Geometric attack resistant image watermarking based on MSER

Abstract

Geometric distortions are simple and effective attacks rendering many watermarking methods useless. They make detection and extraction of the embedded watermark difficult or even impossible by destroying the synchronization between the watermark reader and the embedded watermark. In this paper, we propose a blind content-based image watermarking scheme against geometric distortions. Firstly, the MSER detector is adopted to extract a set of maximally stable extremal regions which are affine covariant and robust to geometric distortions and common signal processing. Secondly, every original MSER is fitted into an elliptical region that was proved to be affine invariant. In order to achieve rotation invariance, an image normalization process is performed to transform the elliptical regions into circular ones. Finally, watermarks are repeatedly embedded into every circular disk by modifying the wavelet transform coefficients. Experimental results on standard benchmark demonstrate that the proposed scheme is robust to geometric distortions as well as common signal processing.

Keywords

image watermarking / maximally stable extremal region / geometric distortions / image normalization / wavelet transform

References

[1] Petitcolas F. Watermarking schemes evaluation. IEEE Signal Process, 2000, 17(5): 58-64

[2] Podilchuk C, Delp E. Digital watermarking: algorithms and applications. IEEE Signal Process, 2001, 18(4): 33-46

[3] Petitcolas F, Anderson R, Kuhn M. Attacks on copyright marking systems. Lecture Notes in Computer Science, 1998, 1525: 218-238

[4] Qi X, Qi J. A robust content-based digital image watermarking scheme. Signal Processing, 2007, 87(6): 1264-1280

[5] Gao X, Deng C, Li X, Tao D. A local tchebichef moments-based robust image watermarking. Signal Processing, 2009, 89(8): 1531-1539

[6] O’Ruanaidh J, Pun T. Rotation, scale, and translation invariant spread spectrum digital image watermarking. Signal Processing, 1998, 66(3): 303-317

[7] Song H, Yu S, Yang X, Song L, Wang C. Contourlet-based image adaptive watermarking. Signal Processing: Image Communication, 2008, 23(3): 162-178

[8] Xiao M, Wan X, Gan C, Du B. A robust dct domain watermarking algorithm based on chaos system. In: Proceedings of SPIE, 2009, 7495

[9] Pereira S, Pun T. Robust template matching for affine resistant image watermarks. IEEE Transactions on Image Process, 2000, 9(6): 1123-1129

[10] Qi X, Qi J. Improved affine resistant watermarking by using robust templates. In: IEEE International Conference on Acoustics, Speech, and Signal Processing. 2004, 495-408

[11] Alghoniemy M, Tewfik A. Geometric invariance in image watermarking. IEEE Transactions on Image Process, 2004, 13(2): 145-153

[12] Dong P, Brankov J, Galatsanos N, Yang Y, Davoine F. Digital watermarking robust to geometric distortions. IEEE Transactions on Image Process, 2005, 14(12): 2140-2150

[13] Zhang H, Shu H, Coatrieux G, Zhu J, Wu Y Z J, Zhu H, Luo L. Affine legendre moment invariants for image watermarking robust to geometric distortions. IEEE Transactions on Image Process, 2011, 20(8): 2189-2199

[14] Reiss T. The revised fundamental theorem of moment invariants. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(8): 830-834

[15] Flusser J, Suk T. Pattern recognition by affine moment invariants. In: IEEE International Conference on Pattern Recognition. 1993, 167-174

[16] Bas P, Chassery J, Macq B. Geometrically invariant watermarking using feature points. IEEE Transactions on Image Process, 2002, 11(9): 1014-1028

[17] Lee H, Kim H. Robust image watermarking using local invariant features. Optical Engineering, 2006, 45(3): 1-11

[18] Li L, Qian J, Pan J. High capacity watermark embedding based on local invariant features. In: IEEE International Conference on Multimedia and Expo. 2010, 1311-1314

[19] Li L, Qian J, Pan J. Characteristic region based watermark embedding with rst invariance and high capacity. International Journal of Electronics and Communications, 2011, 65(5): 435-442

[20] Seo J, Yoo C. Localized image watermarking based on feature points of scale-space representation. In: IEEE International Conference Computer Vision Pattern Recognition. 2004, 1365-1375

[21] Seo J, Yoo C. Image watermarking based on invariant regions of scalespace representation. IEEE Transactions on Signal Processing, 2006, 54(4): 1537-1549

[22] Terzija N, Geisselhardt W. A novel synchronisation approach for digital image watermarking based on scale invariant feature point detector. In: IEEE International Conference on Image Processing. 2006, 2585-2588

[23] Gao X, Deng C, Li X, Tao D. Geometric distortion insensitive image watermarking in affine covariant regions. IEEE Transactions on Systems. Man. and Cybernetics Society, 2010, 40(3): 278-286

[24] Matas J, Chum O, Urban M, Pajdla T. Robust wide baseline stereo from maximally stable extremal regions. In: British Machine Vision Conference. 2004, 36-43

[25] Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A, Matas J, Schaffalitzky F, Kadir T, Gool L V. A comparison of affine region detectors. Internation Journal Of Computer Vision, 2005, 65(1-2): 43-72

[26] Matas J, Petr B, Chum O. Rotational invariants for wide-baseline stereo. Research Report of CMP, 2003

[27] Lu S, Sun W, Hsu Y, Chang C. Image quality assessment: From error visibility to structural similarity. IEEE Transactions onMultimedia, 2006, 8(4): 668-685

[28] Wang Z, Bovik A C, Sheikh H R, Simoncelli E P. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Process, 2004, 13(4): 600-612

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg