Forgery Detection in Digital Images by Multi-Scale Noise Estimation

A complex processing chain is applied from the moment a raw image is acquired untilthe final image is obtained. This process transforms the originally Poisson-distributed noise into acomplex noise model. Noise inconsistency analysis is a rich source for forgery detection, as forgedregions have likely undergone a different processing pipeline or out-camera processing. We propose amulti-scale approach, which is shown to be suitable for analyzing the highly correlated noise presentin JPEG-compressed images. We estimate a noise curve for each image block, in each color channeland at each scale. We then compare each noise curve to its corresponding noise curve obtained fromthe whole image by counting the percentage of bins of the local noise curve that are below the globa lone. This procedure yields crucial detection cues since many forgeries create a local noise deficit.Our method is shown to be competitive with the state of the art. It outperforms all other methodswhen evaluated using the MCC score, or on forged regions large enough and for colorization attacks,regardless of the evaluation metric.