Content distribution and copyright authentication based on combined indexing and watermarking

  • Authors:
  • Shiguo Lian;Xi Chen;Jinwei Wang

  • Affiliations:
  • France Telecom R&D (Orange Labs) Beijing, Beijing, People's Republic of China 100080;E-Commerce Department, Nanjing University, Nanjing, People's Republic of China 210093;The 28th Research Institute, CETC, Nanjing, People's Republic of China 210007

  • Venue:
  • Multimedia Tools and Applications
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Copyright issues become more and more urgent with the wide spread of multimedia content over Internet, e.g., whether the media content is copyright-protected in multimedia social networks, or whether a media content is released on Internet illegally. To solve these problems, this paper proposes a content distribution and copyright authentication system based on media index and watermarking techniques. Before media distribution, the media content is marked (by embedding the ownership information or customer identification into the media), and the robust features that can be used both for media index and content emendation is extracted from the watermarked media and registered in a feature database. Some customer may leak out his media copy over Internet directly or after slight operations, such as rotation, shearing, scaling, translation, etc. To detect whether a media over Internet is copyright-protected or not, the following work is done. Firstly, a watermark is extracted from the media and compared with the original one. If the watermark exists, then the media is copyright-protected, and the authentication process is finished. Otherwise, a robust feature is extracted from the considered media and matched with the feature database. The matching result gives the operation parameters that are used to emend the media content. After media emendation, a watermark is extracted or detected again and used to authenticate the copyright. In this system, the robust feature is not only used to search the related media contents but also to emend the media in order to improve the robustness against such operations as adding noise, compression, rotation, shearing, scaling, translation, etc. Experimental results show that the combination of media index and watermark detection can improve the detection rate greatly.