C12. A Zernike Moment Based Rotational Invariant Watermarking Scheme

Abstract

Zernike moments (ZM), are extensively used in pattern recognition and image classification. However, they suffer from severe computational errors especially as the moment order increases. In this paper, in order to reduce the effects of these errors and make ZM suitable for image processing applications, it is proposed to use Bspline interpolation to interpolate between image pixels. Due to the smooth and robust performance of Bspline interpolation, significant image quality improvements can be achieved. Having significantly improving the computations of ZM, the paper also proposes to use the rotation invariant feature of ZM, in developing a watermarking scheme that is insensitive to rotations or rotation attacks. In this respect, the Natural Preserving Watermarking technique known for its robustness to cropping, compression and noise attacks has been modified to be rotational invariant using the proposed ZM methods. Several simulation experiments are given to verify these results.