Sánchez-Sánchez M Araceli, Conde Cristina, Gómez-Ayllón Beatriz, Ortega-DelCampo David, Tsitiridis Aristeidis, Palacios-Alonso Daniel, Cabello Enrique
Departamento de Informática y Automática-Universidad de Salamanca, Avda. Fernando Ballesteros, 2, 37008 Salamanca, Spain.
Escuela Técnica Superior de Ingeniería Informática-Universidad Rey Juan Carlos, Tulipán, s/n, 28933 Móstoles, Madrid, Spain.
Entropy (Basel). 2020 Nov 14;22(11):1296. doi: 10.3390/e22111296.
Automated border control systems are the first critical infrastructure point when crossing a border country. Crossing border lines for unauthorized passengers is a high security risk to any country. This paper presents a multispectral analysis of presentation attack detection for facial biometrics using the learned features from a convolutional neural network. Three sensors are considered to design and develop a new database that is composed of visible (VIS), near-infrared (NIR), and thermal images. Most studies are based on laboratory or ideal conditions-controlled environments. However, in a real scenario, a subject's situation is completely modified due to diverse physiological conditions, such as stress, temperature changes, sweating, and increased blood pressure. For this reason, the added value of this study is that this database was acquired in situ. The attacks considered were printed, masked, and displayed images. In addition, five classifiers were used to detect the presentation attack. Note that thermal sensors provide better performance than other solutions. The results present better outputs when all sensors are used together, regardless of whether classifier or feature-level fusion is considered. Finally, classifiers such as KNN or SVM show high performance and low computational level.
自动化边境控制系统是跨越边境国家时的首个关键基础设施点。未经授权的乘客穿越边境线对任何国家来说都是高安全风险。本文提出了一种利用卷积神经网络学习到的特征对面部生物识别进行呈现攻击检测的多光谱分析方法。考虑使用三个传感器来设计和开发一个由可见光（VIS）、近红外（NIR）和热图像组成的新数据库。大多数研究基于实验室或理想条件控制的环境。然而，在实际场景中，由于压力、温度变化、出汗和血压升高等多种生理状况，受试者的情况会完全改变。因此，本研究的附加值在于该数据库是在现场采集的。所考虑的攻击包括打印、蒙面和显示的图像。此外，使用了五个分类器来检测呈现攻击。请注意，热传感器比其他解决方案具有更好的性能。无论考虑分类器融合还是特征级融合，当所有传感器一起使用时，结果都呈现出更好的输出。最后，诸如KNN或SVM等分类器表现出高性能和低计算量。
