Face demorphing in the presence of facial appearance variations
Matteo Ferrara, Annalisa Franco, Davide Maltoni · 2018
This study focuses on the robustness of face demorphing as a technique to protect face recognition systems against the well-known morphing threat. In particular, we check if in presence of face variations of different type and strength, the demorphing process significantly reduces the Genuine Acceptance Rate leading to an excessive number of false morphing warnings. Experimental results show that, except for extreme conditions that are unlikely in e-gates scenario, demorphing does not markedly affect face recognition accuracy.