2026-09-15T07:26:05Zhttps://gredos.usal.es/oai/request

oai:gredos.usal.es:10366/1454982025-04-30T20:15:51Zcom_10366_4386com_10366_4349com_10366_3946com_10366_3823col_10366_4387

Gómez-Ayllón, Beatriz Ortega-DelCampo, David Tsitiridis, Aristeidis Palacios-Alonso, Daniel Sánchez Sánchez, María Araceli Conde, Cristina Cabello, Enrique 2020 [EN] 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. application/pdf http://hdl.handle.net/10366/145498 eng Entropy 1203 Ciencia de los ordenadores 1203.17 Informática Convolutional Neural Network Approach for Multispectral Facial Presentation Attack Detection in Automated Border Control Systems info:eu-repo/semantics/article TEXT Gredos. Repositorio Documental de la Universidad de Salamanca Hispana