Conference Paper

Image Watermarking based on Genetic Algorithm.

DOI: 10.1109/ICME.2006.262731 Conference: Proceedings of the 2006 IEEE International Conference on Multimedia and Expo, ICME 2006, July 9-12 2006, Toronto, Ontario, Canada
Source: DBLP

ABSTRACT In order to improve the robustness and imperceptibleness of the image spread spectrum watermark algorithm, a new approach for optimization in 8×8 DCT domain using genetic algorithm (GA) was proposed. GA was used to choose the AC coefficients, which were modified to embed the spread spectrum watermark. The bands were varied to find the most suitable for image with different characteristics. Performance improvement with respect to existing algorithm is obtained by GA adaptive global search. The experimental results show that the proposed algorithm yields a watermark that is invisible to human eyes and robust to various image manipulation, and show that some special positions are the best choices for embedding the watermark. The authors also compare their experimental results with the results of the previous work of others.

1 Bookmark
  • [Show abstract] [Hide abstract]
    ABSTRACT: In Digital Watermarking a low energy signal is imperceptibly embedded in another signal. The low energy signal is called watermark. Earlier techniques based on spatial and frequency domain, had the problems of a poor fidelity especially with higher payloads of watermark image. Unsatisfactory value of Peak Signal to Noise Ratio (PSNR) of watermarked image resulting in image quality degradation was seen in varying degree, in various research works. This paper is an attempt to employ genetic algorithms to find suitable locations for watermark insertion within a cover image, to focus on the issue of optimizing fidelity. The paper uses a roulette-wheel selection strategy in genetic algorithm and investigates the variation of maximum fitness which reflects the higher PSNR of the watermarked image with respect to embedding strength, number of genes, and incremental payloads of watermark consisting of binary matrix. With the proper understanding and analysis of the results of this paper, a successful watermarking scheme can be obtained using Genetic algorithms, which may be useful when optimizing the fidelity aspect of digital watermarking.
    Computational Intelligence and Communication Networks (CICN), 2010 International Conference on; 12/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Imperceptibility or quality for digital image watermarking represents one of the most important requirements for any digital watermarking system. Many studies try to enhance the quality by using different techniques and methods. In this study, Genetic Algorithm (GA) method is used to embed two bits of watermarking data within every pixel of original image and to find the optimal value based on the existing Dual Intermediate Significant Bit (DISB). However, if the two embedded bits is equal to the original bits then this means the watermarked image is still the same as the original one without any changing, while in the other case GA is used getting the minimum fitness value in which the fitness is the absolute value between the pixel and chromosome and the value of chromosome between 0-255. The results show that the new method improves the image quality and get the optimal value for the two embedded bits.
    Advanced Computer Science Applications and Technologies (ACSAT), 2012 International Conference on; 01/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: Watermarking methods in transform domains are usually achieved using the discrete cosine transform or the discrete wavelet transform. In this paper, we develop a technique for optimizing the image watermarking using the genetic algorithm applied to the double-density dual-tree discrete wavelet transform which improves the quality of the watermarked image and the robustness of watermark. We employ, genetic algorithm based embedding schemes namely surrounding mean and zero tree embedding approach. The detection process can be performed without using the original image. The experimental results demonstrate that the watermark is robust to attacks.
    Wavelet Analysis and Pattern Recognition, 2008. ICWAPR '08. International Conference on; 10/2008


Available from