Detection of Copy–Move Image Forgery Applying Robust Matching with K-D Tree Sorting

Abstract

Digital images contribute significantly to the field of visualization. Using stronger technology, digital image forgery is easier. The most common method of image forgery is to re-create a portion of a person’s location or to conceal a portion of an image. In our paper, we worked on detecting region duplication forgery using COMOFORD databases by utilizing the discrete cosine transform (DCT), k-dimensional tree (k-d tree) for sorting efficiently, and a robust matching method. Here, the size of the block will be 16 × 16, and it will be divided into four blocks. This study can detect forged portions for PNG images with better performance by highlighting the images with a quality factor of 0.5 and a threshold value of 10, as well as gives good results for JPEG images.