基于LASSO的可逆图像水印算法  

LASSO based image reversible watermarking

作　　者：郑鸿昌 王春桃[1] 王俊祥 ZHENG Hongchang1, WANG Chuntao1, WANGJunxlang2(1. College of Mathematics and Informatics, South China Agricultural University, Guangzhou Guangdong 510642, China; 2. School of Mechanical and Electrical Engineering, Jingdezhen Ceramic Institute, Jingdezhen Jiangxi 333403, Chin)

机构地区：[1]华南农业大学数学与信息学院,广州510642 [2]景德镇陶瓷大学机械电子工程学院,江西景德镇333403

出　　处：《计算机应用》2018年第8期2287-2292,共6页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61672242;61762054)~~

摘　　要：对于采用差值扩展-直方图平移的可逆水印算法,提高预测的准确度有利于减小预测误差,从而在同等嵌入失真时获得更大的嵌入容量。为了进一步提高图像像素预测的准确度,构造了一种基于LASSO(Least Absolute Shrinkage And Selection Operator)的局部预测算法。具体而言,根据图像存在边缘、纹理方向的特点,将图像像素预测问题表征为基于LASSO的优化问题;然后通过优化求解得到预测系数,进而得到预测误差;随后利用预测误差,结合差值扩展-直方图平移嵌入技术设计可逆图像水印算法。实验仿真结果表明,与当前预测性能较好的、基于最小二乘局部预测的可逆图像水印算法相比,所提算法在嵌入相同的数据时拥有更高的峰值信噪比(PSNR)。For the Difference Expansion-Histogram Shifting（ DE-HS） based reversible watermarking,improving the prediction accuracy helps to decrease the prediction errors,resulting in higher embedding capacity at the same embedding distortion. To predict image pixels more accurately,an LASSO（ Least Absolute Shrinkage and Selection Operator） based local predictor was proposed. Specifically,by taking into account the fact that there exist edges and textures in natural images,the problem of image pixel prediction was formulated as the optimization problem of LASSO,then the prediction coefficients were obtained by solving the optimization problem,generating prediction errors accordingly. By applying the technique of DE-HS on the yielded prediction errors,an LASSO-based reversible watermarking scheme was designed. The experimental results show that compared with the least-square-based predictor,the proposed scheme has higher Peak Signal-to-Noise Ratio（ PSNR）when embedding the same data.

关 键 词：可逆水印 预测误差 差值扩展 局部预测 直方图平移 

分 类 号：TP309.2[自动化与计算机技术—计算机系统结构]