Copy - Move Image Forgery Detection

Abstract

Copy–move forgery is a widely used image manipulation technique in which a region of an image is duplicated within the same image to conceal or replicate objects. With the rapid expansion of digital media and editing tools, ensuring the authenticity of images has become increasingly important.This work presents a computer vision-based method for detecting copy–move forgery in digital images. Initially, the input image undergoes preprocessing using Discrete Wavelet Transform (DyWT) to enhance significant structural features. Subsequently, Scale-Invariant Feature Transform (SIFT) is employed to extract robust keypoints and feature descriptors. These descriptors are matched using the Generalized 2-Nearest Neighbor (G2NN) ratio test to identify similar regions. To further refine the detection, hierarchical clustering is applied to group matched keypoints corresponding to duplicated areas.The forged regions are visualized by connecting matched keypoints, enabling clear identification of manipulated areas. The proposed approach demonstrates robustness against common transformations such as scaling, rotation, and noise. This system is suitable for applications in digital forensics, media authentication, and security analysis.