Face De-Spoofing: Anti-Spoofing via Noise Modeling

By Amin Jourabloo, Yaojie Liu, Xiaoming Liu. 2018

259 citations recorded by the source corpus.

Many prior face anti-spoofing works develop discriminative models for recognizing the subtle differences between live and spoof faces. Those approaches often regard the image as an indivisible unit, and process it holistically, without explicit modeling of the spoofing process. In this work, motivated by the noise modeling and denoising algorithms, we identify a new problem of face de-spoofing, for the purpose of anti-spoofing: inversely decomposing a spoof face into a spoof noise and a live face, and then utilizing the spoof noise for classification. A CNN architecture with proper constraints and supervisions is proposed to overcome the problem of having no ground truth for the decomposition. We evaluate the proposed method on multiple face anti-spoofing databases. The results show promising improvements due to our spoof noise modeling. Moreover, the estimated spoof noise provides a visualization which helps to understand the added spoof noise by each spoof medium.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xiaogang Wang
2. Xiaoming Liu
3. Luc Van Gool
4. Dacheng Tao
5. Xilin Chen
6. Chen Change Loy
7. Yu Qiao
8. S. Li

In Signal Processing

1. Sébastien Marcel
2. Xiaoming Liu
3. Yaojie Liu
4. Amin Jourabloo
5. Xilin Chen
6. Hu Han
7. Shiguang Shan
8. Zitong Yu

Citations in the corpus

• Detection and Continual Learning of Novel Face Presentation Attacks (2021, background): “Similar to most sub-fields in computer vision, advances in deep learning, which is inspired by the nervous system [17], have led to significant face PAD improvements on benchmark datasets using convolutional neural network-based (CNN) end-to-end representation learning and classification [1, 7, 12, ”
• On the Detection of Digital Face Manipulation (2019, background): “i) Physical spoofing attacks can be as simple as face printed on a paper, replaying image/video on a phone, or as complicated as a 3D mask [8, 24, 34, 35].”
• Deep Tree Learning for Zero-Shot Face Anti-Spoofing (2019, methodology): “Secondly, unlike generic objects with rich semantic embedding, there is no explicit well-defined semantic embedding for spoof patterns [20].”
• Deep Face Recognition: A Survey (2018, background): “[277] proposed to inversely decompose a spoof face into the live face and the spoof noise pattern.”
• Single-Side Domain Generalization for Face Anti-Spoofing (2020, methodology): “And the face de-spoofing method [16] inversely decomposes a spoof face into a live face and a spoof noise for classification.”
• Deep Anomaly Detection for Generalized Face Anti-Spoofing (2019, background): “Face-PAD approaches can be categorized regarding the following standpoints: i) from the required user interaction as active [19] or passive [20, 33] methods; ii) from the hardware used for data acquisition as rgb-only [14, 25, 33], rgb-infrared-depth [3, 37] or additional sensors [30] approaches; ii”
• Face Anti-Spoofing with Human Material Perception (2020, methodology): “Some frame-level CNN methods [23,24,25,26,11,27] are supervised by binary scalars or pixel-wise binary maps.”
• CASIA-SURF: A Large-Scale Multi-Modal Benchmark for Face Anti-Spoofing (2019, methodology): “[16] introduce a new perspective for solving the face anti-spoofing by inversely decomposing a spoof face into the live face and the spoof noise pattern.”
• CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations (2020, background): “[15] solved the problem of face anti-spoofing by decomposing a spoof photo into a Live photo and a Spoof noise pattern.”
• Multispectral Biometrics System Framework: Application to Presentation Attack Detection (2020, methodology): “The suggested network architecture was inspired by the supervision channel approach in [70], [71] and its first part (identical to [67]) is equivalent to a patch-based architecture when the stride is 1, albeit with increased computational efficiency and reduced memory overhead.”
• Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning (2020, methodology): “[21] inversely decomposed a spoof face into a live face and a noise of spoof, and then utilized the spoof noise for PAD.”
• Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing (2020, background): “More recently, [26] attempts to learn spoof noise and depth for generalized face anti-spoofing.”
• Face Anti-Spoofing: Model Matters, so Does Data (2019, methodology): “The performance of our model is comparable with the latest results of FaceDs [18], while slightly worse than those of Auxiliary [26].”