Robust Feature Region Set For Digital Image Watermarking

The main objective of the paper is to select a novel feature region for robust digital image watermarking. The method used select a no overlapping feature region set, which has the greatest robustness against various attacks and can preserve image quality as much as possible after watermarked. To evaluate the robustness of every candidate feature we first perform a simulated attacking procedure using some predefined attacks. That evaluation results are track-with-pruning procedure to search a primary feature set. Then preserving the image quality, we extended the primary feature set by adding into some auxiliary feature regions. This work is formulated as a multidimensional knapsack problem and solved by a genetic algorithm based approach. By comparing and evaluate the result of both primary and extended feature region set results, the proposed method exhibits better performance in robust digital watermarking.