Abstract

We propose a novel gray scale image watermarking scheme using hybrid DCT-DWT transform. The low frequency band coefficients are selected and the dataset of size 256*7 prepared using these coefficients is supplied to a newly developed simple layer feed forward network popularly known as Extreme Learning Machine (ELM). The ELM produces a normalized column vector of size 256*1 which is used as watermark sequence to be embedded in the low frequency coefficients. The DWT-DCT hybrid transform is supposed to produce better results for imperceptibility criteria. Five different image processing attacks are carried out over signed images. Watermarks are extracted successfully from signed and attacked images. Time complexity calculation indicates that the watermarking scheme is completely executed within seconds which makes it suitable for real time watermarking applications. .

References

• I. J. Cox, Joe Kilian, F. Thomson Leighton and Talal Shamoon, "Secure Spread Spectrum Watermarking for Multimedia", IEEE Transactions on Image Processing, vol. 6, no. 12 (1997) pp. 1673-1687
• M. Kutter and F. Petitcolas, "A fair benchmark for image watermarking systems," Electronic Imaging 199: Security and Watermarking of Multimedia Content, Vol. 3657 of SPIE Proceedings, San Jose, California USA, 25-27
• Charu Agarwal and Anurag Mishra, "A Novel Image Watermarking Technique using Fuzzy-BP Network", (2010) Proceedings of 6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 102 – 105
• Charu Agarwal, Anurag Mishra and Arpita Sharma, "Gray-Scale watermarking using GA-BPN Hybrid Network", (2013), Journal of Visual Communication and Image Representation, Vol 24, pp. 1135 – 1146
• M-B. Lin, G-B Huang, P. Saratchandran and N. Sudararajan, "Fully complex extreme learning machine", Neurocomputing, (2005), vol (68), pp 306 – 314
• G-B Huang, Q-Y Zhu and C K Siew, "Extreme Learning Machine: Theory and Applications", (2006), Neurocomputing, vol (70), pp 489-501
• G-B Huang, Q-Y Zhu and C K Siew, "Real-Time Learning Capability of Neural Networks", (2006), IEEE Transactions on Neural Networks, vol 17(4), pp 863-878
• G-B Huang (2004), The Matlab code for ELM is available on: http://www. ntu. edu. sg/home/egbhuang
• S. K. Amirgholipour, A. R. Naghsh-Nilchi, "Robust Image Watermarking Based on Joint DWT-DCT,", International Journal of Digital Content Technology and its Applications, vol 3, pp. 42-54, 2009
• J X Liu and Z M Lu,. "DWT and DCT Combined Robust Watermarking Algorithm Based on Vector Quantization with Labeled Codewords," Proc. IEEE Conf, Anti-counterfeiting, Security, and Identification in Communication (ASID'08), IEEE press, Nov. 2008, pp. 51- 54