Blur-invarient copy-move forgery detection technique

What is it about?

The majority of the existing copy-move forgery detection algorithms operate based on the principle of image block matching. However, such detection becomes complicated when an intelligent adversary blurs the edges of forged region(s). To solve this problem, we present a novel approach for detection of copy-move forgery using Stationary Wavelet Transform which, unlike most wavelet transforms (e.g. Discrete Wavelet Transform), is shift-invariant. It helps in finding the similarities i.e. matches and dissimilarities i.e. noise, between the blocks of an image, caused due to blurring. The blocks here are represented by features extracted using the scaling- and rotation-invariant Singular Value Decomposition of the image. In this paper, we introduce the concepts of automatic threshold tting to automate the process and minimize manual effort, as well as color-based segmentation to make the detection blur-invariant, and 8-connected neighborhood check to reduce false positives in the proposed approach. Segmentation also helps to reduce the time complexity by avoiding unnecessary comparisons between blocks in different segments. Our experimental results prove the efficiency of the proposed method in detection of copy-move forgery involving intelligent edge blurring. Also, our experimental results prove that the performance of the proposed method in terms of detection accuracy is considerably higher compared to the state-of-the-art.

Featured Image

Why is it important?

In this paper, we introduce the concepts of automatic threshold tting to automate the process and minimize manual effort, as well as color-based segmentation to make the detection blur-invariant, and 8-connected neighborhood check to reduce false positives in the proposed approach. Segmentation also helps to reduce the time complexity by avoiding unnecessary comparisons between blocks in different segments.