Multi-modal Document Presentation Attack Detection With Forensics Trace Disentanglement

arXiv:2404.06663v1 Announce Type: new
Abstract: Document Presentation Attack Detection (DPAD) is an important measure in protecting the authenticity of a document image. However, recent DPAD methods demand additional resources, such as manual effort in collecting additional data or knowing the parameters of acquisition devices. This work proposes a DPAD method based on multi-modal disentangled traces (MMDT) without the above drawbacks. We first disentangle the recaptured traces by a self-supervised disentanglement and synthesis network to enhance the generalization capacity in document …

abstract acquisition additional resources arxiv authenticity cs.cv data demand detection devices document forensics however image modal multi-modal parameters presentation resources type work