联合SIFT特征点和CS-LBP特征描述子的复制粘贴篡改检测  

Copy-paste forgery detection using SIFT key-points and CS-LBP descriptor

作　　者：刘丹[1] 胡永健[1] 刘琲贝[1] 

机构地区：[1]华南理工大学电子与信息学院,广东广州510640

出　　处：《合肥工业大学学报（自然科学版）》2012年第3期325-330,共6页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(60772115)

摘　　要：针对现有数字图像复制-粘贴篡改检测中尺度不变特征变换(Scale Invariant Feature Transform,简称SIFT)算法计算复杂度高的问题,文章提出一种将SIFT特征点和中心对称局部二进制模式(Center Symmet-ric-Local Binary Pattern,简称CS-LBP)描述子相结合的篡改检测方法。首先提取SIFT关键点,再对每个关键点生成CS-LBP特征描述子,并利用K-D(k-dimensional)树和BBF(Best-Bin-First)搜索算法寻找符合特征匹配关系的匹配点对,判断是否存在图像区域的篡改。实验表明,与同类算法相比,所提出算法在不损失检测精度的同时有效地减少了运算量。The existing scale invariant feature transform（SIFT）-based detection algorithm for copy-paste forgery has high computational complexity.To solve this problem,a new algorithm using the SIFT key-points and center symmetric-local binary pattern（CS-LBP） descriptor is proposed.Firstly,the SIFT key-points are determined by using the SIFT algorithm.Secondly,the CS-LBP descriptor for each key-point is generated.Finally,the k-dimensional（K-D） tree and the best-bin-first（BBF） search algorithm are used to locate the matched pairs of key-points and to determine whether there is any copy-paste forgery in the image.Experimental results show that compared with other algorithms,the proposed algorithm remarkably reduces the computational load under the same detection accuracy.

关 键 词：复制-粘贴篡改 尺度不变特征变换 中心对称局部二进制模式 特征匹配 BBF搜索算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]