arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.00975cs.CV
收藏

监控人脸防欺骗

Surveillance Face Anti-spoofing

University of Chinese Academy of Sciences (UCAS)(中国科学院大学);Beijing Normal University(北京师范大学);SailYond Technology(赛扬德科技);Universitat de Barcelona (UB)(巴塞罗那大学);Computer Vision Center (CVC)(计算机视觉中心);Aalborg University (AAU)(奥尔堡大学);Westlake University(西湖大学)

Hao Fang, Ajian Liu, Jun Wan, Sergio Escalera, Chenxu Zhao, Xu Zhang, Stan Z. Li, Zhen Lei

摘要:

人脸反欺骗(FAS)对于保护人脸识别系统免受各种物理攻击至关重要。然而,最近的研究通常集中在短距离应用(即,电话解锁)而缺乏对远距离场景的考虑(即,安全检查)。为了推动相关研究并填补这一空白,我们收集了一个大规模的监控高保真面具(SuHiFiMask)数据集,该数据集在40个监控场景下捕获,其中有101个来自不同年龄段的受试者,有232个3D攻击(高保真面具),200个2D攻击(海报,肖像和屏幕),以及2个对抗攻击。在这样的场景下,图像分辨率低、噪声干扰等问题成为监控FAS面临的新挑战.结合SuHiFiMask数据集,我们提出了一种对比质量不变学习(CQIL)网络,从三个方面来缓解图像质量带来的性能下降:(1)引入图像质量变量模块(IQV),结合超分辨率网络来恢复与辨别相关的图像信息。(2)使用生成的样本对来模拟质量方差分布,以帮助对比学习策略在质量变化下获得鲁棒的特征表示。(3)分离质量网络(SQN)旨在学习独立于图像质量的区分特征。最后,通过大量的实验验证了SuHiFiMask数据集的质量和CQIL的优越性。

英文摘要:

Face Anti-spoofing (FAS) is essential to secure face recognition systems from various physical attacks. However, recent research generally focuses on short-distance applications (i.e., phone unlocking) while lacking consideration of long-distance scenes (i.e., surveillance security checks). In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks. In this scene, low image resolution and noise interference are new challenges faced in surveillance FAS. Together with the SuHiFiMask dataset, we propose a Contrastive Quality-Invariance Learning (CQIL) network to alleviate the performance degradation caused by image quality from three aspects: (1) An Image Quality Variable module (IQV) is introduced to recover image information associated with discrimination by combining the super-resolution network. (2) Using generated sample pairs to simulate quality variance distributions to help contrastive learning strategies obtain robust feature representation under quality variation. (3) A Separate Quality Network (SQN) is designed to learn discriminative features independent of image quality. Finally, a large number of experiments verify the quality of the SuHiFiMask dataset and the superiority of the proposed CQIL.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑