Search

Watermarking for identity images printed on a plastic card support is still challenging. In this application, the scheme must be robust against a combination of geometric and signal processing attacks related to the print/scan process. In addition, the scheme must deal with all the possible aggressions that a smart card can encounter during its lifetime. This paper investigates a robust watermarking solution in the Fourier domain in the continuity of our earlier developments reported in this field. It includes both preventive and curative stages that are complementary. The solution is preventive as only a small set of selected bits presenting a small variance are concerned the watermarking process. This property increases the chances of watermark detection rate while maintaining the same level of security. The curative part consists in pre-processing the watermarked image before the detection process. It comprises two specific and accurate counterattacks: the first one deals with blurring correction under a dedicated Wiener filter and the second one focuses on color corrections. The hybrid scheme is highly efficient and has a low computational cost. The new watermarking scheme clearly outperforms competitive approaches and is compatible with industrial constraints. [ABSTRACT FROM AUTHOR]

Smartphone watermarking has many potential applications but also many challenging issues such as being able to withstand print-cam attacks. These include perspective deformations that can strongly deform the freehandedly digitized image. In this paper, we present the design of an image watermarking for print-cam process in the context of an industrial security application for identity images. The method uses watermarking based on the Fourier transform and a specific correction pre-process. These corrections combine frame-based perspective rectification of the freehandedly captured images, a Wiener filter to decrease image blurring and adjustments to reduce color degradations. Results show that the Fourier watermarking method gives better results than state of the art of existing watermarking methods often chosen to cope with print-cam attacks. Fourier watermarking provides a total error rate of 1%, which is compatible with the targeted industrial application. The error of the other methods is at best 25%. Finally, no noticeable difference was found between the two smartphones tested (iPhone 6 and Samsung S5), in terms of error rate, for the proposed method. [ABSTRACT FROM AUTHOR]