Matches in Ghent University Academic Bibliography for { <https://biblio.ugent.be/publication/01HRESBXED003D2NHEAW9DN2FQ> ?p ?o. }
Showing items 1 to 25 of
25
with 100 items per page.
- 01HRESBXED003D2NHEAW9DN2FQ classification C1.
- 01HRESBXED003D2NHEAW9DN2FQ date "2024".
- 01HRESBXED003D2NHEAW9DN2FQ language "eng".
- 01HRESBXED003D2NHEAW9DN2FQ type conference.
- 01HRESBXED003D2NHEAW9DN2FQ hasPart 01HRESNV8Q4SCQ24DTPBVCTPRA.pdf.
- 01HRESBXED003D2NHEAW9DN2FQ hasPart 01HRESPEAPMDM6BE40XDA9KMVA.pdf.
- 01HRESBXED003D2NHEAW9DN2FQ subject "Technology and Engineering".
- 01HRESBXED003D2NHEAW9DN2FQ doi "10.1109/icce59016.2024.10444317".
- 01HRESBXED003D2NHEAW9DN2FQ isbn "9798350324136".
- 01HRESBXED003D2NHEAW9DN2FQ issn "2158-4001".
- 01HRESBXED003D2NHEAW9DN2FQ presentedAt urn:uuid:90e4d5f4-5849-4a33-8f10-3c7bb3a0a632.
- 01HRESBXED003D2NHEAW9DN2FQ abstract "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.".
- 01HRESBXED003D2NHEAW9DN2FQ author 35BCF514-F0EE-11E1-A9DE-61C894A0A6B4.
- 01HRESBXED003D2NHEAW9DN2FQ author 7D910E2E-94E1-11E7-8073-9A50AE28A064.
- 01HRESBXED003D2NHEAW9DN2FQ author F67712CC-F0ED-11E1-A9DE-61C894A0A6B4.
- 01HRESBXED003D2NHEAW9DN2FQ author FAF31990-F0ED-11E1-A9DE-61C894A0A6B4.
- 01HRESBXED003D2NHEAW9DN2FQ dateCreated "2024-03-08T10:22:30Z".
- 01HRESBXED003D2NHEAW9DN2FQ dateModified "2024-10-29T18:36:37Z".
- 01HRESBXED003D2NHEAW9DN2FQ name "Blind deep-learning-based image watermarking robust against geometric transformations".
- 01HRESBXED003D2NHEAW9DN2FQ pagination urn:uuid:93d00f51-c02b-4800-bf1b-2ad67a50089a.
- 01HRESBXED003D2NHEAW9DN2FQ publisher urn:uuid:832577de-c602-487c-b73a-b85425c79765.
- 01HRESBXED003D2NHEAW9DN2FQ sameAs LU-01HRESBXED003D2NHEAW9DN2FQ.
- 01HRESBXED003D2NHEAW9DN2FQ sourceOrganization urn:uuid:94004d55-ebc0-406f-8d07-2e51e4283c0f.
- 01HRESBXED003D2NHEAW9DN2FQ sourceOrganization urn:uuid:9ca6dfef-eb2e-49f6-ba89-5397c41424ee.
- 01HRESBXED003D2NHEAW9DN2FQ type C1.