A new robust digital watermarking algorithm based on genetic algorithms and neural networks
Prayoth Kumsawat, Kasama Pasitwilitham, Kitti Attakitmongcol, Arthit Srikaew · 2011
This paper proposes a new robust digital image watermarking algorithm using genetic algorithms and neural networks in the multiwavelet domain. The embedding technique is based on the quantization index modulation and the watermark extraction process does not require the original image. We have developed an optimization technique using the genetic algorithms to search for optimal quantization steps to improve the quality of watermarked image and robustness of the watermark. In addition, we construct a prediction model based on image moments and back propagation neural network to correct an attacked image geometrically before the watermark extraction process begins. The experimental results show that the proposed watermarking algorithm yields watermarked image with good imperceptibility and very robust watermark against various common image processing attacks and general geometrical distortions.