ID-Card Synthetic Generation: Toward a Simulated Bona fide Dataset

TL;DR

This paper introduces a method to generate synthetic bona fide ID card images using Stable Diffusion, aiming to enhance presentation attack detection systems by addressing data scarcity and diversity challenges.

Contribution

It is among the first to mimic bona fide images with synthetic data for ID cards, improving PAD system robustness and generalization.

Findings

Synthetic images are recognized as bona fide by PAD systems.

Generated data improves detection performance.

Method enhances robustness against diverse attack instruments.

Abstract

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.