ReDMark: Framework for residual diffusion watermarking based on deep networks

By Mahdi Ahmadi, Alireza Norouzi, Nader Karimi, Shadrokh Samavi, Ali Emami. Expert systems with applications, 2018

297 citations recorded by the source corpus.

Abstract Due to the rapid growth of machine learning tools and specifically deep networks in various computer vision and image processing areas, applications of Convolutional Neural Networks for watermarking have recently emerged. In this paper, we propose a deep end-to-end diffusion watermarking framework (ReDMark) which can learn a new watermarking algorithm in any desired transform space. The framework is composed of two Fully Convolutional Neural Networks with residual structure which handle embedding and extraction operations in real-time. The whole deep network is trained end-to-end to conduct a blind secure watermarking. The proposed framework simulates various attacks as a differentiable network layer to facilitate end-to-end training. The watermark data is diffused in a relatively wide area of the image to enhance security and robustness of the algorithm. Comparative results versus recent state-of-the-art researches highlight the superiority of the proposed framework in terms of imperceptibility, robustness and speed. The source codes of the proposed framework are publicly available at Github 1 .

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7898ae238b81b2547f6769e6c74052c727046627

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

  1. Feng Yang
  2. Zhenyu Guan
  3. Xin Deng
  4. Peyman Milanfar
  5. Mai Xu
  6. Ruohan Zhan
  7. Jianyi Wang
  8. Junpeng Jing

Citations in the corpus