Improving Cross-Dataset Performance of Face Presentation Attack Detection Systems Using Face Recognition Datasets
Amir Mohammadi, Sushil Bhattacharjee, Sébastien Marcel
Abstract
Presentation attack detection (PAD) is now considered critically important for any face-recognition (FR) based access-control system. Current deep-learning based PAD systems show excellent performance when they are tested in intra-dataset scenarios. Under cross-dataset evaluation the performance of these PAD systems drops significantly. This lack of generalization is attributed to domain-shift. Here, we propose a novel PAD method that leverages the large variability present in FR datasets to induce invariance to factors that cause domain-shift. Evaluation of the proposed method on several datasets, including datasets collected using mobile devices, shows performance improvements in cross-dataset evaluations. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>
BibTeX
@inproceedings{icassp2020_improvingcrossda,
title = {Improving Cross-Dataset Performance of Face Presentation Attack Detection Systems Using Face Recognition Datasets},
author = {Amir Mohammadi and Sushil Bhattacharjee and Sébastien Marcel},
booktitle = {ICASSP 2020},
year = {2020}
}