Decision of image watermarking strength based on artificial neural-networks

Digital watermarking is a new technique for digital multimedia copyright protection. The robustness and the imperceptibility are the basic requirements of the digital watermark. The key factor that affects both the robustness and the imperceptibility of the digital watermark is the watermarking strength. In this paper, artificial neural network (ANN) is used to model human visual system (HVS) and an ANN-based image-adaptive method for deciding watermarking strength for image DCT coefficients is presented. The experimental results show that the method can increase the watermarking strength so that the robustness of digital watermark is enhanced and that the method has very good adaptability.