An original face anti-spoofing approach using partial convolutional neural network

Li, Lei; Feng, Xiaoyi; Boulkenafet, Zinelabidine; Xia, Zhaoqiang; Li, Mingming; Hadid, Abdenour

doi:10.1109/ipta.2016.7821013

Cited by 250 publications

(144 citation statements)

References 21 publications

Supporting

Mentioning

142

Contrasting

Unclassified

Order By: Relevance

“…Apart from that, some feature descriptors or indexes are computed to describe the clarity of facial texture [9,8,21]. More recently, many attempts of using CNN-based features in face PAD [22,23,24]. While these methods are effective to typical 2D paper or replayed attacks, they become vulnerable when attackers wear a lifelike face mask.…”

Section: Methods For 2d Face Padmentioning

confidence: 99%

3D face mask presentation attack detection based on intrinsic image analysis

Xia

Jiang

et al. 2020

IET biom.

Self Cite

View full text Add to dashboard Cite

Face presentation attacks have become a major threat to face recognition systems and many countermeasures have been proposed in the past decade. However, most of them are devoted to 2D face presentation attacks, rather than 3D face masks. Unlike the real face, the 3D face mask is usually made of resin materials and has a smooth surface, resulting in reflectance differences. So, we propose a novel detection method for 3D face mask presentation attack by modeling reflectance differences based on intrinsic image analysis. In the proposed method, the face image is first processed with intrinsic image decomposition to compute its reflectance image. Then, the intensity distribution histograms are extracted from three orthogonal planes to represent the intensity differences of reflectance images between the real face and 3D face mask. After that, the 1D convolutional network is further used to capture the information for describing different materials or surfaces react differently to changes in illumination. Extensive experiments on the 3DMAD database demonstrate the effectiveness of our proposed method in distinguishing a face mask from the real one and show that the detection performance outperforms other state-of-the-art methods.

show abstract

Section: Methods For 2d Face Padmentioning

confidence: 99%

3D face mask presentation attack detection based on intrinsic image analysis

Xia

Jiang

et al. 2020

IET biom.

Self Cite

View full text Add to dashboard Cite

show abstract

“…1) Using RGB single frame with binary supervision [7,8]: Most approaches just adopt the final fully-connected layer to distinguish the real and fake faces. While Li et al [7] proposed a way to link the deep partial features (from CNN) and Principle Component Analysis (PCA) to reduce the dimension, and lastly they used SVM to distinguish real and fake faces. Patel et al [8] applied the action features (such as eye blinking) to enhance the state of the art.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, deep learning techniques are widely used to extract deep features [6,7,8], which have richer semantical information compared to traditional handcrafted features. Hence utilizing the deep learning for face PAD has been widely used recently.…”

Section: Introductionmentioning

confidence: 99%

FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-Spoofing

Zhang

Zou²,

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Face Anti-spoofing gains increased attentions recently in both academic and industrial fields. With the emergence of various CNN based solutions, the multi-modal(RGB, depth and IR) methods based CNN showed better performance than single modal classifiers. However, there is a need for improving the performance and reducing the complexity. Therefore, an extreme light network architecture(FeatherNet A/B) is proposed with a streaming module which fixes the weakness of Global Average Pooling and uses less parameters. Our single FeatherNet trained by depth image only, provides a higher baseline with 0.00168 ACER, 0.35M parameters and 83M FLOPS. Furthermore, a novel fusion procedure with "ensemble + cascade" structure is presented to satisfy the performance preferred use cases. Meanwhile, the MMFD dataset is collected to provide more attacks and diversity to gain better generalization. We use the fusion method in the Face Anti-spoofing Attack Detection Challenge@CVPR2019 and got the result of 0.0013(ACER), 0.999(TPR@FPR=10e-2), 0.998(TPR@FPR=10e-3) and 0.9814(TPR@FPR=10e-4).

show abstract

“…Most of the texture-based methods treat face antispoofing as a binary classification problem. In [19,24], it uses the CaffeNet or VGG model pre-trained on ImageNet as initialization and then fine-tunes it on face-spoofing data. The SVM is finally applied for face spoofing detection.…”

Section: Related Workmentioning

confidence: 99%

“…Deep learning based methods mainly consist of two types. The first one treats PA as a binary classification or pseudo-depth regression problem [19,37,1]. The other one tries to utilize temporal information of the video, such as applying the RNN-based structure [35,20].…”

Section: Introductionmentioning

confidence: 99%

Improving Face Anti-Spoofing by 3D Virtual Synthesis

Guo

Zhu

Xiao

et al. 2019

2019 International Conference on Biometrics (ICB)

View full text Add to dashboard Cite

Face anti-spoofing is crucial for the security of face recognition systems. Learning based methods especially deep learning based methods need large-scale training samples to reduce overfitting. However, acquiring spoof data is very expensive since the live faces should be reprinted and re-captured in many views. In this paper, we present a method to synthesize virtual spoof data in 3D space to alleviate this problem. Specifically, we consider a printed photo as a flat surface and mesh it into a 3D object, which is then randomly bent and rotated in 3D space. Afterward, the transformed 3D photo is rendered through perspective projection as a virtual sample. The synthetic virtual samples can significantly boost the anti-spoofing performance when combined with a proposed data balancing strategy. Our promising results open up new possibilities for advancing face anti-spoofing using cheap and largescale synthetic data.

show abstract

An original face anti-spoofing approach using partial convolutional neural network

Cited by 250 publications

References 21 publications

3D face mask presentation attack detection based on intrinsic image analysis

3D face mask presentation attack detection based on intrinsic image analysis

FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-Spoofing

Improving Face Anti-Spoofing by 3D Virtual Synthesis

Contact Info

Product

Resources

About