期刊
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
卷 16, 期 -, 页码 2477-2492出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIFS.2021.3055018
关键词
Cameras; Feature extraction; Faces; Face recognition; Data mining; Databases; Training; Face anti-spoofing; camera invariant; deep learning; generalization capability
资金
- Science, Technology, and Innovation Commission of Shenzhen Municipality [JCYJ20180307123934031]
- National Natural Science Foundation of China [62022002]
- Hong Kong Research Grants Council, Early Career Scheme (RGC ECS) [21211018]
- General Research Fund (GRF) [11203220]
A framework was proposed to eliminate the domain gap caused by camera models in learning based face anti-spoofing, leading to a more generalized detection model. The framework consists of two branches for feature learning and information fusion, demonstrating better classification results.
There has been an increasing consensus in learning based face anti-spoofing that the divergence in terms of camera models is causing a large domain gap in real application scenarios. We describe a framework that eliminates the influence of inherent variance from acquisition cameras at the feature level, leading to the generalized face spoofing detection model that could be highly adaptive to different acquisition devices. In particular, the framework is composed of two branches. The first branch aims to learn the camera invariant spoofing features via feature level decomposition in the high frequency domain. Motivated by the fact that the spoofing features exist not only in the high frequency domain, in the second branch the discrimination capability of extracted spoofing features is further boosted from the enhanced image based on the recomposition of the high-frequency and low-frequency information. Finally, the classification results of the two branches are fused together by a weighting strategy. Experiments show that the proposed method can achieve better performance in both intra-dataset and cross-dataset settings, demonstrating the high generalization capability in various application scenarios.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据