结合多目标演化和图像自身纹理特征的智能水印算法  

An Intelligent Watermarking Algorithm Combining Multi-objective Evolutionary and Image Itself Texture Feature

作　　者：王赛娇[1,2] 袁文强 WANG Saijiao;YUAN Wenqiang(Taizhou Radio & TV University,Taizhou 318000;Computer College,Hangzhou Dianzi University,Hangzhou 310018)

机构地区：[1]台州广播电视大学,台州318000 [2]杭州电子科技大学计算机学院,杭州310018

出　　处：《计算机与数字工程》2019年第6期1472-1477,共6页Computer & Digital Engineering

基　　金：国家自然科学基金青年科学基金项目“基于不确定性分析的高效复杂产品系统优化设计研究”(编号:F020510)资助

摘　　要：数字水印作为一种有效的防伪技术在图像版权保护领域有着广泛的应用。已有的图像水印算法在灵活度、鲁棒性等方面也都有很大的提高,但面临当下大数据时代的海量图片防伪要求,依然不能有效满足。为此,论文提出一种新的图像智能水印解决方案。主要包含两个步骤:1)针对图像数字水印的鲁棒性和透明性两个主要的互相冲突的性能指标,基于多目标演化决策思想求解多个可行的候选嵌入方案;2)对于得到的候选水印嵌入方案,计算载体图片的纹理密度分布,进一步筛选。该方案重点考虑了载体图像本身的纹理特征,智能地选择最优的嵌入方案。文中相关实验验证了论文提出的水印嵌入算法的可行性和有效性。Digital watermarking is an effective anti-forgery technology and has been widely applied in the field of image copyright protection. The existing related image watermarking algorithms also have great improvement in flexibility and weak robustness.However,facing the bulk of anti-forgery requirements in the age of big data,it can not effectively meet the demands. Therefore,this paper presents an intelligent image watermarking solution,which mainly consists of two steps:1)Considering the conflict two objectives-imperceptivity and robustness,a set of watermarking embedding solutions are obtained on the basis of multi-objective evolutionary decision idea. 2)With regard to the obtained watermarking candidates,the texture density distribution of the carrier image is computed to further filter the final optimal embedding solution. This algorithm seriously considers the texture feature of carrier image itself and selects the optimal embedding solution in an intelligent mode. The related experiments have demonstrated the feasibility and effectiveness of the proposed approach.

关 键 词：图像数字水印 多目标演化 图片纹理特征 二进制距离 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]