PERCEIVING DIGITAL WATERMARK DETECTION AS IMAGE CLASSIFICATION PROBLEM

Authors

  • P. Then School of Information Technology and Multimedia, Swinburne University of Technology (Sarawak)
  • Y.C. Wang Faculty of Computer Science and Information Technology,Universiti Malaysia Sarawak

DOI:

https://doi.org/10.33736/jita.52.2007

Keywords:

Support Vector Machine, Digital Watermark, Receiver Operating Characteristics, Stirmark attacks.

Abstract

Digital watermark detection is treated as classification problem of image processing. For image classification that searches for a butterfly, an image can be classified as positive class that is a butterfly and negative class that is not a butterfly. Similarly, the watermarked and unwatermarked images are perceived as positive and negative class respectively. Hence, Support Vector Machine (SVM) is used as the classifier of watermarked and unwatermarked digital image due to its ability of separating both linearly and non-linearly separable data. Hyperplanes of various detectors are briefly elaborated to show how SVM's hyperplane is suitable for Stirmark attacked watermarked image. Cox’s spread spectrum watermarking scheme is used to embed the watermark into digital images. Then, Support Vector Machine is trained with both the watermarked and unwatermarked images. Training SVM eliminates the use of watermark during the detection process. Receiver Operating Characteristics (ROC) graphs are plotted to assess the false positive and false negative probability of both the correlation detector of the watermarking schemes and SVM classifier. Both watermarked and unwatermarked images are later attacked under Stirmark, and then tested on the correlation detector and SVM classifier. Remedies are suggested to preprocess the training data. The optimal setting of SVM parameters is also investigated and determined besides preprocessing. The preprocessing and optimal parameters setting enable the trained SVM to achieve substantially better results than those resulting from the correlation detector.

References

Burges, C. J. C., 1998. A Tutorial on Support Vector Machines for Pattern Recognition, Kluwer Academic Publishers, Boston.

Chen, S., Cowan, F.N., and Grant,P.M., 1999. Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks,IEEE Trans. On Neural Network, 2,2, pp.302-309.

https://doi.org/10.1109/72.80341

Clark,D., Albrecht, D.W., and Tischer, P. 2004. An Investigation into Applying Support Vector Machines to Pixel Classification in Image Processing, 17th Australian Joint Conference on Artificial Intelligence, LNCS 3339 , pp140-151.

https://doi.org/10.1007/978-3-540-30549-1_13

Cox, I.J., Kilian, J. , Leighton, T., and Shamoon, T., 1997. Secure Spread Spectrum Watermarking for Multimedia, IEEE Trans. Image Processing, Vol. 6, No. 12, pp. 1673-1687.

https://doi.org/10.1109/83.650120

Cox, I.J., Miller, M.L., and Bloom, J. 2002. Digital Watermarking, Morgan Kaufmann.

https://doi.org/10.1016/B978-155860714-9/50009-2

Davis, K.J., and Najarian, K.,2001. Maximizing Strength of Digital Watermarks using Neural Networks, IJCNN'01,vol.4,pp. 2893-2898.

Fu, Y. , Shen, R., and Lu, H., 2004. Watermarking Scheme based on Support Vector Machine for Colour Images, IEE Electronic Letters,40,16.

https://doi.org/10.1049/el:20040600

Joachims, T., 1999. Making large-Scale SVM Learning Practical, Advances in Kernel Methods - Support Vector Learning, In B. Schölkopf and C. Burges and A. Smola eds. MIT-Press.

Kalker. T.. 1998. A Security Risk for Publicly Available Watermark Detectors, Benelux Information Theory Symposium, May 98, Veldhoven, The Netherlands.

Kutter, M., and Petitcolas, F.A.P., 1999. A Fair Benchmark for Image Watermarking Systems, Security and Watermarking of Multimedia Contents, In Proc. Of SPIE, 3657, USA.

https://doi.org/10.1117/12.344672

Linnartz, J-P., and van Dijk,M., 1998. Analysis of the Sensitivity Attack against Electronic Watermarks in Images. Information Hiding 1998, LNCS 1525, pp. 258-272.

https://doi.org/10.1007/3-540-49380-8_18

Lou, D.C., Liu, J.L., and Hu, M.C.,2003. Adaptive Digital Watermarking using Neural Network Technique, IEEE 37th Annual 2003 Intl Carnahan Conference on Security Technology, pp.325-332.

Mansour,M.F. and Tewfik,A.H., 2002. Improving the Security of Watermark Public Detectors, In Proceedings of DSP 2002,vol.1,pp.59-66

Mei, S.H., Li,R.H., Dang,H.M., and Wang, Y.K., 2002. Decision of image watermarking strength based on artificial neural-networks, ICONIP 2002,vol.5,pp. 2430-2434.

Petitcolas, F.A.P., and Anderson,R.J., 1999. Evaluation of Copyright Marking Systems. In Proceedings of IEEE Multimedia Systems, vol.1, pp. 574-579.

Petitcolas, F.A.P., Anderson, R.J., and Kuhn, M.G., 1998. Attacks on Copyright Marking Systems, Second workshop on Information Hiding, LNCS 1525, pp.218-238.

https://doi.org/10.1007/3-540-49380-8_16

Picard, J., and Robert, A., 2001. Neural Networks Functions for Public Key Watermarking, IH 2001, LNCS 2137, pp. 142-156.

https://doi.org/10.1007/3-540-45496-9_11

Schőlkpf, B., Sung, K., Burges, C., Girosi, F., Niyogi, P., Poggio, T., and Vapnik,V., 1996. Comparing Support Vector Machines with Gaussian Kernels to Radial Basis Function Classifiers. MIT, AI Lab and Center for Biological and Computational Learning Department of Brain and Cognitive Sciences,A.I. Memo No. 1599, C.B.CL. Paper No. 142.

Schwenker, F., Kestler,H.A., and Palm, G.,2001. Three Learning Phases for Radial-basis-function Networks, Neural Networks, 14, pp.439-458.

https://doi.org/10.1016/S0893-6080(01)00027-2

Shen, M.F., Huang, J., and Beadle, P.J., 2003. Application of ICA to the digital image watermarking, IEEE Intl Conf. on Neural Networks and Signal Processing, vol.2 pp. 1485-1488.

Shieh, C.S., Huang, H.C., and Wang, F.H., 2004. Genetic Watermarking based on Transform-Domain Technique, Pattern Recognition, vol. 37, 3, Elsevier, pp. 555-565.

https://doi.org/10.1016/j.patcog.2003.07.003

Then,H.H. Patrick, and Wang, Y.C., 2006. Support Vector Machine as Digital Image Watermark Detector, Real-Time Image Processing 2006. Edited by Kehtarnavaz, Nasser; Laplante, Philip A. Proceedings of the SPIE, Volume 6964, pp. 478-489.

Then,H.H. Patrick, and Wang,Y.C., 2005. Perceiving Digital Watermark Detection as Image Classification Problem using Support Vector Machine. In Proceedings of CITA05, pp.198-206.

Vapnik, V., 1995. The Nature of Statistical Learning Theory, Springer-Verlag New York, USA.

https://doi.org/10.1007/978-1-4757-2440-0

Vapnik, V., 1998. Statistical Learning Theory, John Wiley, New York, USA.

Webb, A.,2004. Statistical Pattern Recognition, 2nd Ed. Wiley.

Yu, D., and Sattar, F., 2002. A New Blind Watermarking Technique Based on Independent Component Analysis, IWDW 2002, LNCS2613, pp. 51-63.

https://doi.org/10.1007/3-540-36617-2_6

Yu, P.T., Tsai, H.-H., and Lin, J.-S., 2001. Digital Watermarking based on Neural Networks for Color Images, Signal Processing, vol 81,3, Elsevier, pp. 663-671.

https://doi.org/10.1016/S0165-1684(00)00239-5

Zhang, Z.M., Li, R-Y., and Wang, L.,2003. Adaptive Watermark Scheme with RBF Neural Networks, IEEE Int. Conf. Neural Networks & Signal Processing, Nanjing, China, pp.1517-1520.

Downloads

Published

2016-04-26

How to Cite

Then, P., & Wang, Y. (2016). PERCEIVING DIGITAL WATERMARK DETECTION AS IMAGE CLASSIFICATION PROBLEM. Journal of IT in Asia, 2(1), 1–22. https://doi.org/10.33736/jita.52.2007

Issue

Section

Articles