Spatio-Temporal Deep Learning for Face Liveness Detection: A ResNet-GRU Approach
International Journal of Drug Delivery Technology · 02.06.2026 · 16 (44s)
DOI: 10.25258/ijddt.16.44s.63 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 02.06.2026. Verfasst von Punam Chandrashekhar Wagale und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Biometric authentication systems founded on face recognition are now embedded across a broad spectrum of realworld applications, making them high-value targets for spoofing attacks. Adversaries exploit artefacts ranging from two-dimensional printed photographs and replay video sequences to sculpted three-dimensional masks to deceive these systems. Countering such threats, face anti-spoofing (FAS)—also termed presentation attack detection (PAD)—has emerged as an indispensable safeguard within modern authentication pipelines. This paper presents a spatio-temporal deep learning framework that fuses a ResNet-50 spatial encoder with a Gated Recurrent Unit (GRU) temporal module to simultaneously capture liveness cues at both the texture and motion levels. Beyond the proposed system, a structured review of contemporary deep FAS methodologies is provided, covering pixel-wise supervisory signals, domain-invariant training strategies, open-set evaluation protocols, and sensor-aware multi-modal architectures. Experimental results on a curated dataset of 1,250 samples yield a classification accuracy of 96.2%, a false acceptance rate of 3.4%, and a false rejection rate of 3.8%, outperforming several recently published baseline methods. Key open challenges and prospective research directions are identified to guide further development of robust, deployment-ready FAS systems.
Zitieren
APA
Wagale, P. C., Agarkar, P., & Mahajan, A. (2026). Spatio-Temporal Deep Learning for Face Liveness Detection: A ResNet-GRU Approach. International Journal of Drug Delivery Technology, 16(44s). https://doi.org/10.25258/ijddt.16.44s.63
Vancouver
Wagale PC, Agarkar P, Mahajan A. Spatio-Temporal Deep Learning for Face Liveness Detection: A ResNet-GRU Approach. International Journal of Drug Delivery Technology. 2026;16(44s). doi:10.25258/ijddt.16.44s.63
BibTeX
@article{Wagale2026,
author = {Wagale, Punam Chandrashekhar and Agarkar, Pankaj and Mahajan, Anita},
title = {Spatio-Temporal Deep Learning for Face Liveness Detection: A ResNet-GRU Approach},
journal = {International Journal of Drug Delivery Technology},
year = {2026},
volume = {16},
number = {44s},
doi = {10.25258/ijddt.16.44s.63}
}
EUVIMED