Enhancing Image Copy-Move Forgery Detection using Particle Swarm Optimization Techniques

Copy-Move Forgery (CMF) is a simple and effective operation to generate forged digital images. Recent, techniques on Scale Invariant Features Transform (SIFT) are commonly used to detect CMF. Various approaches under the SIFTframework are the most acceptable ways to CMF detection due to the robust performance of SIFT. However, for some CMF images, these approaches cannot produce satisfactory detection results. For instance, the number of the matched keypoints may be too less to prove an image to be a CMF image or to produce an accurate result. These values are only applicable for few images, which limits their application. To solve the problem, a novel approach names as CMF Detection with Particle Swarm Optimizations (PSO) algorithm into the SIFT-based framework. Sometimes these approaches may even produce error results. According to our observations, one of the reasons is that detection results produced by the SIFT-based framework are highly depending on parameters whose values are often determined with experiences. It utilizes the PSO algorithm to generate customized parameter values for images, which are used for CMF detection under the SIFT=based framework. Experimental results show that CMFD-PSO has good performance.