DAMAGELESS DIGITAL WATERMARKING USING COMPLEXVALUED ARTIFICIAL NEURAL NETWORK

Abstract

Several high-ranking watermarking schemes using neural networks have been proposed in order to make the watermark stronger to resist attacks. However, the current system only deals with real value data. Once the data become complex, the current algorithms are not capable of handling complex data. In this paper, a distortion-free digital watermarking scheme based on Complex-Valued Neural Network (CVNN) in transform domain is proposed. Fast Fourier Transform (FFT) was used to obtain the complex number (real and imaginary part) of the host image. The complex values form the input data of the Complex Back-Propagation (CBP) algorithm. Because neural networks perform best on detection, classification, learning and adaption, these features are employed to simulate the Safe Region (SR) to embed the watermark, thus, watermark are appropriately mapped to the mid frequency of selected coeffi cients. The algorithm was appraised by Mean Squared Error MSE and Average Difference Indicator (ADI). Implementation results have shown that this watermarking algorithm has a high level of robustness and accuracy in recovery of the watermark.