Share Email Print

Optical Engineering

Neural-network-based zero-watermark scheme for digital images
Author(s): Sang Jun; Xiaofeng Liao; Mohammad S. Alam
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Digital watermarking has been widely studied for the copyright protection of digital multimedia data. In traditional digital image watermarking techniques, a watermark signal is inserted into the host image, which generally introduces visual quality degradation. On the contrary, zero-watermark techniques extract some features from the host image and use them for watermark detection, instead of watermark embedding. In this method, the distortion problem to the host image due to watermark embedding is eliminated. The zero-watermark scheme proposed in this work employs neural networks for features extraction. It can be used for automatic piracy detection as well as copyright demonstration if it is associated with a copyright authentication center.

Paper Details

Date Published: 1 September 2006
PDF: 9 pages
Opt. Eng. 45(9) 097006 doi: 10.1117/1.2354076
Published in: Optical Engineering Volume 45, Issue 9
Show Author Affiliations
Sang Jun, Chongqing Univ. (China)
Xiaofeng Liao, Chongqing Univ. (China)
Mohammad S. Alam, Univ. of South Alabama (United States)

© SPIE. Terms of Use
Back to Top