A Novel Blind Watermarking Scheme Based on Neural Network in Wavelet Domain

Abstract

This paper proposes a novel digital watermarking technique based on neural networks in wavelet domain. Watermark embed processing is carried out by transforming the host image in wavelet domain. Watermark bits are added to the significant coefficients of wavelet selected by considering the human visual system (HVS) characteristics. Because of the learning and adaptive capabilities of neural networks, the trained neural networks can exactly recover the watermark from the watermarked image. Extensive experiments show that our technique possesses significant robustness to be against the various attacks.