On the Effectiveness of Sparse Linear Polarization Pixels for Face Anti-Spoofing

Robust face anti-spoofing (FAS) is essential for secure facial recognition systems. This article presents a novel hybrid sensor approach using sparsely linear polarization pixels integrated into an RGB pixel matrix to leverage both angle of linear polarization (AoLP) and degree of linear polarization (DoLP). The sparse pixel integration overcomes the vulnerabilities of conventional RGB-based methods and the complexity of multisensor solutions. By integrating polarization features into a lightweight convolutional neural network (CNN), our solution offers a cost-effective and reliable FAS under all light conditions. Experimental results show that combining AoLP and DoLP significantly boosts accuracy compared to methods relying solely on RGB or DoLP, achieving an average classification error rate (ACER) as low as 0.4%, even with an extremely sparse deployment of polarization pixels (1 per 400 RGB pixels). An ablation study quantifies the individual contributions of AoLP and DoLP. Moreover, the system sustains its efficacy in challenging low-light scenarios and delivers a 10-fold reduction in errors compared to RGB-based methods. These findings underscore the potential of this single-sensor, low-compute solution for secure, affordable deployments in mobile devices and embedded systems.