基于SIFT特征点的三维医学图像零水印算法  

Zero Watermarking Algorithm for 3D Medical Image Based on SIFT Keypoints

作　　者：沈炎斌[1] SHEN Yanbin(Zhicheng College,Fuzhou University,Fuzhou 350002,China)

机构地区：[1]福州大学至诚学院,福建福州350002

出　　处：《贵州大学学报（自然科学版）》2020年第6期92-96,共5页Journal of Guizhou University:Natural Sciences

基　　金：福建省中青年教师教育科研资助项目(JT180810)。

摘　　要：为了在三维医学图像中隐藏病人的个人信息,并对该三维医学图像进行认证,提出了一种基于SIFT特征点的三维医学图像零水印算法,该算法既不会对原始的三维医学图像造成影响,又可以嵌入大容量的水印内容。首先,对三维医学图像进行切片并投影成二维图像;其次,对投影后的图像进行提升小波变换;再次,从小波低频系数中寻找SIFT特征点;最后选择纹理强的区域的SIFT特征点来生成特征向量,用于水印的嵌入。试验表明,该算法可以抵抗常规攻击和几何攻击,具有较强的鲁棒性。In order to hide patient′s personal information in three-dimensional medical image and authenticate the three-dimensional medical image,a zero watermarking algorithm for three-dimensional medical image based on SIFT keypoints is presented,which can not affect the three-dimensional medical image,but can embed large-capacity watermarking content.Firstly,the three-dimensional medical image is sliced and projected into two-dimensional image.Next,the projected image is subjected to a Lifting Wavelet Transform.Then,the SIFT keypoints are found from the low-frequency coefficients of the wavelet.Finally,some SIFT keypoints of the textured areas are selected to generate the feature vectors for embedding the watermarks.Experiment results show that the algorithm can resist conventional attacks and geometric attacks and has strong robustness.

关 键 词：三维医学图像 SIFT 零水印 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]