An improved wavelet-based image watermarking technique

This paper proposes an adaptive blind image watermarking technique based on wavelet transform using a random sequence of real numbers. First, the image is decomposed into non overlapping blocks. Then, each block is classified as uniform or non uniform by using a JND-based classifier. The strength of the embedded watermark into the high subband coefficients of each transformed block depends upon the nature of the block according to its classification. The Neyman-Pearson criterion is used to derive the detection rule. Unlike the embedding process, the detection does not require any classification of blocs. This adaptive approach has been assessed on various standard images and compared with a similar watermarking technique (H. Inoue et al., 1999). The results have shown an obvious improvement in terms of robustness against different manipulations and a better ability of detection