一种基于顺序QR分解和AdaBoost分类器的盲水印算法  

New blind watermarking algorithm based on sorted QR decomposition and Ada Boost classifier

作　　者：巫朝霞[1] 郑盼盼[1] 

机构地区：[1]新疆财经大学应用数学学院,乌鲁木齐830012

出　　处：《计算机应用研究》2016年第11期3464-3467,共4页Application Research of Computers

基　　金：新疆自然科学基金资助项目(2014211A001)

摘　　要：提出了一种基于顺序QR分解和Ada Boost分类器的智能水印算法。对顺序QR分解并提取R矩阵的对角线元素来构造样本特征向量并嵌入水印。在水印提取过程中,利用Ada Boost分类器对待检测的样本向量进行分类。实验结果表明,提出的方法不仅能够抵抗诸如噪声、滤波和压缩的类噪声攻击,也可以抵抗类似裁剪和旋转的几何失真。This paper presented a novel intelligent watermarking algorithm based on sorted QR decomposition and AdaBoost classifier. For embedding watermark, this algorithm decomposed a matrix by sorted QR decomposition and extracted diagonal el- ements of R matrix to construct feature vectors of samples. For extracting watermark, it used AdaBoost classifier to classify the feature vectors of detected samples. Experimental results shows that the proposed solution can not only resist noise-like attacks such as noise ,filtering and compression, but also resist geometric distortion such as cutting and rotating.

关 键 词：数字水印 排序QR分解 ADA Boost分类器 几何失真 

分 类 号：TP309.7[自动化与计算机技术—计算机系统结构]