An improved watermarking method based on neural network for color image
Qianhui Yi, Ke Wang · 2009
In this paper, a novel digital watermarking scheme is devised based on improved Back-Propagation neural network (BPN) for color image. The watermark is embedded into the discrete wavelet domain of the original image and extracted by training BPN, which can learn the characteristic of the image. For improving the performance of traditional BPN, we consider the adding of momentum coefficient to reduce the error and improve the rate of the learning. The watermark can be successfully extracted by training the improved BP neural network, and the watermarking algorithm is good at defending many kinds of common attacks. The experimental results demonstrate that the proposed algorithm has good visual effect and high robustness to general image processing techniques and geometric distortions.