Robust watermarking against print and scan attack through efficient modeling algorithm

作者：

Highlights：

• A neural network as a nonlinear system models print and scan distortions properly.

• An accurate model could suggest suitable locations in DWT domain for watermarking.

• Watermarking in the combination of DWT and DCT domains will improve the robustness.

• Only downsampling attack will degrade the robustness of watermarking algorithm.

摘要

•A neural network as a nonlinear system models print and scan distortions properly.•An accurate model could suggest suitable locations in DWT domain for watermarking.•Watermarking in the combination of DWT and DCT domains will improve the robustness.•Only downsampling attack will degrade the robustness of watermarking algorithm.

论文关键词：Image watermarking,Print and scan attack,Modeling,Robustness,Image Quality

论文评审过程：Received 8 January 2013, Revised 21 July 2014, Accepted 21 July 2014, Available online 7 August 2014.

论文官网地址：https://doi.org/10.1016/j.image.2014.07.004