Face Anti-spoofing based on Deep Stack Generalization Networks

Xin Ning, Weijun Li, Meili Wei, Linjun Sun, Xiaoli Dong

Abstract

Thanks for the recent development of Convolutional Neural Networks (CNNs), the performance of face anti-spoofing methods has been improved by extracting more distinguishing features between genuine and fake faces than the hand-crafted texture features. As known, the way of fraud is diverse, thus the fake class has large intra-class variations, so training as a binary classification problem is hard to learn the distinguishing features. In this work, our contribution is a novel model fusion approach for face anti-spoofing, which can reduce the intra-class variations. According to the type of fraud, we firstly train different models for face anti-spoofing problem by CNN, thus the intra-class variations of fake class has reduced during training each model. Distinguishing features can be learned more easily. Then the stacked generalized method is used for combining the lower models to achieve better predictive accuracy. For perfecting the generalized accuracy, the stacked generalized approach changes the weight of each model's prediction, so that the model after fusion can predict precisely whether the face image is fake or genuine. Meanwhile, the experimental results indicate our method can obtain excellent results compared to the state-of-the-art methods.

References

Download


Paper Citation


in Harvard Style

Ning X., Li W., Wei M., Sun L. and Dong X. (2018). Face Anti-spoofing based on Deep Stack Generalization Networks.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 317-323. DOI: 10.5220/0006568103170323


in Bibtex Style

@conference{icpram18,
author={Xin Ning and Weijun Li and Meili Wei and Linjun Sun and Xiaoli Dong},
title={Face Anti-spoofing based on Deep Stack Generalization Networks},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={317-323},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006568103170323},
isbn={978-989-758-276-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Face Anti-spoofing based on Deep Stack Generalization Networks
SN - 978-989-758-276-9
AU - Ning X.
AU - Li W.
AU - Wei M.
AU - Sun L.
AU - Dong X.
PY - 2018
SP - 317
EP - 323
DO - 10.5220/0006568103170323