Non-invertible DWT domain image watermarking using human visual model

In recent years, digital watermarking technologies are considered to be important means to protect digital image copyrights. In this paper, we combine a non-invertible watermark scheme with an HVS model adaptive watermark. The application of adaptive watermarks improves visual imperceptibility. However, we find that an adversary is able to apply ambiguity attacks on the non-invertible watermark scheme by using the adaptive coefficients information. We then propose a solution resisting this kind of attacks by making a restriction on the adaptive coefficients. As a result, the adaptive and non-invertible watermark scheme is visually imperceptible, robust and resistant to ambiguity attacks. In addition, we give a theoretic formula for calculating the global watermark intensity from PSNR (peak signal to noise ratio).