Detection of various image operations based on CNN

Abstract

Over the past years, a number of effective digital image forensic techniques have been proposed. However, most of them design features focused on specific image operation and do binary classification, which are not very reasonable in practice and don't work for detecting other operations. To detect various image operations, in this paper, we propose a carefully crafted CNN model to learn features from the magnified images and do multi-classification automatically. Firstly, the images will be magnified by nearest neighbor interpolation in the preprocessing layer. The property of image operations can be well preserved by the nearest up-sampling. Then, hierarchical representations of different operations are learned via two multi scale convolutional layers. After that, the well-known mlpconv layers are used to enhance the whole architecture's nonlinear modeling ability and finally derive the feature map. Further more, shortcut connections between mlpconv layers allow for increasing the depth of the network while reducing information loss. We present comprehensive experiments on 6 typical image operations. The results show that the proposed method have a good performance both in binary and multi-class detection.