A digital watermarking method based on NSCT transform and hybrid evolutionary algorithms with neural networks

This study aims to determine the watermark resistance to different attacks as well as the PSNR level, both of which are essential requirements of watermarking. In our research, we came up with an intelligent design based on NSCT-SVD that fulfills these requirements to a great extent and we managed to use different-sized images for watermark instead of using logos on the host images. Yet we were able to improve PSNR levels and resistance to various attacks. In this paper an NSCT-SVD-based smart watermark model is proposed. We first compare the PSO and PSO-GA algorithms for greater stability using larger SFs obtained by the PSO-GA-AI algorithm. The resulting host image is then decomposed by NSCT transform to obtain images below the low frequency range. Stationary Wavelet Transform (SWT) is performed once on these coefficients and the low frequency coefficients are fed to SVD. Afterwards, SWT transform is performed on the watermark image and the transform is once again taken from the HL coefficients and the LL frequencies are given to the SVD conversion. The rest of image process is insertion. This insertion process dramatically increases the visual transparency and PSNR value. The experiment shows that such a model is able to resist the repeated image attacks with better visibility and power. These results are compared before and after using SWT. We have used a PSO-based algorithm for better results on the False Positive rate in the embedding phase.