基于伪Zernike矩与SURF特征的自适应水印算法

Adaptive Watermarking Algorithm Based on Pseudo-Zernike Moments and SURF Features

针对目前多数图像水印算法水印的嵌入区域固定不变带来的安全性问题,且水印的抗旋转攻击能力弱,提出一种基于伪Zernike矩和SURF的自适应水印算法。首先,利用SURF(Speed Up Robust Features)算法对图像进行特征提取,然后采用RANSAC(Random Sample Consensus)算法筛选出稳定的特征点,根据特征点位置构建合适的水印嵌入区域。最后,采用SWT变换和SVD分解将水印信息嵌入在构造区域内。利用伪Zernike矩估计旋转角度对图像进行旋转校正。实验结果表明,该水印算法可以有效地抵抗旋转攻击,水印的安全性得到提高。

Aiming at the security problems caused by the fixed embedding area of the watermark in most current image water-marking algorithms and the weak anti-rotation attack ability of the watermark,an adaptive watermarking algorithm based on pseu-do-Zernike moments and SURF is proposed.First,the SURF(speed up robust features)algorithm is used to extract the features of the image,and then the RANSAC(random sample consensus)algorithm is used to screen out stable feature points,and a suitable watermark embedding area is constructed according to the position of the feature points.Finally,SWT transform and SVD decompo-sition are employed to embed the watermark information in the constructed region.Rotation correction is performed on the image by estimating the rotation angle using pseudo-Zernike moments.The experimental results show that the watermarking algorithm can ef-fectively resist the rotation attack,and the security of watermarking is improved.