Images Copy-Move Forgery Detection Using SIFT and DB-SCAN algorithm

Nowadays, reasonable and accessible digital camera devices have made capturing and manipulating uploaded images as a game. Statistics show that the use of social networking websites has greatly influenced people's intentions to create digital images. Billions of photos are uploaded, shared, and posted on these platforms every day. This makes every user an active source of digital information. Among the various digital image manipulation operations, copy-move forgery is one of the simplest and most common approaches to making forgery images. The idea of copy-move forgery is to duplicate objects or hide the areas of information in that image. In this study, the Scale-invariant feature transform (SIFT) algorithm was used to extract the features of key points, and the spatial classification algorithm based on Density-based spatial clustering of applications with noise (DB-SCAN) is a data clustering algorithm to reduce the error and increase the accuracy of detecting this type image forgery. In this study, the evaluation of four data sets shows that the accuracy of the proposed method in detecting copy-move forgery is about 96%. According to the experimental results, this method performs better than other proposed algorithms.