基于显著目标的图像认证与自恢复  

Salient Object Based Image Authentication and Self-recovery

作　　者：石艳娇 张晴 易玉根 SHI Yan-jiao;ZHANG Qing;YI Yu-gen(School of Computer Science and Information Engineering,Shanghai Institute of Technology,Shanghai 201418,China;School of Software,Jiangxi Normal University,Nanchang 330022,China)

机构地区：[1]上海应用技术大学计算机科学与信息工程学院,上海201418 [2]江西师范大学软件学院,南昌330022

出　　处：《小型微型计算机系统》2018年第12期2705-2709,共5页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(61806126;61602221)资助

摘　　要：为实现图像认证与内容保护,提出一种基于显著目标的图像认证与自恢复方法.通过自嵌入水印与无损水印方法的联合使用,实现图像中显著目标与被篡改内容的有效恢复.嵌入信息包括图像的主要信息及显著目标的细节信息,采用参考共享机制进行嵌入.在认证端,一旦判定图像遭受到篡改攻击,被篡改内容及显著目标的细节信息将被进行有效恢复.为保证嵌入端与认证端所提取的显著目标一致,提出使用一种合成图像而非原始图像提取显著目标.实验结果表明,该算法能够定位篡改区域,恢复被篡改内容,并实现显著目标的无损恢复.In order to protect an image,an novel image authentication and self-recovery method based on salient object detection is proposed. By jointly using the self-embedding watermarking and lossless watermarking method,salient object and tampered area can be recovered. The embedded information including the main content of the image and the details of the salient object is embedded under the reference sharing mechanism. At the authentication end,once the image is authenticated as tampered,the tampered contents and the details of salient object can be restored. In order to ensure that the detected salient object at the authentication end is consistent with that at the embedding end,a synthesized image is used to detect the salient object instead of the original image. The experimental results show that the proposed method can locate the tampered area,restore the tampered content and recover salient object losslessly.

关 键 词：图像认证 自嵌入水印 无损水印 显著目标检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]