基于SIFT的区域复制窜改检测算法  

Detection algorithm for region duplication forgery based on SIFT

作　　者：谷宗运[1,2] 吕皖丽[2] 罗斌[2] 

机构地区：[1]安徽中医学院医药信息工程学院,合肥230031 [2]安徽大学计算智能与信号处理教育部重点实验室,合肥230039

出　　处：《计算机应用研究》2011年第12期4760-4762,共3页Application Research of Computers

基　　金：国家自然科学基金资助项目(60772122);安徽省高等学校省级自然科学研究重点资助项目(KJ2007A045)

摘　　要：提出了一种区域复制窜改检测算法,用于检测同幅图像中经几何变换的区域复制窜改问题。先利用SIFT算法提取出图像中SIFT关键点后,再用欧式距离找出所有匹配的关键点,最后根据同一幅自然图像不存在互相匹配的特征点这一特性,判定图像是否被窜改以及定位出被窜改的区域。实验结果表明,算法不仅可以检测出伪造图像中经平移变换的窜改区域,还可以检测出经旋转、缩放以及两者组合的几何变换。与其他的区域复制窜改算法相比,算法对伪造图像的检测有了较大的改进。This paper presented a detection algorithm for a region duplication forgery which could detect the region by geometric transformation. The algorithm firstly extracted the image key points with SIFT algorithm, and then matched them with Euclidean distance. At last, the algorithm could determine whether the image had been tampered and detected the tampered region according to the feature that the feature point did not match one another in a natural image. The experiment verifies the algorithm can not only detect forged images altered by the shift transformation but only detect region by the rotation, scaling, and a combination of both the geometric transformation. The algorithm has been greatly improved compared to other regional replication of tampering methods.

关 键 词：区域复制窜改 SIFT算法 窜改检测 关键点 几何变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]