Laser & Optoelectronics Progress, Volume. 58, Issue 6, 615006(2021)

Robust Watermarking Algorithm Based on Structured Forests Edge and SIFT

Liu Ying1,2, Yang Xing1、*, and Zhu Tingge1,2
Author Affiliations
  • 1School of Communication and Information Engineering, Xi''an University of Posts & Telecommunications, Xi''an, Shaanxi 710121, China
  • 2Key Laboratory of Electronic Information Application Technology for Scene Investigation, Ministry of Public Security, Xi''an, Shaanxi 710121, China
  • show less
    Figures & Tables(9)
    Flow chart of SIFT operator extracting 1024 stable points
    Flow chart of watermark embedding
    Flow chart of watermark extraction
    Cover images.(a) Lena; (b) Peppers; (c) Plane; (d) Mandrill
    Watermark images.(a) Lena_W; (b) Peppers_W; (c) Plane_W; (d) Mandrill_W
    NC values of the extracted watermark against different attacks
    • Table 1. Test results of watermarked images without attacks

      View table

      Table 1. Test results of watermarked images without attacks

      ParameterLenaPeppersPlaneMandrill
      PSNR /dB55.3956.1859.4358.33
      NC1111
      SSIM1111
    • Table 2. Comparison results of different cover images without attacks

      View table

      Table 2. Comparison results of different cover images without attacks

      AlgorithmLenaPeppersPlaneMandrill
      PSNR /dBNCPSNR /dBNCPSNR /dBNCPSNR /dBNC
      Proposed algorithm55.39156.18159.43158.331
      Algorithm in Ref.[8]47.960.977547.340.960244.520.983048.340.9793
      Algorithm in Ref.[22]52.340.988953.210.989150.960.988354.690.9921
    • Table 3. NC values of the extracted watermarks against various attacks

      View table

      Table 3. NC values of the extracted watermarks against various attacks

      AttacksLenaPeppersPlaneMandrill
      No attack1111
      Salt & pepper noise(d=0.01)0.98240.98670.98590.9825
      Salt & pepper noise(d=0.03)0.95850.95930.95910.9608
      Gaussian noise (m=0, var is 0.005)0.98930.98090.98260.9972
      Gaussian noise (m=0, var is 0.01)0.96010.97000.97170.9961
      Cropping (20 columns)0.99870.99540.99720.9964
      Cropping (30 columns)0.99790.99270.99630.9945
      Cropping (40 columns)0.99170.99360.99490.9908
      JPEG compression (Q=50)0.99540.99820.99630.9975
      JPEG compression (Q=70)10.999110.9984
      Median filter (3×3)0.98700.98890.99070.9861
      Sharpening0.99270.98420.99930.9878
      Histogram equalization0.95520.99820.96920.9576
      Rotation (45°)0.98290.97480.95990.9767
      Average filter (3×3)0.96290.98790.98790.9824
      Contrast adjustment0.98890.99360.99160.9962
      Speckle noise (var is 0.01)0.99070.99260.99460.9975
      Speckle noise (var is 0.05)0.99630.99350.99580.9963
      Motion blur0.98420.98790.97570.9861
      Gaussian filter (3×3)0.97610.98890.98980.9870
    Tools

    Get Citation

    Copy Citation Text

    Liu Ying, Yang Xing, Zhu Tingge. Robust Watermarking Algorithm Based on Structured Forests Edge and SIFT[J]. Laser & Optoelectronics Progress, 2021, 58(6): 615006

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Machine Vision

    Received: Jul. 21, 2020

    Accepted: --

    Published Online: Mar. 11, 2021

    The Author Email: Xing Yang (1830850314@qq.com)

    DOI:10.3788/LOP202158.0615006

    Topics