基于支持向量机的小波域图像水印算法  

Image watermarking technique in wavelet domain based on supportvector machine

作　　者：李三平[1] 张毓森[1] 尹康银[1] 

机构地区：[1]解放军理工大学指挥自动化学院,江苏南京210007

出　　处：《系统工程与电子技术》2008年第2期354-357,共4页Systems Engineering and Electronics

摘　　要：提出了一种新的基于支持向量机(support vector machine,SVM)的小波域图像水印算法。其主要思想是先对图像进行小波分解,然后利用图像小波分解后的子图系数之间的关系训练SVM,并利用训练好的SVM在小波域嵌入水印和提取水印。实验结果表明,提出的方法对于一般的图像处理和JPEG压缩都具有很强的鲁棒性,与基于SVM的空间域上的算法相比性能更加优越。A new image watermarking technique in wavelet domain based on support vector machine（SVM） is proposed. First, the image is decomposed through wavelet transform. Then the relationship between the se lected coefficient and its＇neighboring coefficients is applied to train SVM. The watermark is adaptively embedded in wavelet domain and can also be extracted by the well trained SVM. Experimental results show that the proposed method＇ s performance is better than the one based on SVM in spacial domain in the high robustness to the common image processing and JPEG compression.

关 键 词：图像处理 数字水印 小波域 支持向量机 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]