Reversible Image Watermarking Based on Genetic Algorithm
Yueh Hong Chen, Hsiang Cheh Huang · 2014
Hiding data into images can be referred to as a constrained optimization problem. Hence, we proposed a reversible genetic watermarking scheme based on the wavelet packet transform in this paper. Genetic algorithm is used to select an appropriate basis from permissible bases of wavelet packet transform to increase the robustness of the embedded data, and the binary string to be hidden is embedded into middle and high frequency coefficients of the wavelet packet transform. The scheme to embed each binary value a modified version of "difference expansion". Experimental results show that the proposed method can resist some image processing methods, such as sharping operation, while keeping cover image quality and the amount of hidden data acceptable in real world applications.