High-performance image forgery detection via adaptive SIFT feature extraction for low-contrast or small or smooth copy-move region images

Due to their robustness against large-scale geometric transformations, keypoint-based detection methods play an important role in revealing copy-move evidence. However, where copy-move forgeries are only involved in low-contrast or small or smooth regions, these approaches do not yield high-performance results because the number of keypoints in these regions is very limited. We recommend a highly efficient copy-move forgery detection algorithm by ADaptive Scale-Invariant Feature Transform (ADSIFT). Initially, by adapting the gamma factor for contrast threshold and rescaling factor values for feature matching and forgery detection, we produce an adequate number of keypoints that occur even in low-contrast or small or smooth regions of noisy or noiseless images. The proposed approach delivers greater performance than the existing methods as compared to precision and efficiency.