Copy-Move Forgery Detection using Integrated DWT and SURF

Abstract

In this study, we propose a combination of two feature extraction methods namely Discrete Wavelet Transform (DWT) and Speeded Up Robust Features (SURF) to detect a copy-move forgery in digital media. Copy-move is one of the most popular kinds of digital image tempering, in which one or more parts of a digital image are copied and pasted into different locations. DWT is used to reduce image dimension and SURF is superior in extracting the key features from the image. The method has been tested with BMP and JPG images consisting of genuine and counterfeited images. Furthermore, the method has also been tested with copied-moved images applied with a number of various geometric transformation attacks including rotation, translation, scaling or set of them. The experiments results prove that the proposed method is superior with overall accuracy 95% when compared with the existing method. The copy-move attacks in the digital image have been successfully detected.