用于JPEG图像认证的特征水印算法  

JPEG Image Authentication Based on Content Feature Watermarking

作　　者：王津申[1] 戴跃伟[1] 王执铨[1] 

机构地区：[1]南京理工大学自动化学院,南京210094

出　　处：《中国图象图形学报》2008年第7期1265-1271,共7页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60374066)

摘　　要：为了更加快速有效地进行JPEG图像认证,提出了一种基于内容的JPEG特征编码算法。该算法的基本思想是首先采用DCT变换域中不同8×8块之间DCT能量关系来构造特征码;然后在此基础上给出了JPEG图像半脆弱水印方案,即将内容特征码生成方法和水印算法有机地结合在一起。由于特征码具有"半脆弱"特性,即它对于可接受的"内容保持"修改具有鲁棒性,因而对常见的"内容篡改"性修改具有敏感性。另外,由于DCT系数块能量的主要部分集中在低频部分,从而使得可以用低频部分来生成特征码,而且可用高频部分来嵌入水印。实验结果表明,该算法计算简单,不仅有很好的抗JPEG压缩性能,同时对篡改的定位也很精确。A feature coding scheme based on the content of JPEG image was proposed. The basic logic of the scheme is to use partial energy relation between groups of 8 × 8 DCT block to produce related feature code. A semi-fragile watermarking scheme combines correctly the content based feature coding with the watermarking scheme. The feature code has the semi-fragile property, meaning that it is robust to the acceptable ＇ content preserving＇ modifications but sensitive to the ＇ content changing＇ tampering. The lower DCT region is used to form the feature codes while the higher one is used to embed watermarks. The experimental results demonstrate that the proposed algorithm has the advantages such as simple computation complexity, good robustness to JPEG, and precise location of tampered areas.

关 键 词：JPEG图像 水印算法 图像认证 特征码 DCT变换域 半脆弱水印 能量关系 DCT系数 

分 类 号：TP311.56[自动化与计算机技术—计算机软件与理论] TP391.41[自动化与计算机技术—计算机科学与技术]