Improved watermark detection for spread-spectrum based watermarking using independent component analysis

ABSTRACT

This paper presents an efficient blind watermark detection/decoding scheme for spread spectrum (SS) based watermarking, exploiting the fact that in SS-based embedding schemes the embedded watermark and the host signal are mutually independent and obey non-Gaussian distribution. The proposed scheme employs the theory of independent component analysis (ICA) and posed the watermark detection as a blind source separation problem. The proposed ICA-based blind detection/decoding scheme has been simulated using real-world audio clips. The simulation results show that the ICA-based detector can detect and decode watermark with extremely low decoding bit error probability (less than 0.01) against common watermarking attacks and benchmark degradations.

REFERENCES

• 1: Ingemar Cox , Matthew L. Miller , Jeffery A. Bloom, Digital watermarking, Morgan Kaufmann Publishers Inc., San Francisco, CA, 2001
• 2: C.-P. Wu, P.-C. Su, and C.-C. J. Kuo, "Robust Audio Watermarking for Copyright Protection," SPIE's 44th AMASPAAI, 1999.
• 3: H. Malik, A. Khokhar, and R. Ansari, "Robust Audio Watermarking using Frequency Selective Spread Spectrum Theory," Proc. ICASSP'04, Canada, May 2004.
• 4: B. Chen and G. W. Wornell, "Quantization index modulation: A class of provably good methods for digital watermarking and information embedding," IEEE Trans. on Information Theory, vol. 47(4), pp. 1423--1443, May 2001.
• 5: S. G. Mallat, A Theory for Multiresolution Signal Decomposition: The Wavelet Representation, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.11 n.7, p.674-693, July 1989 [doi>10.1109/34.192463]
• 6: F. Pérez-González, F. Balado, and J. R. Hernández, "Performance analysis of existing and new methods for data hiding with known-host information in additive channels," IEEE Trans. on Signal Processing, 51(4):960--980, April 2003.
• 7: P. Noll, "MPEG Digital Audio Coding," IEEE Sig. Proc. Mag. vol. 14(5), pp. 59--81, Sep 1997.
• 8: S. Noel, and H. Szu, "Multimedia Authenticity with ICA Watermarks," Wavelet Applications VII, SPIE Proc. vol. 4056, pp. 175--184. April, 2000.
• 9: F. Serrano, and J. Fuentes, "Independent Component Analysis Applied to Digital Image Watermarking," Proc. ICASSP'01, 2001.
• 10: B. Toch, D. Lowe, and D. Saad, "Watermarking of Audio Signals using using Independent Component Analysis," Proc. 3rd Int. Conf. WEB Delivering of Music, 2003.
• 11: S. Bounkong, B. Toch, D. Saad, and D. Lowe, "ICA for Watermarking Digital Images," J. Machine Learning Research 1, pp. 1--25, 2002.
• 12: D. Yu, F. Sattar, and K. Ma, "Watermark Detection and Extraction using Independent Component Analysis," EURASIP J. Applied Signal Processing, pp. 92-104, January 2002.
• 13: Sait Sener , Bilge Gunsel, Blind Audio Watermark Decoding Using Independent Component Analysis, Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2, p.875-878, August 23-26, 2004 [doi>10.1109/ICPR.2004.219]
• 14: A. Hyvärinen, J. Karhunen, and E. Oja, "Independent Component Analysis," John Wiley & Sons, 2001.
• 15: Pierre Comon, Independent component analysis, a new concept?, Signal Processing, v.36 n.3, p.287-314, April 1994 [doi>10.1016/0165-1684(94)90029-9]
• 16: A. Hyvärinen , E. Oja, Independent component analysis: algorithms and applications, Neural Networks, v.13 n.4-5, p.411-430, May-June 2000 [doi>10.1016/S0893-6080(00)00026-5]
• 17: A. Hyvärinen, "Fast independent component analysis with noisy data using gaussian moments," Proc. ISCS'99, 1999.
• 18: Jean-François Cardoso, High-order contrasts for independent component analysis, Neural Computation, v.11 n.1, p.157-192, Jan. 1999 [doi>10.1162/089976699300016863]
• 19: A. Hyvärinen, "Independent Component Analysis in the Presence of Gaussian Noise by Maximizing Joint Likelihood" Neurocomputing, 22:49--67, 1998.
• 20: M. Gaeta, and J.-L. Lacoume, "Source separation without prior knowledge: the maximum likelihood solution," Proc. EUSIPCO'90, pp. 621--624, 1990.
• 21: A. Cichocki, S. Douglas, and S. Amari, "Robust techniques for independent component analysis (ICA) with noisy data," Neurocomputing, vol. 22, pp. 113--129, 1998.
• 22: P. Pajunen., "Blind Separation of Binary Sources with Less Sensors than Sources," Proc. Int. Conf. on Neural Networks (ICNN-97), pp. 1994--1997, 1997.
• 23: M. Zibulevsky, and Y.Y. Zeevi, "Extraction of a single source from multichannel data using sparse decomposition", Neurocomputing, 49, pp 163--173, 2002.
• 24: Yuanqing Li , Andrzej Cichocki , Shun-ichi Amari, Analysis of sparse representation and blind source separation, Neural Computation, v.16 n.6, p.1193-1234, June 2004 [doi>10.1162/089976604773717586]
• 25: P. Comon, "Blind Identification in Presence of Noise," Proc. EUSIPCO'92, pp. 835--838, 1992.
• 26: Anthony J. Bell , Terrence J. Sejnowski, An information-maximization approach to blind separation and blind deconvolution, Neural Computation, v.7 n.6, p.1129-1159, Nov. 1995 [doi>10.1162/neco.1995.7.6.1129]
• 27: É. Moulines, J-F. Cardoso, and E. Gassiat, "Maximum likelihood for blind separation and deconvolution of noisy signals using mixture models," Proc. ICASSP'97, pp. 3617--20, 1997.
• 28: R. Gribonval, L. Benaroya, E. Vincent, and C. Févotte, "Proposals for Performance Measurement in Source Separation," 4th Int. Sym. ICA & BSS (ICA 2003), April, 2003.
• 29: Y. Li, D. Powers, and J. Peach, "Comparison of Blind Source Separation Algorithms," Advances in Neural Networks and Applications, N. Mastorakis (Ed.), WSES, pp. 18--21, 2000
• 30: M. Steinebach, A. Lang, J. Dittmann, and F. A. P. Prtitcolas, "Stirmark Benchmark: Audio Watermarking Attacks based on Lossy Compression," Proc. SPIE Security Watermarking Multimedia, vol. 4675, pp. 79--90, 2002.
• 31: "StirMark Benchmark for Audio", http://amsl-smb.cs.uni-magdeburg.de/smfa/main.php
• 32: http://multimedia.ece.uic.edu/~hafiz/ICA_WM.html

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.1 MODELS AND PRINCIPLES
      H.1.1 Systems and Information Theory

General Terms:
Algorithms, Design, Performance, Security

Keywords:
blind source separation, correlation, detection, independent component analysis, spread spectrum, watermarking