Performance evaluation of block-based copy- move image forgery detection algorithms

Copy-move forgery is a particular type of distortion where a part or portions of one image is/are copied to other parts of the same image. This type of manipulation is done to hide a particular part of the image or to copy one or more objects into the same image. There are several methods for detecting copy-move forgery, including block-based and key point-based methods. In this paper, a method for detecting copy-move forgery is presented based on hybrid features such as SIFT, KAZE, HOG, and Zernike descriptors. The experimental results of the combinational of these descriptors on the forged images show that this type of combination increases the accuracy of detection than using single and double descriptors; but this high accuracy has the cost of computational time. To reduce the computational time, a Genetic Algorithm (GA) was used to optimize the descriptors and analysis algorithm of the principal component was applied to reduce the dimensions of the features. The results show that the HOG descriptor with a precision of 93.59 has better performance than the other descriptors to detect parts. Combined the four descriptors, the performance of the system is improved by about three percentage in compared with HOG, and reaches a precision of 96.29. The GA as the selector of the best features (six features) achieved the detection rate of 96.94. Using the principal component analysis, the dimensions of the features were reduced to 35, with a detection rate of 94.63.