Deep Learning for Face Anti-Spoofing : An End-to-End Approach
Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 32_Refereed conference paper (with ISBN/ISSN) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Title of host publication | 2017 Signal Processing |
Subtitle of host publication | Algorithms, Architectures, Arrangements, and Applications (SPA) |
Publisher | IEEE |
Pages | 195-200 |
ISBN (Electronic) | 978-83-62065-30-1 |
Publication status | Published - Dec 2017 |
Publication series
Name | Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA) |
---|---|
ISSN (Print) | 2326-0262 |
ISSN (Electronic) | 2326-0319 |
Conference
Title | Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA 2017) |
---|---|
Location | Poznan University of Technology |
Place | Poland |
City | Poznan |
Period | 20 - 22 September 2017 |
Link(s)
Abstract
The importance of face anti-spoofing algorithms in biometric authentication systems is becoming indispensable. Recently, the success of Convolution Neural Networks (CNN) in key application areas of computer vision has encouraged its use in face biometrics for face anti-spoofing and verification applications. However, small training data has restricted the use of deep CNN architectures for face anti-spoofing applications. In this paper, we develop an end-to-end CNN architecture for face anti-spoofing application. i.e. a deep CNN architecture which directly map the raw input face images to the corresponding output classes. Additionally, an efficient training strategy has been proposed to enable the use of deeper CNN structures for face anti-spoofing applications and to enable the growth of training data in autonomous way. For training a CNN architecture, we propose a 50RS-30SeC-1E (50 Random Samples-30 Sub-epochs Count-1Epoch) training strategy. The training data is randomly sampled during each forward-pass through the CNN architecture and 30 such passes counts for 1 complete epoch. An 11-layer VGG network with 2 derived VGG-11 networks have been trained for face anti-spoofing on CASIA-FASD dataset. Experimental results show significant improvement on various face-spoofing scenarios. A 3% improvement over state of the art approaches has been reported for Overall Test (OT) while achieving a lowest EER of 5%.
Citation Format(s)
Deep Learning for Face Anti-Spoofing : An End-to-End Approach. / Rehman, Yasar Abbas Ur; Po, Lai Man; Liu, Mengyang.
2017 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA). IEEE, 2017. p. 195-200 8166863 (Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)).Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 32_Refereed conference paper (with ISBN/ISSN) › peer-review