基于压缩感知和模糊理论的鲁棒数字水印算法  

Robust digital watermarking algorithm based on compressed sensing and fuzzy theory

作　　者：高晓玲[1] 马旭 

机构地区：[1]宁夏大学新华学院,宁夏银川750021 [2]宁夏师范大学数学与计算机科学学院,宁夏固原756099

出　　处：《计算机工程与设计》2017年第10期2672-2677,共6页Computer Engineering and Design

基　　金：宁夏高等学校科学技术研究基金项目(NGY2015184)

摘　　要：很多基于变换域的数字水印算法在完整性和鲁棒性方面表现较差,针对此问题,提出一种基于压缩感知和模糊理论的水印算法。利用非下采样Contourlet变换(NSCT)将载体图像稀疏分解,得到低频系数矩阵;运用模糊理论获得观测值,这些观测值可用于水印的嵌入;稀疏信号可通过子空间追踪(SP)算法恢复,重构图像通过NSCT逆变换完成。实验结果表明,该算法满足了水印的隐蔽性,表现出对常见的攻击的强鲁棒性,信息安全得到了明显提升,与其它同类算法相比,大多数情况下,其具有更高的峰值信噪比(PSNR),结构相似性度量(SSIM)和归一化互相关(NCC)函数值。Integrity and robustness of many digital watermarking algorithms based on transform domain are poor.To solve the problem,a digital watermarking algorithm based on compressed sensing and fuzzy theory was proposed.Non-subsampled Contourlet transform（NSCT）was used for the sparse decomposition of the carrier image,obtaining low-frequency coefficient matrix.The observed values were got through fuzzy theory and these observations were used for the embedding of watermarking.The sparse signal was recovered using the subspace pursuit（SP）algorithm,and the reconstructed image was replaced through the NSCT inverse transform.Experimental results show that the proposed algorithm not only meets the watermarking invisibility,but also shows the strong robustness to the common attacks,so the information security is significantly improved.Compared with other similar algorithms,in most cases,the presented algorithm has higher values of peak signal to noise ratio（PSNR）,structural similarity measure（SSIM）and normalized cross correlation（NCC）function.

关 键 词：数字水印 压缩传感 模糊理论 子空间追踪算法 CONTOURLET变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]