A passive forensic scheme for copy-move forgery based on superpixel segmentation and K-means clustering

Abstract

Copy-move forgery is a commonly used operation for digital image. Most of the existing copy-move schemes designed to region duplication are block-based and keypoint-based. In general, block-based methods fail to handle geometric transformations. Though keypoint-based methods can handle geometric transformations, they have a poor detection effect on the smooth region. This has motivated us to propose an efficient copy-move forgery detection method, which is based on superpixel segmentation and cluster analysis to improve the detection accuracy due to some specified attacks in this paper. In the proposed method, K-means clustering technology is used to divide the superpixel of the image into complex regions and smooth regions. The clustering rule is based on the mean and standard deviation of the pixels, and the ratio of the feature points in the superpixel block, this clustering method can distinguish complex regions (non-smooth regions) and smooth regions. In complex regions, Scale-Invariant Feature Transform (SIFT) features are used to detect tampering. In smooth regions, the sector mask feature and RGB color feature are proposed to detect tampering. Filtering out error matching is applied to these two kinds of regions for the copy-move detection. Experimental results have shown that the proposed method can detect the tampering of complex regions and smooth regions and it indeed has the advantage in the detection accuracy compared with some related works when the test images are processed by blurring, adding noise, JPEG compression and rotation.