基于Schur分解的Contourlet域彩色图像零水印算法  

Zero-watermarking Algorithm for Color Image in Contourlet Domain Based on Schur Decomposition

作　　者：朱春伟 李永毅 迟万达 高尚 范迪[1] ZHU Chun-wei;LI Yong-yi;CHI Wan-da;GAO Shang;FAN Di

机构地区：[1]山东科技大学,山东青岛266590

出　　处：《信息技术与信息化》2019年第2期89-93,共5页Information Technology and Informatization

摘　　要：针对数字水印技术中鲁棒性和不可见性平衡的问题,本文提出了一种基于Schur分解的Contourlet域彩色图像零水印算法。算法对图像的YCoCg颜色空间的Co分量进行两层Contourlet变换,对其低频子带的DCT变换结果进行分块和Schur分解,利用子块的最大特征值构造过渡矩阵并进而形成特征矩阵,并与加密水印异或得到零水印。算法利用YCoCg彩色空间转换无损的特点及CT、DCT和Schur分解的优良特性,运算比较简单,同时因对载体图像无介入,确保了不可见性。实验结果表明,算法对噪声、JPEG压缩、缩放、剪切、旋转等多种攻击具有较强的鲁棒性,在抗缩放、旋转攻击方面效果尤为突出。To balance robustness and invisibility in digital watermarking technology,a zero-watermarking algorithm for color image in Contourlet domain based on Schur decomposition is proposed in this paper.The Co component of YCoCg color space is transformed by two-layer Contourlet transform(CT),and the DCT transform results of its low-frequency subband are divided into blocks and decomposed by Schur respectively.The transition matrix is constructed by the maximum eigenvalue of the subblocks.Then the feature matrix is formed,and the zero watermarking is obtained by operating feature matrix and encrypted watermark image with XOR.The algorithm takes advantages of the non-destructive characteristics of YCoCg color space conversion and the excellent characteristics of CT,DCT and Schur decomposition,and its operation is relatively simple.At the same time,the algorithm does not interfere with the carrier image and ensures the invisibility.The experimental results show that the algorithm has strong robustness against noise,JPEG compression,scaling,shearing,rotation and other attacks,especially in scaling and rotation attacks.

关 键 词：零水印 CONTOURLET变换 SCHUR分解 鲁棒性 YCoCg颜色空间 

分 类 号：TP309.7[自动化与计算机技术—计算机系统结构]