Robust Digital image watermarking method using Graph-based transform(GBT) and Genetic Algorithm

Numerous methods have been introduced for digital images watermarking as well as rubosting them. In this method, with using Graph-based transform and extracts the best graph structure with genetic algorithm so that watermarking can be performed with maximum robustness. One of the common methods in watermarking robustness is the use of discrete cosine transform (DCT). In this study, we have shown that the proposed method is much more powerful than DCT. The proposed method is tested on five different color images such as Lena, Barbara, Boat, Baboon, Peppers. Watermark image (logo) is a random binary image with size 16 x 16 and 8 x 8 pixels. This simulation results show that the proposed method is more robust to similar methods such as discrete cosine transforms. Proposing Watermarking has been evaluated using Bit Error Rate (BER), Structural Similarity Index Measuring (SSIM) and Peak signal-to-noise ratio (PSNR) criteria and different strength Gaussian noise attacks, JPEG compression, median filter, bluring, rescaling, rotate and cropping attacks