Dataset Information

Real masks and spoof faces: On the masked face presentation attack detection.

ABSTRACT: Face masks have become one of the main methods for reducing the transmission of COVID-19. This makes face recognition (FR) a challenging task because masks hide several discriminative features of faces. Moreover, face presentation attack detection (PAD) is crucial to ensure the security of FR systems. In contrast to the growing number of masked FR studies, the impact of face masked attacks on PAD has not been explored. Therefore, we present novel attacks with real face masks placed on presentations and attacks with subjects wearing masks to reflect the current real-world situation. Furthermore, this study investigates the effect of masked attacks on PAD performance by using seven state-of-the-art PAD algorithms under different experimental settings. We also evaluate the vulnerability of FR systems to masked attacks. The experiments show that real masked attacks pose a serious threat to the operation and security of FR systems.

SUBMITTER: Fang M

PROVIDER: S-EPMC8547786 | biostudies-literature | 2022 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Real masks and spoof faces: On the masked face presentation attack detection.

Fang Meiling M Damer Naser N Kirchbuchner Florian F Kuijper Arjan A

Pattern recognition 20211026

Face masks have become one of the main methods for reducing the transmission of COVID-19. This makes face recognition (FR) a challenging task because masks hide several discriminative features of faces. Moreover, face presentation attack detection (PAD) is crucial to ensure the security of FR systems. In contrast to the growing number of masked FR studies, the impact of face masked attacks on PAD has not been explored. Therefore, we present novel attacks with real face masks placed on presentati ...[more]

PMID: 34720199

Similar Datasets

Project description:IntroductionSince the onset of the coronavirus disease 2019 (COVID-19) pandemic, wearing surgical face masks has become mandatory for healthcare staff in many countries when interacting with patients. Recently, it has been shown that wearing face masks impairs social interaction by diminishing a person's ability to read the emotion of their counterparts, an essential prerequisite to respond adequately in social situations. It is easily conceivable that this may have a tangible negative influence on the communication and relationship between patients and healthcare personnel. We therefore investigated whether it has an effect on how patients perceive healthcare professionals when physicians and nursing staff wear portrait photos with their smiling faces in addition to face masks.MethodsDuring the study period of 16 days, the medical staff of our Department wore surgical face masks at all times during any kind of interaction with patients. In a pseudorandomized order, all members of our staff additionally affixed their portrait photos to their work clothes on 8 of the 16 days. After completion of their visit, 226 patients were interviewed anonymously in a cross-sectional study design using a questionnaire in which they rated the following three items: friendliness of staff, medical quality of treatment, and how well they felt taken care of during treatment in our Department.ResultsOn days, on which staff wore photos, mean scores of the questionnaires were significantly higher than on non-photo days (p = 0.013; mean ± standard deviation = 92.8 ± 11.3 vs. 91.0 ± 12.6; median (range) = 97 (98) vs. 96 (76)). When analyzed separately, the increased scores were only significant for the item friendliness of staff (p = 0.009; mean ± standard deviation = 95.8 ± 6.3 vs. 92.2 ± 11.5; median (range) = 98 (39) vs. 97 (54)).ConclusionOur study suggests that the use of portrait photos with smiling faces has a positive effect on how patients perceive healthcare staff.

Dataset Information

Real masks and spoof faces: On the masked face presentation attack detection.

Publications

Real masks and spoof faces: On the masked face presentation attack detection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets