The morphing attack proved to be a serious threat for modern automated border control systems where face recognition is used to link the identity of a passenger to his/her e-document. In this paper we show that by exploiting the live face image acquired at the gate, the morphed face image stored in the document can be reverted (or demorphed) enough to reveal the identity of the legitimate document owner, thus allowing the system to issue a warning. A number of practical experiments on two datasets proves the efficacy of our approach.
Ferrara, M., Franco, A., Maltoni, D. (2018). Face Demorphing. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 13(4), 1008-1017 [10.1109/TIFS.2017.2777340].
Face Demorphing
Ferrara, Matteo
;Franco, Annalisa;Maltoni, Davide
2018
Abstract
The morphing attack proved to be a serious threat for modern automated border control systems where face recognition is used to link the identity of a passenger to his/her e-document. In this paper we show that by exploiting the live face image acquired at the gate, the morphed face image stored in the document can be reverted (or demorphed) enough to reveal the identity of the legitimate document owner, thus allowing the system to issue a warning. A number of practical experiments on two datasets proves the efficacy of our approach.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
