Secure Face Unlock: Spoof Detection on Smartphones

By Keyurkumar Patel, Hu Han, Anil K. Jain. IEEE Transactions on Information Forensics and Security, 2016

489 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Signal Processing

View Paper: https://www.semanticscholar.org/paper/e6718d1239b348ff5af0f034a113f93cbcadb550

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. Luc Van Gool
4. Dacheng Tao
5. Xilin Chen
6. Chen Change Loy
7. Yu Qiao
8. Yi Yang

In Information Systems

1. Xiaoming Liu
2. Yaojie Liu
3. Amin Jourabloo
4. Shiguang Shan
5. Xilin Chen
6. Guoying Zhao
7. Zitong Yu
8. Xiaobai Li

In Signal Processing

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

Citations in the corpus

• CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations (2020, background): “Second is the single-modal dataset, such as Replay Attack [5], CASIA-MFSD [39], MSU-MFSD [34], MSU-USSA [29] and HKBU-MARS V2 [21].”
• Deep Learning in the Wild (2018, background): “This might be facilitated by the available datasets: to develop and evaluate anti-spoofing tools, amongst others CASIA [66], MSU-USSA [43], and the Replay Attack Database [12] exist.”
• Generalized Out-of-Distribution Detection: A Survey (2021, unknown): “ample applications include adversarial defense [37], forgery recognition of biometrics and artworks [38], [39], [40], [41],”
• Deep Tree Learning for Zero-Shot Face Anti-Spoofing (2019, methodology): “Different methods are proposed to handle replay and print attacks, based on either handcrafted features [7, 35, 38] or CNN-based fea.”
• Face Anti-Spoofing with Human Material Perception (2020, methodology): “Several classical local 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.”
• Single-Side Domain Generalization for Face Anti-Spoofing (2020, background): “Many prior works adopt hand-craft descriptors for face anti-spoofing, such as LBP [9, 26], HOG [14], SURF [5], SIFT [29], etc.”
• 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): “This problem remains open, although some works [43], [44] adopt transfer learning to train a CNN model from ImageNet [17].”
• 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].”
• Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision (2018, methodology): “More recent MSU-USSA [38] and OULU databases [14] have subjects with fewer variations in poses, illuminations, expressions (PIE).”
• Face anti-spoofing using patch and depth-based CNNs (2017, methodology): “We also test our method on the MSU-USSA database.”
• 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.”
• 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].”