CASIA-SURF: A Large-Scale Multi-Modal Benchmark for Face Anti-Spoofing

@article{Zhang2020CASIASURFAL,
  title={CASIA-SURF: A Large-Scale Multi-Modal Benchmark for Face Anti-Spoofing},
  author={Shifeng Zhang and Ajian Liu and Jun Wan and Yanyan Liang and Guo-qing Guo and Sergio Escalera and Hugo Jair Escalante and S. Li},
  journal={IEEE Transactions on Biometrics, Behavior, and Identity Science},
  year={2020},
  volume={2},
  pages={182-193}
}
  • Shifeng Zhang, Ajian Liu, +5 authors S. Li
  • Published 28 August 2019
  • Computer Science
  • IEEE Transactions on Biometrics, Behavior, and Identity Science
Face anti-spoofing is essential to prevent face recognition systems from a security breach. [...] Key Method Specifically, it consists of $1,000$ subjects with $21,000$ videos and each sample has $3$ modalities (i.e., RGB, Depth and IR). We also provide comprehensive evaluation metrics, diverse evaluation protocols, training/validation/testing subsets and a measurement tool, developing a new benchmark for face anti-spoofing.Expand
Cross-ethnicity Face Anti-spoofing Recognition Challenge: A Review
TLDR
An overview of the Chalearn Face Anti-spoofing Attack Detection Challenge, including its design, evaluation protocol and a summary of results is presented, which analyzed the top ranked solutions and drew conclusions derived from the competition.
CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing
TLDR
This work introduces the largest CASIA-SURF Cross-ethnicity Face Anti-spoofing (CeFA) dataset, and proposes a novel multi-modal fusion method as a strong baseline to alleviate the ethnic bias.
Static and Dynamic Fusion for Multi-modal Cross-ethnicity Face Anti-spoofing
TLDR
This work proposes a static-dynamic fusion mechanism for multi-modal face anti-spoofing, inspired by motion divergences between real and fake faces, and develops a partially shared fusion method to learn complementary information from multiple modalities.
PipeNet: Selective Modal Pipeline of Fusion Network for Multi-Modal Face Anti-Spoofing
TLDR
This paper proposes a novel pipeline-based multi-stream CNN architecture called PipeNet for multimodal face anti-spoofing, designed to enable a customized pipeline for each data modality to take full advantage of multi-modal data.
Deep Learning for Face Anti-Spoofing: A Survey
TLDR
This paper presents the first comprehensive review of recent advances in deep learning based FAS, and collects and analyzes the latest methods specially designed for domain generalization and open-set FAS.
Revisiting Pixel-Wise Supervision for Face Anti-Spoofing
TLDR
A novel pyramid supervision is proposed, which guides deep models to learn both local details and global semantics from multi-scale spatial context in face anti-spoofing, to improve the performance beyond existing pixel-wise supervision frameworks and enhance the model’s interpretability.
Face Anti-Spoofing via Adversarial Cross-Modality Translation
TLDR
This work proposes a novel Cross-modal Auxiliary (CMA) framework for the VIS-based FAS task, which aims to close the visible gap between different modalities via a generative model that maps inputs from one modality to another (i.e., NIR).
Shuffled Patch-Wise Supervision for Presentation Attack Detection
TLDR
A new PAD approach is proposed, which combines pixel-wise binary supervision with patch-based CNN and believes that training a CNN with face patches allows the model to distinguish spoofs without learning background or dataset-specific traces.
Attention-Based Face AntiSpoofing of RGB Camera using a Minimal End-2-End Neural Network
TLDR
This paper addresses the anti-spoofing problem by proposing two end-to-end systems of convolutional neural networks based on the EfficientNet B0 network and a very light model of the MobileNet V2, both of which achieve remarkable results on detecting the real and fake images of the face input data.
3DPC-Net: 3D Point Cloud Network for Face Anti-spoofing
TLDR
This work proposes a novel method named 3D Point Cloud Network (3DPC-Net), an encoder-decoder network that can predict the 3DPC maps to discriminate live faces from spoofing ones and is comparative to the state-of-the-art methods.
...
1
2
3
4
...

References

SHOWING 1-10 OF 69 REFERENCES
A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing
TLDR
A large-scale multi-modal dataset, namely CASIA-SURF, is introduced, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and visual modalities and a new multi- modal fusion method is presented, which performs feature re-weighting to select the more informative channel features while suppressing the less useful ones for each modal.
Face Anti-Spoofing: Model Matters, so Does Data
  • Xiao Yang, Wenhan Luo, +5 authors W. Liu
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
TLDR
A data collection solution along with a data synthesis technique to simulate digital medium-based face spoofing attacks, and a novel Spatio-Temporal Anti-Spoof Network (STASN) that can distinguish spoof faces by extracting features from a variety of regions to seek out subtle evidences.
Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
TLDR
This paper argues the importance of auxiliary supervision to guide the learning toward discriminative and generalizable cues, and introduces a new face anti-spoofing database that covers a large range of illumination, subject, and pose variations.
Exploiting temporal and depth information for multi-frame face anti-spoofing
TLDR
A new method to estimate depth information from multiple RGB frames is developed and a depth-supervised architecture which can efficiently encodes spatiotemporal information for presentation attack detection is proposed.
Context based face anti-spoofing
TLDR
This work provides the first investigation in research literature that attempts to detect the presence of spoofing medium in the observed scene and shows that the proposed approach has promising generalization capabilities.
Learn Convolutional Neural Network for Face Anti-Spoofing
TLDR
Instead of designing feature by ourselves, the deep convolutional neural network is relied on to learn features of high discriminative ability in a supervised manner and combined with some data pre-processing, the face anti-spoofing performance improves drastically.
Face De-Spoofing: Anti-Spoofing via Noise Modeling
TLDR
A CNN architecture with proper constraints and supervisions is proposed to overcome the problem of having no ground truth for the decomposition of face de-spoofing, and the results show promising improvements due to the spoof noise modeling.
Spoofing in 2D face recognition with 3D masks and anti-spoofing with Kinect
  • N. Erdogmus, S. Marcel
  • Computer Science
    2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)
  • 2013
TLDR
The 3D Mask Attack Database (3DMAD), the first publicly available 3D spoofing database, recorded with a low-cost depth camera is introduced and it is shown that easily attainable facial masks can pose a serious threat to 2D face recognition systems and LBP is a powerful weapon to eliminate it.
Face liveness detection using variable focusing
TLDR
The experimental result shows that the focus-based approach is a new method that can significantly increase the level of difficulty of spoof attacks, which is a way to improve the security of FR systems.
A 3D Mask Face Anti-Spoofing Database with Real World Variations
TLDR
A new 3D mask anti-spoofing database with more variations to simulate the real world scenario and plans to release the database as an platform to evaluate methods under different variations.
...
1
2
3
4
5
...