一种新的复制移动篡改JPEG图像探测方法  

A novel detection method of copy-move forgery in JPEG images

作　　者：赵于前[1] 陈瑜[1] 李香花[2] 廖苗[1] 刘助龙[1] 

机构地区：[1]中南大学地球科学与信息物理学院,湖南长沙410083 [2]中南大学土木工程学院,湖南长沙410075

出　　处：《中南大学学报（自然科学版）》2012年第10期3964-3970,共7页Journal of Central South University:Science and Technology

基　　金：国家自然科学基金资助项目(61172184)

摘　　要：针对JPEG(Joint photographic experts group)图像的复制移动篡改,提出基于SURF(Speeded up robust features)特征匹配与块伪影特征矩阵因子(Blocking artifact characteristics matrix factor,BACMF)的篡改区域快速自动探测与定位方法。首先,应用SURF算法提取待检测图像的特征点和特征向量并进行特征匹配,估计匹配对之间的仿射变换参数并消除错配;然后,通过仿射变换找出趋近完整的复制移动区域;最后,根据各区域的块伪影特征矩阵因子区分复制移动区域中的被复制区域和篡改区域。实验结果证明了该方法对复制移动篡改探测的有效性。Aiming at copy-move forgery in JPEG images, a new method for automatic detection and location of the tampered region was proposed based on speeded up robust features （SURF） matching and blocking artifact characteristics matrix factor（BACMF）. Firstly, image SURF key points were obtained and descriptor vectors were collected at the detected key points. Secondly, the detected key points were collected by computing the Euclidean distance of their descriptor vectors. Next, the matched SURF key points were used to estimate the affine transform parameters. After discounting the estimated transforms, all pixels within the copy-move regions were obtained. Finally, the copied region and the tampered region were distinguished from the copy-move regions according to the BACMFs. The experimental results indicate that the proposed method is effective for the detection and location of copy-move forgery in JPEG images.

关 键 词：数字图像取证 复制移动 SURF JPEG BACMF 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]