Morphing attack detection based on adaptive incremental learning

Face morphing images pose a significant threat to the security of face recognition systems. Most existing morphing attack detection （MAD） methods rely on large amounts of training data. However， due to the insufficient diversity of training data， the detection accuracy of these models often degrades...

Full beskrivning

Bibliografiska uppgifter

Huvudupphov:	HE Zu-Yuan, ZHAO Pei-Yi, DENG Zong-Yong, ZHOU Si-Rui, ZHAO Qi-Jun
Materialtyp:	Artigo
Språk:	Inglês
Utgiven:	Editorial Department of Journal of Sichuan University (Natural Science Edition) 2025-09-01
Serie:	四川大学学报. 自然科学版
Ämnen:	Face morphing attack detection Incremental learning Contrastive learning Prototype learning
Länkar:	http://science.scu.edu.cn/thesisDetails#10.19907/j.0490-6756.250031
Taggar:	Lägg till en tagg Inga taggar, Lägg till första taggen!