Face spoofing detection from single images using micro-texture analysis

By Jukka Määttä, Abdenour Hadid, Matti Pietikäinen. 2011 International Joint Conference on Biometrics (IJCB), 2011

719 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/140c6d2332e7f8552537be622c6b93fb38ba9b22

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. Xiaoming Liu
2. Xiaogang Wang
3. Dacheng Tao
4. Luc Van Gool
5. Xilin Chen
6. Shiguang Shan
7. Yi Yang
8. Sébastien Marcel

In Signal Processing

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

Citations in the corpus

• Spoofing in 2D face recognition with 3D masks and anti-spoofing with Kinect (2013, methodology): “The authors propose to apply an LBP-based method [14] on both color and depth channels and claim 88.”
• Biometric Antispoofing Methods: A Survey in Face Recognition (2014, methodology): “combination of low-level and high-level face component descriptors [146]; a recent trend based on the use of Local Binary Patterns (LBP) to detect photo-attacks [104], [147], which has been successfully combined with other texture descriptors such as Gabor Wavelets and with shape related information”
• Learning One Class Representations for Face Presentation Attack Detection Using Multi-Channel Convolutional Neural Networks (2020, methodology): “Often, features such as color, texture [5], [6], motion [7], and physiological cues [8], [9] and CNN”
• Secure Face Unlock: Spoof Detection on Smartphones (2016, methodology): “This motivated us to conduct experiments to test if MLBP performs better than LBP when detecting for face liveness.”
• Learn Convolutional Neural Network for Face Anti-Spoofing (2014, methodology): “According to the experimental results on the REPLAY-ATTACK database, it outperformed the LBP-based method in [23].”
• Face De-Spoofing: Anti-Spoofing via Noise Modeling (2018, methodology): “Early works apply the hand-crafted feature descriptors, such as LBP [3,4,21], HoG [5,6], SIFT [22] and SURF [23], to project the faces to a low-dimension embedding.”
• Face liveness detection with component dependent descriptor (2013, methodology): “In the most recent, Maatta et al. [16] make use of the micro-textures in the holistic faces.”
• Face anti-spoofing based on color texture analysis (2015, background): “Research on face spoofing detection has mainly been focusing on analyzing gray-scale images [3] [4] [5] and hence discarding the color information which can be useful for discriminating fake faces from genuine ones.”
• Presentation Attack Detection Methods for Face Recognition Systems (2017, methodology): “The most famous and most widely used approach is based on Local Binary Patterns (LBPs) [Maatta et al. 2011].”
• Deep Representations for Iris, Face, and Fingerprint Spoofing Detection (2014, methodology): “Kose et al. [60] demonstrated that a face verification system is vulnerable to mask-based attacks and, in another work, Kose et al. [61] evaluated the anti-spoofing method proposed by M¨a¨att¨a et al. [52] (originally proposed to detect photo-based spoofing attacks).”
• Motion-based counter-measures to photo attacks in face recognition (2014, background): “More recently, in [12], Määttä and others show that Local Binary Patterns (LBP) can also be used for spoofing detection achieving near perfect scoring on the PRINT-ATTACK database [13].”
• Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision (2018, methodology): “Researchers start the texture-based anti-spoofing approaches by feeding handcrafted features to binary classifiers [13,18, 19,27,33,34,38,49].”
• Face Anti-Spoofing: Model Matters, so Does Data (2019, methodology): “For example, many hand-crafted features have been studied in previous works, including LBP [29, 12, 13], HOG [21, 43], DOG [37, 33], SIFT [32], and SURF [9].”
• Presentation Attack Detection for Face Recognition Using Light Field Camera (2015, methodology): “The proposed method I (c) indicates the performance improvement of over 2% when compared with the second best method based on LBP variant [8] and [5].”
• Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing (2020, methodology): “One is training on the CASIA-MFSD and testing on Replay-Attack, which we name protocol CR; the other is training on the Replay-Attack and testing on CASIA-7 50.2 47.9 LBP-1 [15] 55.9 57.6 LBP-TOP [15] 49.7 60.6 Motion-Mag [3] 50.1 47.0 Spectral cubes [44] 34.4 50.0 CNN [51] 48.5 45.5 LBP-2 [7] 47.0 ”