Optimal Dual Watermarking of Color Images with SWT and SVD Through Genetic Algorithm

An optimized color image watermarking algorithm with stationary wavelet transform and singular value decomposition has been proposed in this work. The algorithm uses two watermarks to address the issues of copyright protection and tamper localization. A gray-scale image watermark is embedded in the transform domain of the green plane of the cover image to address the issue of copyright protection. A binary logo watermark is inserted in the spatial domain of the blue plane of the cover image by the least significant bit approach. It helps to locate the visible and invisible tampers in the cover image. This work is optimized through the genetic algorithm (GA) to achieve better perceptual quality and robustness. A novel fitness function has been proposed to use with the GA to figure out an optimal scaling factor for the embedding process. The strength of the algorithm has been examined by enforcing several attacks on the watermarked image. The embedding capacity of the algorithm and the time complexity of the proposed fitness function are compared with other existing works.