Journal
IET IMAGE PROCESSING
Volume 13, Issue 10, Pages 1783-1789Publisher
WILEY
DOI: 10.1049/iet-ipr.2019.0266
Keywords
image watermarking; neural nets; self-attention mechanisms; self-attention layer; real images; GANs model; visible watermark removal algorithm; generative adversarial networks model; watermark removal rate indicator; competitive watermark removal models; watermarked region
Categories
Funding
- National Natural Science Foundation of China [U1536121, 61370195]
- BUPT Excellent Ph.D.
- Students Foundation [CX2018206]
Ask authors/readers for more resources
Previously visible watermark removal algorithms required the location of known watermarks. A corresponding removal algorithm is then proposed based on the location and the feature of the watermark. If the location of the watermark is random or the watermark has different angles, the watermark removal algorithm will encounter problems. The authors recommend a visible watermark removal algorithm based on generative adversarial networks (GANs) and self-attention mechanisms. During the training, the authors introduce a GANs model to build mappings between watermarked images and real images. The authors observe that the feature of the watermarked region in different watermarked images is invariant in nature, and the other regions are changed. The self-attention layer will automatically focus on this invariant feature. Experiments on two public datasets prove that the authors' model has gained excellent performance. Compared with the other four most competitive watermark removal models, the authors improve the watermark removal rate indicator from 17 to 92%. For the other four evaluation indicators, the authors have improved performance by up to 20%.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available