Fusing Multiscale Texture and Residual Descriptors for Multilevel 2D Barcode Rebroadcasting Detection

TL;DR

This paper introduces a novel multimedia forensics approach that fuses multiscale texture and residual descriptors to detect illegal rebroadcasting of 2D barcodes, enhancing authenticity verification in practical scenarios.

Contribution

It proposes a new feature set combining global and local descriptors for improved detection of barcode copying attacks, outperforming existing methods.

Findings

Effective in cross-dataset scenarios

Outperforms existing texture and deep learning methods

Practical for real-world applications

Abstract

Nowadays, 2D barcodes have been widely used for advertisement, mobile payment, and product authentication. However, in applications related to product authentication, an authentic 2D barcode can be illegally copied and attached to a counterfeited product in such a way to bypass the authentication scheme. In this paper, we employ a proprietary 2D barcode pattern and use multimedia forensics methods to analyse the scanning and printing artefacts resulting from the copy (rebroadcasting) attack. A diverse and complementary feature set is proposed to quantify the barcode texture distortions introduced during the illegal copying process. The proposed features are composed of global and local descriptors, which characterize the multi-scale texture appearance and the points of interest distribution, respectively. The proposed descriptors are compared against some existing texture descriptors and deep learning-based approaches under various scenarios, such as cross-datasets and cross-size. Experimental results highlight the practicality of the proposed method in real-world settings.