SED-NET: DETECTING MULTI-TYPE EDITS OF IMAGES

As the editing of digital images is greatly facilitated by the powerful and convenient tools, detecting and tracing edit operations on images to deal with rampant pirate copies has recently attracted more and more attention. Especially, it is important to classify different types of image edits between an original image and an edited image. As there has been no work considering complex edit types like adding logos and it is possible to make multiple types of edits to an image, we propose a deep Siamese network model trained by a weighted sigmoid cross-entropy loss to increase recall while keeping high accuracy. We also construct a flexible dataset involving ten types of edits for this task to train and test the model. A detailed ablation analysis shows the effectiveness of each part of the model. The results of the experiments demonstrate that the model achieves high accuracy on ten types and can handle unseen types.