Analyzing Human Observer Ability in Morphing Attack Detection -- Where Do We Stand?

• Main Authors: Godage, Sankini Rancha, Løvåsdal, Frøy, Venkatesh, Sushma, Raja, Kiran, Ramachandra, Raghavendra, Busch, Christoph
• Format: Journal Article
• Language: English
• Published: 24.02.2022
• Subjects: Computer Science - Computer Vision and Pattern Recognition; Computer Science - Computers and Society
• DOI: 10.48550/arxiv.2202.12426

Few studies have focused on examining how people recognize morphing attacks, even as several publications have examined the susceptibility of automated FRS and offered morphing attack detection (MAD) approaches. MAD approaches base their decisions either on a single image with no reference to compare against (S-MAD) or using a reference image (D-MAD). One prevalent misconception is that an examiner's or observer's capacity for facial morph detection depends on their subject expertise, experience, and familiarity with the issue and that no works have reported the specific results of observers who regularly verify identity (ID) documents for their jobs. As human observers are involved in checking the ID documents having facial images, a lapse in their competence can have significant societal challenges. To assess the observers' proficiency, this work first builds a new benchmark database of realistic morphing attacks from 48 different subjects, resulting in 400 morphed images. We also capture images from Automated Border Control (ABC) gates to mimic the realistic border-crossing scenarios in the D-MAD setting with 400 probe images to study the ability of human observers to detect morphed images. A new dataset of 180 morphing images is also produced to research human capacity in the S-MAD environment. In addition to creating a new evaluation platform to conduct S-MAD and D-MAD analysis, the study employs 469 observers for D-MAD and 410 observers for S-MAD who are primarily governmental employees from more than 40 countries, along with 103 subjects who are not examiners. The analysis offers intriguing insights and highlights the lack of expertise and failure to recognize a sizable number of morphing attacks by experts. The results of this study are intended to aid in the development of training programs to prevent security failures while determining whether an image is bona fide or altered.