Keyframe and GAN-Based Data Augmentation for Face Anti-Spoofing

Jarred Orfao, Dustin van der Haar

2023

Abstract

As technology improves, criminals, find new ways to gain unauthorised access. Accordingly, face spoofing has become more prevalent in face recognition systems, requiring adequate presentation attack detection. Traditional face anti-spoofing methods used human-engineered features, and due to their limited representation capacity, these features created a gap which deep learning has filled in recent years. However, these deep learning methods still need further improvements, especially in the wild settings. In this work, we use generative models as a data augmentation strategy to improve the face anti-spoofing performance of a vision transformer. Moreover, we propose an unsupervised keyframe selection process to generate better candidate samples for more efficient training. Experiments show that our augmentation approaches improve the baseline performance of the CASIA-FASD and achieve state-of-the-art performance on the Spoof in the Wild database for protocols 2 and 3.

Paper Citation

in Harvard Style

Orfao J. and van der Haar D. (2023). Keyframe and GAN-Based Data Augmentation for Face Anti-Spoofing. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 629-640. DOI: 10.5220/0011648400003411

in Bibtex Style

@conference{icpram23,
author={Jarred Orfao and Dustin van der Haar},
title={Keyframe and GAN-Based Data Augmentation for Face Anti-Spoofing},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={629-640},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011648400003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Keyframe and GAN-Based Data Augmentation for Face Anti-Spoofing
SN - 978-989-758-626-2
AU - Orfao J.
AU - van der Haar D.
PY - 2023
SP - 629
EP - 640
DO - 10.5220/0011648400003411