Digital watermarking based on neural networks for color images
Signal Processing - Special section on digital signal processing for multimedia communications and services
Hi-index | 0.00 |
Moment-domain based watermark can resist geometric attacks but can not be detected blindly. The purpose of this paper is to outline the state of the research of wavelet moment modulation-based watermark and to propose a neural network detection algorithm towards it. With regard to the later we first analyze the computation of the wavelet moment and inverse wavelet moment. Then we focus on watermark added with template embedding and detection based on neural network. Results of the experiments revealed that our watermark detection algorithm is more robust comparing with conventional wavelet-based algorithm. In addition, it detects the watermark blindly.