Geometric Distortions Correction Scheme Based on Hausdorff Distance for Digital Watermarking Image

Abstract

One of the methods for detecting watermarks after geometrical distortions is correcting distorted watermarked image before detecting. In this paper, a definition of weight Hausdorff distance is defined. It is applied to evaluation the similarity between original and geometric distorted watermarking image. A fast divide and conquer strategy in six dimension is used to search the transformation parameters. The geometric distortion is corrected by the parameters. As a result, a distorted watermarking image could be corrected based on image feature.

A robust blind color image watermarking in quaternion Fourier transform domain

“…Then the watermarking image is corrected by affine transform of these match points. In approach (Nian et al, 2010), a definition of weight Hausdorff distance is defined. It is applied to evaluate the similarity between original and geometric distorted watermarking image.…”

Affine invariant image watermarking using intensity probability density-based Harris Laplace detector

“…The watermark extraction is carried out after watermarked image has been synchronized without original image. In [21], a definition of weight Hausdorff distance is defined. It is applied to evaluation the similarity between original and geometric distorted watermarking image.…”

Bayesian Segmentation Based Local Geometrically Invariant Image Watermarking

“…In approach [22], a definition of weight Hausdorff distance is defined. It is applied to evaluation the similarity between original and geometric distorted watermarking image.…”