一种基于Slant变换和SVD的稳健性数字水印算法  

A robust digital watermarking algorithm based on Slant transform and SVD

作　　者：肖振久[1] 郭冰莹 李南[1] 唐晓亮[1] XIAO Zhen-jiu;GUO Bing-ying;LI Nan;TANG Xiao-liang(College of Software,Liaoning Technical University,Huludao 125105,China)

机构地区：[1]辽宁工程技术大学软件学院,辽宁葫芦岛125105

出　　处：《计算机工程与科学》2018年第10期1772-1779,共8页Computer Engineering & Science

基　　金：国家自然科学基金(61401185)

摘　　要：针对奇异值分解(SVD)存在的虚警错误和水印隐蔽性与鲁棒性的矛盾问题,提出了一种基于Slant变换和SVD的稳健性数字水印算法。对二值水印图像进行Arnold置乱和Logistic映射双因子加密预处理,增强水印信息安全性;将原始载体图像分成8×8不重叠子块分别对其进行Slant变换和块奇异值分解;然后将水印图像SVD后的左奇异矩阵和奇异值矩阵相乘作为水印主成分嵌入到每个子块的最大奇异值中。仿真实验结果表明,该算法不仅有效解决了传统SVD水印算法的虚警问题,提升了运行速度和水印安全性,在具有较好隐蔽性的同时,对JPEG压缩、噪声、滤波、几何攻击等也有较好的稳健性。Aiming at the false alarm errors of singular value decomposition(SVD)and the contradiction between robustness and invisibility of watermarking,we present a robust digital watermarking based on Slant transform and SVD.Firstly,the watermarking image is pretreated by the two-factor encrypting processing of Arnold scrambling and Logistic mapping.The original host image is divided into 8*8 non-overlapping sub-blocks,and then the sub-blocks are transformed by Slant transform and decomposed by the blocked SVD.Thirdly,left singular matrix and singular value matrix of the watermarking image after SVD processing are multiplied as watermarking principal components to embed into the maximum singular value of each sub-block.Simulation results show that the proposed watermarking algorithm not only effectively solves the problem of false alarm problem of the traditional SVD watermarking algorithm,but also improves the running speed and watermarking security.At the same time,it has better visibility and robustness to common attacks such as JPEG compression,noise,filtering and geometric attacks.

关 键 词：Slant变换 奇异值分解 LOGISTIC映射 水印主成分 虚警错误 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]