基于BAG误匹配的JPEG窜改图像的被动检测算法  

Passive detection of doctored JPEG image via BAG mismatching

作　　者：张鑫[1] 周尚波[1] 

机构地区：[1]重庆大学计算机学院,重庆400044

出　　处：《计算机应用研究》2012年第12期4626-4630,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(60873200;1004112);211工程第3期资助项目(S-10218)

摘　　要：当JPEG图像被窜改时,通过检测人工的块状网格BAG(block artifact grid)误匹配的痕迹,可以判定待检测图像是否被窜改过,但这种算法有较高的虚警率,提出一种改进算法。首先利用BAG误匹配原理检测图像,再在疑似窜改区域检测竖直方向和水平方向上是否同时存在相邻BAG的边缘,从而将窜改区域与偶发噪声点区域分开,最后对全图进行形态学处理,进一步消除噪声。实验证明,该算法可以在有效检测窜改区域的情况下,降低算法的虚警率,在数字图像的被动检测领域有广泛的应用前景。When JPEG image is tampered with,researchers could distinguish a detected image which may be changed or not according to the trace of BAG mismatching.But this algorithm produce high false alarm rate.This paper proposed a method which could improve original algorithm.Firstly,it detected an image based on the principle of BAG mismatching.Secondly,it could make use of the edge of adjacent BAG in vertical and horizontal direction to make a distinction between doctored region and accidental noisy point in doubtful region of the image.Finally,in order to reduce more noise,morphology processing was performed on the image.The experiment demonstrates that the algorithm can lower false alarm rate with effective detection and will be applied widely in the region of passive detection of digital image.

关 键 词：JPEG图像 人工块状网格 窜改 虚警率 被动检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]