Digital Image Forgery Detection using Graph Fourier Transform

This paper proposes a novel method using graph based features for detecting copy move forgery done in digital images. For extracting the features of the image patches the graph Fourier transform are used. A graph can represent data in different applications with a generic data structure. A graph different from classical transforms like DCT and DWT in the sense that it can represent signals on irregular and high dimensional domain. A graph can fit to local characteristics through edges for regular signals like images. Graph Fourier transform extracts the frequency interpretation for signals on graph. To reduce the processing time of feature matching patch match algorithm is used which is a fast approximate nearest neighbor search algorithm. The experiments conducted on the GRIP database shows that the proposed method is highly accurate and are robust to rotation and scaling.

I. Introduction

In this era of digital revolution, images have become the main source of information. An image can convey more information in simple and efficient manner. Digital images are utilized as a proof in official courtroom, in TV news as certificate of honesty and furthermore in military, restorative conclusion, workmanship piece, photography and so forth. Reliability of images decreased due to easier availability of different photo editing software. With the advent in technology it become simpler to manipulate pictures without leaving any noticeable hints of control. So it become hard to recognize between original image and duplicated image with our obvious eye. Images shared over social media can easily be altered to make false interpretation. As such authenticity and integrity of digital images have turned out be significant and forensic analysis of digital images have to be done.