Object-based watermarking scheme against geometrical attacks

An effective watermarking algorithm using Zernike moments and image normalization is proposed to resist object manipulations. Rotation invariance is achieved by taking the magnitude of the Zernike moments. Image normalization method is used for scale and translation invariance. Watermark signal can be inserted into the Zernike moments of cover image, but the reconstruction procedure is computationally expensive and there is severe fidelity loss. Zero-watermarking technique can solve these problems successfully. Experimental results show that the scheme is robust to compression, filtering, Gaussian noise as well as geometrical attacks including rotation, scaling.