• DocumentCode
    551529
  • Title

    The digital watermarking technology based on neural networks

  • Author

    Chang-hui, Yu ; Wan-li, Feng ; Hong, Zhou

  • Author_Institution
    Fac. of Comput. Eng., Huaiyin Inst. of Technol., Huaiyin, China
  • Volume
    1
  • fYear
    2011
  • fDate
    20-21 Aug. 2011
  • Firstpage
    5
  • Lastpage
    8
  • Abstract
    This paper concerns the digital watermarking technology on three different processing stages in order to enhance the robustness of digital watermarking under the premise of invisibility. (1)The first stage is watermark signal pre-processing. The watermark signal created using binary gray images is taken the highly nonlinear processing by the chaotic function first and then by the neural network, which enhances the degree of watermark confidentiality greatly; (2)The second stage is watermark embedding strength degree. First a neural network is constructed and trained. The trained neural network can be used in watermark embedding and extraction by which a watermark algorithm can be achieved to do blind detection; (3)The third stage is watermark embedding and extraction. The treated watermark signal is embedded into the airspace of the original image through the trained neural network. And the neural network is also used to extract and detect the watermark. Proved by experimental results, this algorithm has good robustness.
  • Keywords
    image coding; neural nets; watermarking; binary gray image; blind detection; chaotic function; digital watermarking technology; neural network; nonlinear processing; watermark embedding strength degree; watermark signal preprocessing; Chaos; Cryptography; Discrete cosine transforms; PSNR; Robustness; Watermarking; airspace; embedding strength; neural networks; preprocessing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computing, Control and Industrial Engineering (CCIE), 2011 IEEE 2nd International Conference on
  • Conference_Location
    Wuhan
  • Print_ISBN
    978-1-4244-9599-3
  • Type

    conf

  • DOI
    10.1109/CCIENG.2011.6007943
  • Filename
    6007943