(46-4) 16 * << * >> * Russian * English * Content * All Issues

Detection of artificial fragments embedded in remote sensing images by adversarial neural networks
M.V. Gashnikov 1, A.V. Kuznetsov 1

1 Samara National Research University, 443086, Samara, Russia, Moskovskoye Shosse 34

 PDF, 1900 kB

DOI: 10.18287/2412-6179-CO-1064

Pages: 643-649.

Full text of article: Russian language.

Abstract:
We investigate algorithms for detecting artificial fragments of remote sensing images generated by adversarial neural networks. We consider a detector of artificial images based on the detection of a spectral artifact of generative-adversarial neural networks that is caused by a layer for enhancing the resolution. We use the detecting algorithm to detect artificial fragments embedded in natural remote sensing images using an adversarial neural network that includes a contour generator. We use remote sensing images of various types and resolutions, whereas the substituted areas, some being not simply connected, have different sizes and shapes. We experimentally prove that the investigated spectral neural network detector has high efficiency in detecting artificial fragments of remote sensing images.

Keywords:
detection of artificial fragments of images, neural networks, generative adversarial neural networks, cycle neural networks, image redefinition.

Citation:
Gashnikov MV, Kuznetsov AV. Detection of artificial fragments embedded in remote sensing images by adversarial neural networks. Computer Optics 2022; 46(4): 643-649. DOI: 10.18287/2412-6179-CO-1064.

Acknowledgements:
This work was supported by the Russian Science Foundation under project 22-21-00662.

References:
  1. Jam J, Kendrick C, Walker K, Drouard V, Hsu JG, Yap MH. A comprehensive review of past and present image inpainting methods. Comput Vis Image Underst 2021; 203: 103147.
  2. Patil BH, Patil PM. A comprehensive review on state-of-the-art image inpainting techniques. Scalable Computing: Practice and Experience 2020; 21(2): 265-276.
  3. Qin Z, Zeng Q, Zong Y, Xu F. Image inpainting based on deep learning: A review. Displays 2021; 69: 102028.
  4. Thanh DNH, Prasath VBS, Son NV, Son NV, Hieu LM. An adaptive image inpainting method based on the modified Mumford-Shah model and multiscale parameter estimation. Computer Optics 2019; 43(2): 251-257. DOI: 10.18287/2412-6179-2019-43-2-251-257.
  5. Dash A, Ye J, Wang G. A review of Generative Adversarial Networks (GANs) and its applications in a wide variety of disciplines. arXiv preprint 2021. Source: <https://arxiv.org/abs/2110.01442>.
  6. Gao J, Yuan Q, Li J, Su X. Unsupervised missing information reconstruction for single remote sensing image with Deep Code Regression. Int J Appl Earth Obs Geoinf 2021; 105: 102599.
  7. Nazeri K, Ng E, Joseph T, Qureshi F, Ebrahimi M. EdgeConnect: Generative image inpainting with adversarial edge learning. arXiv preprint 2019. Source: <https://arxiv.org/abs/1901.00212>.
  8. Voronin V, Gapon N, Semenishchev E, Zelensky A, Agaian S. A block-based method for the remote sensing images cloud detection and removal. Proc SPIE 2021; 11734: 117340K.
  9. Kuznetsov AV, Gashnikov MV. Remote sensing data retouching based on image inpainting algorithms in the forgery generation problem. Computer optics 2020; 44(5): 763-771. DOI: 10.18287/2412-6179-CO-721.
  10. Songyuan L, Fan M, Chen R. Overview of generative adversarial networks. J Phys Conf Ser 2021; 1873(1): 012071.
  11. Basso D, Colnago M, Azevedo S, Silva E, Pina P, Casaca W. Combining morphological filtering, anisotropic diffusion and block-based data replication for automatically detecting and recovering unscanned gaps in remote sensing images. Earth Sci Inform 2021; 14: 1145-1158.
  12. Horvath J, Baireddy S, Hao H, Montserrat DM, Delp EJ. Manipulation detection in satellite images using vision transformer. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition 2021: 1032-1041.
  13. Ali L, Kasetkasem T, Khan FG, Chanwimaluang T, Nakahara H. Identification of inpainted satellite images using evalutionary artificial neural network (EANN) and k-nearest neighbor (KNN) algorithm. 8th IEEE Int Conf of Information and Communication Technology for Embedded Systems (IC-ICTES) 2017: 1-6.
  14. Zhang X, Karaman S, Chang SF. Detecting and simulating artifacts in gan fake images. IEEE Int Workshop on Information Forensics and Security (WIFS) 2019: 1-6.
  15. Qin M-Y, Fan Y-C, Liu B-L, Ma X. A survey of style transfer based on generative adversarial network. Proc SPIE 2021; 12069: 120691E.
  16. Wang P, Zhang H, Zhou F, Jiang Z. Unsupervised remote sensing image super-resolution using cycle CNN. IEEE Int Geoscience and Remote Sensing Symposium (IGARSS) 2019: 3117-3120.
  17. Zhao K, Zhou L, Gao S, Wang X, Wang Y, Zhao X, Ye H. Study of low-dose PET image recovery using supervised learning with CycleGAN. Plos one 2020; 15(9): e0238455.
  18. Barth R, Hemming J, Van Henten EJ. Optimising realism of synthetic images using cycle generative adversarial networks for improved part segmentation. Comput Electron Agric 2020; 173: 105378.
  19. He F, Liu T, Tao D. Why resnet works? residuals generalize. IEEE Trans Neural Netw Learn Syst 2020; 31(12): 5349-5362.
  20. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. IEEE Conf on Computer Vision and Pattern Recognition 2009: 248-255.
  21. Index of /~taesung_park/CycleGAN/datasets. Source: <https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/>.
  22. Roscosmos. Source: <www.roscosmos.ru>.
  23. Google Earth. Source: <www.google.com/earth>.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20