Blind Watermark Algorithm Based on HVS and RBF Neural Network in DWT Domain

This paper proposes a new blind watermarking scheme based on discrete wavelet transform(DWT) domain. The method uses the HVS model, and radial basis function neural networks(RBF). RBF will be implemented while embedding and extracting watermark. The human visual system (HVS) model is used to determine the watermark insertion strength. The neural networks almost exactly recover the watermarking signals from the watermarked images after training and learning. The experimental results show that the watermark proposed in this paper is invisible ( the PSNR is higher than 41) and is robust in the case of against some normal at tacks such as JPEG compression , additive noise and filtering , etc. Key-Words: blind digital watermarking, wavelet transform, RBF neural network, robustness