| Abstract: | Localized geometric warping of images is known to be one of the most effective attacks against image watermarking systems. However, the existing local geometrical attacks, when applied to images with regular structures, cause perceptible distortion because they are not adaptive to the content of the images. In this work, we present a multi-scale directional smoothing framework in which local displacement vectors are smoothed by locally adaptive directional kernels. Both the displacement vectors for large structures and those for fine structures are constrained by using a multi-scale pyramid. Subjective tests and objective metrics show that our proposed approach can effectively enhance the perceptual quality of the image after geometric attacks. The test of the attacking effects on two typical watermarking systems demonstrates that our approach does not degrade the attacking effects for Markov random field generated displacement field. |
