptation and Lossless Size Adaptation (FCN-DA-LSA) is proposed. As its name suggests, the FCN-DA-LSA includes a lossless size adaptation preprocessor followed by an FCN based pixel-level classifier embedded with a domain adaptation layer. The FCN local classifier makes full use of the basic properties of face spoof distortion namely ubiquitous and repetitive. The domain adaptation (DA) layer improves generalization across different domains. The lossless size adaptation (LSA) preserves the highfrequent spoof clues caused by the face recapture process. The ablation study shows that both DA and the LSA are necessary for high-accuracy face spoofing detection. The FCN-LSA obtains competitive performance among the state-of-the-art methods. With the help of small-sample external data in the target domain (2/50, 2/50, and 1/20 subjects for CASIA-FASD, Replay-Attack, and OULU-NPU respectively), the FCN-DA-LSA further improves the performance and outperforms the existing methods.

show abstract

A face anti-spoofing method based on optical flow field

Cited by 19 publications

References 11 publications

Algorithm of face anti-spoofing based on pseudo-negative features generation

Algorithm of face anti-spoofing based on pseudo-negative features generation

Domain Generalization via Ensemble Stacking for Face Presentation Attack Detection

A Face Spoofing Detection Method Based on Domain Adaptation and Lossless Size Adaptation

Contact Info

Product

Resources

About