基于混沌和SVD-DWT的稳健数字图像水印算法  

Robust digital image watermarking algorithm based on chaos and SVD-DWT

作　　者：张秋余[1] 李凯[1] 袁占亭[1] 

机构地区：[1]兰州理工大学计算机与通信学院,兰州730050

出　　处：《计算机应用研究》2010年第2期718-720,共3页Application Research of Computers

基　　金：国家自然科学基金资助项目(60572011);甘肃省自然科学基金资助项目(0803RJZA024)

摘　　要：针对现有适用于图像的数字水印对信号处理和几何失真比较敏感的问题,提出一种稳健的数字图像水印算法。该算法先对整个图像应用三级离散小波变换,再对低频域运用奇异值分解,并通过修改奇异值,嵌入经过混沌置乱的水印图像的奇异值,在小波变换域的中频系数上嵌入水印信息。水印检测时,分别在中频区域和低频提取水印并进行比较,采用效果较好的水印作为检测水印。实验结果表明,该方法对一般的信号处理操作及几何攻击等均具有较好的鲁棒性。Many digital watermarks now available for images are sensitive to signal processing and geometric distortions, this paper proposed a robust digital image watermarking algorithm, After decomposing the whole image with 3 level of discrete wavelet transform,then applyed the singular value decomposition（SVD） to the low frequency domain, and embedded the singular values of the watermark image that was decomposed with SVD after chaotic scrambling by modifying the singular values, and embedded the watermark data to the middle frequency coefficients of wavelet domain ; extracted watermarks in the intermediate frequency and low frequency region and compare them, using the extracted watermark which was better. The examination algorithm of watermark used the double watermark comparison examination. The experimental results demonstrate that this proposed watermarking algorithm is robust against some common signal processing and geometric attacks.

关 键 词：稳健性 混沌 离散小波变换 奇异值分解 数字水印 

分 类 号：TN912.34[电子电信—通信与信息系统]