ID-Card Synthetic Generation: Toward a Simulated Bona fide Dataset
This addresses data scarcity for PAD systems in security applications, though it is incremental as it applies an existing generative method to a new domain.
The paper tackles the problem of limited bona fide images for training Presentation Attack Detection (PAD) systems for ID cards by generating synthetic versions using Stable Diffusion, resulting in improved detection performance as the system identifies these images as bona fide.
Nowadays, the development of a Presentation Attack Detection (PAD) system for ID cards presents a challenge due to the lack of images available to train a robust PAD system and the increase in diversity of possible attack instrument species. Today, most algorithms focus on generating attack samples and do not take into account the limited number of bona fide images. This work is one of the first to propose a method for mimicking bona fide images by generating synthetic versions of them using Stable Diffusion, which may help improve the generalisation capabilities of the detector. Furthermore, the new images generated are evaluated in a system trained from scratch and in a commercial solution. The PAD system yields an interesting result, as it identifies our images as bona fide, which has a positive impact on detection performance and data restrictions.