傅里叶-梅林变换的图像复制篡改检测

Detection of image copy-move tamper using Fourier-Mellin Transform in digital forensics

篡改检测已经成为数字图像取证的重要方法。虽然大多数情况下数字图像篡改都难以感知,例如区域复制篡改,它将图像中的对象区域复制到不交叠的其它区域,但仍然会留下少许篡改痕迹。提出了一种新的针对图像区域复制篡改的检测模式。其中,利用傅里叶-梅林变换提取图像块的几何不变量特征,相似性匹配则采用余弦相关系数。通过MATLAB仿真实验,验证了该算法不但可以适应平移、旋转及缩放等几何变换,而且能够有效抵抗噪音污染、模糊滤波以及有损JPEG压缩等攻击。

Tamper detection has become an important component of digital image forensics and multimedia security.In most of the time,digital image tamper is not perceptible by human,however,some traces of digital tamper may be left in the image during the manipulation.This paper proposes a novel scheme to detect and identify the location of image copy-move tamper in which an object region in the image is copied and pasted somewhere else in the same image to confound right and wrong.The Fourier-Mellin Transform（FMT） serve to produce a translation,rotation and scale invariant of local image patches,suspected to be a copy,and cosine correlation coefficient is considered for similarity metric.Experimental results also demonstrate the efficacy of the proposed approach to tampered images by geometric transformations（i.e.translation,rotation and scale） undergone some attacks like blur filter,random noise contamination,lossy JPEG compression,etc.