Copy-Move Forgery Detection in Digital Images—Survey and Accuracy Estimation Metrics

Copy-move forgery is a common type of modification attack on images. In such type of manipulation, part of an image is copied and pasted on any other location of the same image. Hence, this form of manipulation is difficult to be identified by methods which look for statistical inconsistencies between different regions of an image. Existing methods are primarily motivated toward finding copy-moved area(s) in an image. In this chapter, we provide a detailed survey of existing techniques of copy-move forgery detection and demonstrate the application of three metrics for forgery detection, viz., detection accuracy, false positive rate, and false negative rate. On the basis of proposed parameters, we compare and analyze the success of different block-based copy-move forgery detection methods. These metrics help to choose the algorithm most suitable for the context.