Date of Publication :25th December 2020

Abstract: Digital image forgery is a one of multimedia security whose objective is to show the wicked manipulations in digital images. Among different types of image forgery, copy–move forgery detection (CMFD) is the most popular one where a part of the original image is copied and pasted at another position in the same image. Various methods have been developed in the past few years. to achieve geometric transformation like rotation and scaling, a novel methodology based on Scale Invariant Features Transform (SIFT) is proposed. The proposed algorithm mainly involves in feature matching in which features are extracted from each block by computing the dot product between the unit vectors. Random Sample Consensus (RANSAC) algorithm is used to remove the false positive matches. The experimental results of the algorithm are presented to confirm that the technique can extract more accurate results compared with existing forgery detection methods.

Reference :