Affine Correction Based Image Watermarking Robust to Geometric Attacks

How to resist combined geometric attacks effectively while maintain a high embedding capacity is still a challenging task for the digital watermarking research. An affine correction based algorithm is proposed in this paper, which can resist combined geometric attacks and keep a higher watermark embedding capacity. The SURF algorithm and the RANSAC algorithm are used to extract, match and select feature points from the attacked image and the original image. Then, the least square algorithm is used to estimate the affine matrix of the geometric attacks according to the relationship between the matched feature points. The attacks are corrected based on the estimated affine matrix. A fine correction step is included to improve the precision of the watermark detection. To resist the cropping attacks, the watermark information is encoded with LT-coding. The encoded watermark is embedded in the DWT-DCT composite domain of the image. Experimental results show that the proposed algorithm not only has a high embedding capacity, but also is robust to many kinds of geometric attacks.