Digital watermarking method based on heteroassociative image compression and its realization with artificial neural networks
Sirota A.A., Dryuchenko M.A., Mitrofanova E.Yu.

 

Voronezh State University, Voronezh, Russia

 PDF

Abstract:
In this paper, we present a digital watermarking method and associated algorithms that use a heteroassociative compressive transformation to embed a digital watermark bit sequence into blocks (fragments) of container images. A principal feature of the proposed method is the use of the heteroassociative compressing transformation – a mutual mapping with the compression of two neighboring image regions of an arbitrary shape. We also present the results of our experiments, namely the dependencies of quality indicators of thus created digital watermarks, which show the container distortion level, and the probability of digital watermark extraction error. In the final section, we analyze the performance of the proposed digital watermarking algorithms under various distortions and transformations aimed at destroying the hidden data, and compare these algorithms with the existing ones.

Keywords:
data compression, image processing, neural networks, steganography, digital watermarks.

Citation:
Sirota AA, Dryuchenko MA, Mitrofanova EYu. Digital watermarking method based on heteroassociative image compression and its realization with artificial neural networks. Computer Optics 2018; 42(3): 483-494. DOI: 10.18287/2412-6179-2018-42-3-483-494.

References:

  1. Younes MAB, Jantan A. A new steganography approach for image encryption exchange by using the least significant bit insertion. Inter J Comp Sci Network Security 2008; 8(6): 247-254.
  2. Hadhoud MM, Ismail NA, Shawkey W, Mohammed AZ. Secure perceptual data hiding technique using information theory. ICEEC '04 2004: 249-253. DOI: 10.1109/ICEEC.2004.1374433.
  3. Mandal JK, Sengupta M. Steganographic technique based on minimum deviation of fidelity. 2011 Second International Conference on Emerging Applications of Information Technology 2011; 298-301. DOI: 10.1109/EAIT.2011.24.
  4. Wu H-C, Wu N-I, Tsai C-S. Image Steganographic scheme based on pixel-value differencing and LSB replacement methods. IEE Proceedings – Vision, Image and Signal Processing 2005; 152(5): 611-615. DOI: 10.1049/ip-vis:20059022.
  5. Kawaguchi E, Eason RO. Principle and applications of BPCS-Steganography. Proc SPIE 1998; 3524: 464-473. DOI: 10.1117/12.337436.
  6. Maya ST, Miyatake MN, Medina RV. Robust steganography using bit plane complexity segmentation. 1st International Conference on Electrical and Electronics Engineering 2004: 40-43. DOI: 10.1109/ICEEE.2004.1433845.
  7. Darmstaedter V, Delaigle J-F, Quisquater JJ, Macq B. Low cost spatial watermarking. Computers and Graphics 1998; 22(4): 417-424. DOI: 10.1016/S0097-8493(98)00031-4.
  8. Langelaar GC, van der Lubbe JCA, Lagendijk RL. Robust labeling methods for copy protection of images. Proc SPIE 1997; 3022: 298-309. DOI: 10.1117/12.263418.
  9. Provos N, Honeyman P. Hide and seek: An introduction to steganography. IEEE Security & Privacy 2003; 1(3): 32-44. DOI: 10.1109/MSECP.2003.1203220.
  10. Westfeld A. F5-A steganographic algorithm: High capacity despite better steganalysis. Proceedings of 4th International Workshop Information Hiding 2001: 289-302.
  11. Kavitha V, Easwarakumar KS. Neural based steganography. In Book: Zhang Ch, Guesgen HW, Yeap WK, eds. PRICAI 2004: Trends in Artificial Intelligence. Berlin, Heidelberg: Springer-Verlag; 2004: 429-435.
  12. Chang Ch-Y, Shen W-Ch, Wang H-J. Using counter-propagation neural network for robust digital audio watermarking in DWT domain. 2006 IEEE International Conference on Systems, Man and Cybernetics 2006; 2: 1214-1219. DOI: 10.1109/ICSMC.2006.384880.
  13. Sirota AA, Dryuchenko MA, Mitrofanova EY. Neural network functional models and algorithms for information conversion in order to create digital watermarks. Radioelectronics and Communications Systems 2015; 58(1): 1-10. DOI: 10.3103/S073527271501001X.
  14. Sirota AA, Dryuchenko MA. Generalized image compression algorithms for arbitrarily-shaped fragments and their implementation using artificial neural networks. Computer Optics 2015; 39(5): 751-761. DOI: 10.18287/0134-2452-2015-39-5-751-761.
  15. Sirota AA, Mitrofanova EY, Dryuchenko MA. Analysis of the stability of the digital watermarking algorithms based on universal compression to the negative impact of various types [In Russian]. Proceedings of Voronezh State University, Series: Systems Analysis and Information Technologies 2015; 3: 111-121.
  16. Osowski S. Sieci neuronowe do przetwarzania informacji [In Polish]. Warsaw, Poland: Oficyna Wydawnicza Politechniki Warszawskiej; 2000. ISBN: 978-83-7207-615-1.
  17. Wang Z, Bovik AC. A universal image quality index. IEEE Signal Processing Letters 2002; 9(3): 81-84. DOI: 10.1109/97.995823.
  18. Kutter M, Jordan FD, Bossen F. Digital signature of color images using amplitude modulation. Proc SPIE 1997; 3022: 518-526. DOI: 10.1117/12.263442.
  19. Koch E, Zhao J. Towards robust and hidden image copyright labeling. Proc IEEE Workshop on Nonlinear Signal and Image Processing 1995: 452-455.
  20. Divecha N, Jani NN. Implementation and performance analysis of DCT-DWT-SVD based watermarking algorithms for Color images. International Conference on Intelligent Systems and Signal Processing (ISSP) 2013: 204-208. DOI: 10.1109/ISSP.2013.6526903.
  21. Kodak lossless true color image suite. Source: <http://r0k.us/graphics/kodak/>.
  22. Testimages. Free collection of digital images for testing. Source: <https://testimages.org/>.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20