FORGERY DETECTION OF SPLICING IMAGE USING GLCM IMAGE FEATURES

Abstract

Digital Forensics is a branch of forensic science which is related to cybercrime. It basically involves the detection, recoveryandinvestigationofmaterialfoundindigitaldevices.Digital images and videos plays most important role in digital forensics. They are the prime evidences of any crime scene. So, the fidelity of the image is important. Digital images can be easily manipulated and edited with the help of image processing tools. Copy-move Forgery is themostprimitiveformofcyber-attackondigitalimages.InCopy-moveforgerya part of image (region) itself is copied and pasted into another part of the same image. The intension behind this type of attack is to “add” or “disappear” some objects from the image. Hence to break the fidelity of the image and fool the viewer. Copy move attack is more prevalent in images having uniform texture or patterns, for e.g. sand, grass, water etc.

To further improve the detection rate with relatively low dimension feature vector, a novel passive splicing detection method using textural features based on the grey level co-occurrence matrices, namely TF-GLCM, is proposed in this study. In the TF-GLCM, the GLCM are calculated based on the difference block discrete cosine transform arrays to capture the textural information and the spatial relationship between image pixels sufficiently. The discriminable properties contained in the GLCM are described by six textural features, which include two new introduced ones and four independent ones. In addition, the statistical moments mean Me and standard deviation SDoftexturalfeaturesare used instead of themselves as elements in feature vector to reduce the dimensionality of feature vector and computational complexity.