Blind Deep-Learning-Based Image Watermarking Robust Against Geometric Transformations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916125046996992 |
|---|---|
| author | Mareen, Hannes Antchougov, Lucas Van Wallendael, Glenn Lambert, Peter |
| author_facet | Mareen, Hannes Antchougov, Lucas Van Wallendael, Glenn Lambert, Peter |
| contents | Digital watermarking enables protection against copyright infringement of images. Although existing methods embed watermarks imperceptibly and demonstrate robustness against attacks, they typically lack resilience against geometric transformations. Therefore, this paper proposes a new watermarking method that is robust against geometric attacks. The proposed method is based on the existing HiDDeN architecture that uses deep learning for watermark encoding and decoding. We add new noise layers to this architecture, namely for a differentiable JPEG estimation, rotation, rescaling, translation, shearing and mirroring. We demonstrate that our method outperforms the state of the art when it comes to geometric robustness. In conclusion, the proposed method can be used to protect images when viewed on consumers' devices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09062 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Blind Deep-Learning-Based Image Watermarking Robust Against Geometric Transformations Mareen, Hannes Antchougov, Lucas Van Wallendael, Glenn Lambert, Peter Multimedia Cryptography and Security Computer Vision and Pattern Recognition Digital watermarking enables protection against copyright infringement of images. Although existing methods embed watermarks imperceptibly and demonstrate robustness against attacks, they typically lack resilience against geometric transformations. Therefore, this paper proposes a new watermarking method that is robust against geometric attacks. The proposed method is based on the existing HiDDeN architecture that uses deep learning for watermark encoding and decoding. We add new noise layers to this architecture, namely for a differentiable JPEG estimation, rotation, rescaling, translation, shearing and mirroring. We demonstrate that our method outperforms the state of the art when it comes to geometric robustness. In conclusion, the proposed method can be used to protect images when viewed on consumers' devices. |
| title | Blind Deep-Learning-Based Image Watermarking Robust Against Geometric Transformations |
| topic | Multimedia Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.09062 |