Multi-modal Document Presentation Attack Detection With Forensics Trace Disentanglement
This work addresses the problem of detecting forged document images for security applications, presenting an incremental improvement by integrating disentangled traces as new modalities.
The paper tackles document presentation attack detection by proposing a multi-modal disentangled traces method that enhances generalization across document contents and layouts without requiring additional resources, achieving superior performance on three benchmark datasets.
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 images with different contents and layouts. Then, unlike the existing DPAD approaches that rely only on data in the RGB domain, we propose to explicitly employ the disentangled recaptured traces as new modalities in the transformer backbone through adaptive multi-modal adapters to fuse RGB/trace features efficiently. Visualization of the disentangled traces confirms the effectiveness of the proposed method in different document contents. Extensive experiments on three benchmark datasets demonstrate the superiority of our MMDT method on representing forensic traces of recapturing distortion.