Multispectral Imaging for Differential Face Morphing Attack Detection: A Preliminary Study

Face morphing attack detection is emerging as an increasingly challenging problem owing to advancements in high-quality and realistic morphing attack generation. Reliable detection of morphing attacks is essential because these attacks are targeted for border control applications. This paper presents a multispectral framework for differential morphing-attack detection (D-MAD). The D-MAD methods are based on using two facial images that are captured from the ePassport (also called the reference image) and the trusted device (for example, Automatic Border Control (ABC) gates) to detect whether the face image presented in ePassport is morphed. The proposed multi-spectral D-MAD framework introduce a multispectral image captured as a trusted capture to acquire seven different spectral bands to detect morphing attacks. Extensive experiments were conducted on the newly created Multispectral Morphed Datasets (MSMD) with 143 unique data subjects that were captured using both visible and multispectral cameras in multiple sessions. The results indicate the superior performance of the proposed multispectral framework compared to visible images.

1. Introduction

Face Recognition Systems (FRS) are widely deployed in numerous real-life access control applications. Face biometrics are extensively used in border control scenarios, resulting in more than one billion electric passports (or ePassports) [5] in which the face is used as the primary identifier. The exponential growth in the adaptation of ePassports and automatic Border Control (ABC) gates has also increased the risk of attacking these systems. Among the different types of attacks on ePassports, morphing attacks have emerged as potential attacks by deceiving both humans (at passport applications and border control) and ABC gates [11], [29].