Context based face anti-spoofing

By Jukka Komulainen, Abdenour Hadid, Matti Pietikäinen. International Conference on Biometrics: Theory, Applications and Systems, 2013

330 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/5010a56c9bb6b77007a7ed8fe4dbf4e74c34aad4

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

In Signal Processing

Citations in the corpus

Face Anti-spoofing: Visual Approach (2014, background): “[45] considered scene information for detecting whether someone is presenting a fake face on a display medium in front of the camera by checking if the boundaries of the spoofing medium, e.”
Biometric Antispoofing Methods: A Survey in Face Recognition (2014, background): “, paper or tablet) [128]; or pixel difference evaluation between two consecutive pictures taken with different focus values [150] (although this last method requires two different face images, we include it in the static category as it does not use any temporal information).”
Face anti-spoofing using patch and depth-based CNNs (2017, methodology): “Common local features that have been used in prior work include LBP [30, 15, 16], HOG [25, 47], DoG [42, 36], SIFT [34] and SURF [9].”
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].”
Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning (2020, methodology): “After that, various hand-crafted features such as LBP [32], LPQ [6], SURF [6], HoG [24], SIFT [37] and IDA [48], have been utilized with traditional classiﬁers, e.g., SVM [43] and LDA [13], for live vs. spoof face classiﬁcation.”
Deep Tree Learning for Zero-Shot Face Anti-Spoofing (2019, background): “, LBP [7,16,17,35], HoG [25,47], SIFT [38] and SURF [8], with traditional classifiers, e.”
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].”
Learn Convolutional Neural Network for Face Anti-Spoofing (2014, background): “Recently, researchers are devoted to come up with more generalized and discriminative features for face antispoofing, such as LBP [23][35], HOG [20][35], LBP-TOP [11], DoG [30] [27], etc.”
Face Spoof Detection With Image Distortion Analysis (2015, methodology): “(iv) Methods based on other cues: Face spoof countermeasures using cues derived from sources other than 2D intensity image, such as 3D depth [19], IR image [6], spoofing context [20], and voice [21] have also been proposed.”
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.”
CASIA-SURF: A Large-Scale Multi-Modal Benchmark for Face Anti-Spoofing (2019, background): “Some works are based on contextual [41], [42] and moving [43]–[45] information.”
Presentation Attack Detection Methods for Face Recognition Systems (2017, background): “…face image [Kim et al. 2015b; Libin 2014], one that combines time-frequency information with a texture descriptor [Raghavendra and Busch 2014a; Raghavendra et al. 2017], one that combines shape and texture [M ¨ a ¨ attä et al. 2012], or the use of context information [Komulainen et al. 2013a].”
Searching Central Difference Convolutional Networks for Face Anti-Spoofing (2020, methodology): “Several classical lo-cal descriptors such as LBP [7, 15], SIFT [44], SURF [9], HOG [29] and DoG [45] are utilized to extract frame level features while video level methods usually capture dynamic clues like dynamic texture [28], micro-motion [53] and eye blinking [41].”
Face Anti-Spoofing with Human Material Perception (2020, methodology): “Several classical lo-cal descriptors such as LBP [2,4], SIFT [7], SURF [19], HOG [5] and DoG [6] are utilized to extract frame level features while video level methods usually capture dynamic cues like dynamic texture [20], micro–motion [21] and eye blinking [22].”
Deep Spatial Gradient and Temporal Depth Learning for Face Anti-Spoofing (2020, methodology): “The early works usually rely on hand-crafted features, such as LBP [14, 15, 37], SIFT [42], SURF [9], HoG [28, 52], DoG [43, 48], and traditional classifiers, such as SVM and Random Forests.”