基于Sift特征区域的遥感图像水印算法  

A Watermarking Algorithm for Remote Sensing Image Based on Sift Feature Region

作　　者：李丽丽[1] 孙劲光[2] 

机构地区：[1]辽宁工程技术大学测绘与地理科学学院,辽宁阜新123000 [2]辽宁工程技术大学电子与信息工程学院,辽宁葫芦岛125105

出　　处：《计算机测量与控制》2012年第5期1410-1413,共4页Computer Measurement &Control

基　　金：国家自然科学基金项目(41101452);辽宁省教育厅基金项目(L2010158)

摘　　要：针对现有遥感图像数字水印算法多为全局水印算法,抵抗旋转、缩放、行列剪切及联合几何攻击能力较差的问题,提出一种基于Sift特征区域的局部化遥感图像水印算法;算法依据密钥生成一个伪随机序列,对其实施二值化,并选取64bit一段作为待嵌入的水印;在截选256×256宿主遥感图像中提取Sift特征点,筛选特征点确定水印嵌入特征区域;最后,根据待嵌入的水印信息,将所选特征区域进行扇区划分,利用奇偶量化方法将水印嵌入其中;实验表明算法对JEPG压缩、噪声及滤波等常规信号处理具有较好鲁棒性,并且能够更好地抵抗旋转、缩放、平移及其联合等几何攻击。Against most of existing watermarking algorithms for remote sensing image are global algorithms, their resistance to rotation, scaling, ranks of shear and combined geometric attack is poor. It proposes a localized watermarking scheme for remote sensing image based on Sift feature region. It generates a random sequence through the key, and selects a 64--hit paragraph of the values as watermark after binari zation; then it extracts Sift feature points in the 256 × 256 host remote sensing image, filters the feature points and determines feature regions for watermark embedding; finally, it divides the selected region into sectors according to the watermark, and embeds the watermark into it by odd-- even quantization method. Experiments have shown that the algorithm has good robustness against conventional signal processing such as JPEG- compression, noise attacking, filtering, etc. , and it better resists to geometric attacks such as rotation, scaling, moving and their combination.

关 键 词：数字水印 遥感图像 SIFT 特征区域 几何攻击 

分 类 号：TP309.2[自动化与计算机技术—计算机系统结构]