基于SURF和归一化的数字图像零水印算法

A Digital Image Zero-watermarking Algorithm Based on SURF and Normalization

当前,零水印算法计算多比较复杂,不能应用于实时性强的系统。SURF算法是一种尺度不变、旋转不变且性能较好的算法,它的计算量小,很适合应用在对检测速度有要求的平台。图像归一化能使图像在受到一些处理或攻击时在经过相同参数的归一化处理后,得到相同形式的标准图像。利用归一化和SURF特征生成的零水印信息不仅能够抵抗剪切、旋转、JPEG压缩等各种常规攻击,而且支持实时性要求高的系统。实验表明,与其他算法相比,该算法具有较好的鲁棒性和高效性,能够应用于对检测速度有要求的系统平台。

The zero-watermark algorithm is more complex currently in calculation and can not be applied to real-time systems. SURF algorithm is the algorithm of scale-invariant, rotation-invariant and better performance, and it has the small amount of calculation,it is suitable for application in detection speed platform. Image normalization aims to get the standard images after the same parameters normalized what had suffered some processings or attacks. Owned by one and the SURF feature,the zero-watermark is not only able to resist conventional attack, such as scaling, rotation, JPEG compression and so on, but also supports real-time requirements of the system. The experiments show that compared with other algorithms, the algorithm has good robustness and efficiency and can be applied to the platform which has detection speed requirements.