Detection and localization enhancement for satellite images with small forgeries using modified GAN-based CNN structure

The image forgery process can be simply defined as inserting some objects, with different sizes, in order to vanish some structures and/or scenes. Satellite images can be forged in many ways, such as copy-paste, copy-move and splicing processes. Recent approaches present a generative adversarial network (GAN) as an effective method for identifying the presence of spliced forgeries and identifying their locations with higher detection accuracy of large- and medium-sized forgeries. However, such recent approaches clearly show limited detection accuracy of small-sized forgeries. Accordingly, the localization step of such small-sized forgeries is negatively impacted. In this paper, two different approaches, for detection and localization of small-sized forgeries in satellite images, are proposed. The first approach is inspired from a recently presented GAN-based approach and is modified to an enhanced version. The experimental results manifest that the detection accuracy of the first proposed approach in noticeably increased to 86% compared to his inspiring one with 79% with respect to the small-sized forgeries. Whereas, the second proposed approach uses a different design of a CNN-based discriminator to significantly enhance the detection accuracy to 94%, using the same dataset obtained from NASA and US Geological Survey (USGS) for validation and testing. Furthermore, the results show a comparable detection accuracy in case of large- and medium-sized forgeries using the two proposed approaches compared to the competing ones.