Blind watermarking scheme based on neural network

A novel blind watermarking technique based on back propagation neural networks is proposed. The proposed watermarking technique hides a scrambled watermark into an image, and takes HVS characteristics into consideration during the watermark embedding process, then uses a back propagation neural network to learn the characteristics of the embedded watermark related to the watermarked image. With the aid of the learning and adaptive capabilities of neural network, the trained neural network can exactly recover the watermark from the watermarked image. Extensive experiments show that the proposed watermarking algorithm has a good imperceptibility and high robustness to various common image processing attacks.