Transferemble: A classification method for the detection of fake satellite images created with deep convolutional generative adversarial network

Sürücü S., DİRİ B.

Journal of Electronic Imaging, vol.32, no.4, 2023 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 32 Issue: 4
  • Publication Date: 2023
  • Doi Number: 10.1117/1.jei.32.4.043004
  • Journal Name: Journal of Electronic Imaging
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Applied Science & Technology Source, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, Civil Engineering Abstracts
  • Keywords: deep convolutional generative adversarial network, deep learning, generative adversarial networks, machine learning, manipulation detection, remote sensing
  • Yıldız Technical University Affiliated: Yes


As the number of government and commercial satellites increases, there is a large increase in Earth observation (EO) imagery. Using different locations and tools, images can be taken from more than one satellite. Manipulations are carried out on these images using a variety of different methods. The number of studies that have been done on the manipulation of EO images is very small. In recent years, generative adversarial networks (GANs), a major breakthrough in deep learning, have made it very easy to obtain fake images. In this study, scene-by-scene fake images were obtained with the deep convolutional GAN on the EuroSAT dataset, which is one of the EO image sets, and fake scene images were obtained from the original scenes. In this study, a dataset called RF-EuroSAT was created. It consists of 14 classes and 36,000 images. Five transfer learning models (VGG-16, DenseNet201, MobileNetV2, RegNetY320, and ResNet152V2) were used to classify this dataset. Using these models as feature extraction and ensemble models (XGBoost, CatBoost, and LightGBM) as classifiers, the classification process was performed using our proprietary transferemble model. The best result was obtained with an accuracy of 91.55% using our transferemble model, which is developed in a modular structure.