Biometrics in the Time of Pandemic: 40% Masked Face Recognition Degradation can be Reduced to 2%
This addresses the challenge of biometric recognition in border checkpoint scenarios during pandemics, representing a strong specific gain rather than an incremental improvement.
The study tackled the problem of face recognition performance degradation due to mask-wearing during pandemics, reporting a reduction from 36.78% degradation to 1.79% using advanced deep learning methods.
In this study of the face recognition on masked versus unmasked faces generated using Flickr-Faces-HQ and SpeakingFaces datasets, we report 36.78% degradation of recognition performance caused by the mask-wearing at the time of pandemics, in particular, in border checkpoint scenarios. We have achieved better performance and reduced the degradation to 1.79% using advanced deep learning approaches in the cross-spectral domain.