Minimization of Effect of various Attacks on Watermarked Images using Back Propagation Neural Network in DWT Domain

Watermarked images are affected by various attacks such as cropping, salt &pepper noise and rotation. These attacks destroy the inserted watermark, so that the copyright problem may arise. The effect of these attacks can be reduced by properly inserting the watermark with effective algorithm. In this paper, a robust blind transform domain based algorithm using Back Propagation Neural Network is proposed. The proposed algorithm is robust to cropping, salt &pepper noise and rotation attacks compared to other algorithms.