基于小波和不变矩的图像copy-move篡改盲检测

针对数字图像取证中一类常见的复制粘贴图像伪造,本文提出了一种基于小波变换和不变矩提取的检测算法。该算法利用小波变换提取图像的低频分量,对低频分量分块进行不变矩特征提取,然后将特征矢量进行按行字典排序,并且配合图像块的偏移位置信息,进行图像复制伪造区域的检测和定位。实验表明该算法能够较精确地定位出复制和粘贴的图像伪造区域,并有效地减少了运算量,提高了检测效率。

Blind Detection of Copy-Move Forgery in Digital Images Based on Wavelet and Moment Invariants

Copy-Move is a common forgery in the research field of digital image forensics, this paper proposes a detection approach based on wavelet transform and moment invariants. Firstly, DWT is applied to the image, and moment invariants is extracted on fixed-size blocks of low-frequency component in wavelet sub-band to yield a reduced dimension representation. The SV vectors are then lexicographically sorted, and copy forgery regions are localized by detecting for all neighborhood vectors. The experiments demonstrate that the proposed approach can not only localize the copy forgery regions accurately, but also reduce the amount of computation and improve the detection efficiency.