(48-3) 13 * << * >> * Russian * English * Content * All Issues

Comparison of neural networks for suppression of multiplicative noise in images
V.A. Pavlov 1, A.A. Belov 1, V.T. Nguen 1, N. Jovanovski 1, A.S. Ovsyannikova 1

1 Peter the Great St. Petersburg Polytechnic University,
195251, Russia, St. Petersburg, Polytechnicheskaya 29

 PDF, 3527 kB

DOI: 10.18287/2412-6179-CO-1400

Pages: 425-431.

Full text of article: Russian language.

Abstract:
The paper compares several neural network (NN) architectures for suppression of multiplicative noise. The images may contain sharp boundaries and large homogeneous areas. Convolutional and fully connected networks are investigated. It is shown that different architectures require significantly different amount of training data to reach the same noise suppression quality. Examples of NN requiring lower amounts of training data are presented.

Keywords:
speckle noise, radar image, SAR, noise reduction, image processing, neural network.

Citation:
Pavlov VА, Belov AА, Nguen VT, Jovanovski N, Ovsyannikova AS. Comparison of neural networks for suppression of multiplicative noise in images. Computer Optics 2024; 48(3): 425-431. DOI: 10.18287/2412-6179-CO-1400.

Acknowledgements:
The research was financially supported by the Ministry of Education and Science of the Russian Federation under a federal grant for creation and development of world-class scientific centers for developing advanced research and technology, No.  075-15-2022-311 of April 20, 2022.

References:
  1. Pavlov VA, Belov AA, Tuzova AA. Implementation of synthetic aperture radar processing algorithms on the Jetson TX1 Platform. IEEE Int Conf on Electrical Engineering and Photonics (EExPolytech) 2019: 90-93.
  2. Gonzalez R, Woods R. Digital image processing. 2nd ed.‎ Prentice Hall; 2002.
  3. Lee JS. Digital image enhancement and noise filtering by using local statistics. IEEE Trans Pattern Anal Mach Intell 1980; 2(2): 165-168.
  4. Frost V, Stiles J, Shanmugan K, Holtzman J. A model for radar images and its application to adaptive digital filtering of multiplicative noise. IEEE Trans Pattern Anal Mach Intell 1982; 4(2): 157-166.
  5. Kuan D, Sawchuk A, Strand T, Chavel P. Adaptive restoration of images with speckle. IEEE Transactions on Acoustics, Speech, and Signal Processing 1987; 25(3): 373-383.
  6. Perona P, Malik J. Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 1990; 12(7): 629-639.
  7. Tomasi C, Manduchi R. Bilateral filtering for gray and color images. Sixth Int Conf on Computer Vision (IEEE Cat No 98CH36271) 1998: 839-846.
  8. Achim A, Kuruoglu EE, Zerubia J. Sar image filtering based on the heavy-tailed rayleigh model. IEEE Trans Image Process 2006; 15(9): 2686-2693.
  9. Solbo S, Eltoft T. Homomorphic wavelet-based statistical despeckling of sar images. IEEE Trans Geosci Remote Sens 2004; 42(4): 711-721.
  10. Achim A, Tsakalides P, Bezerianos A. SAR image denoising via bayesian wavelet shrinkage based on heavy-tailed modeling. IEEE Trans Geosci Remote Sens 2003; 41(8): 1773-1784.
  11. Bhuiyan MIH, Ahmad MO, Swamy MNS. Spatially adaptive wavelet-based method using the cauchy prior for denoising the sar images. IEEE Trans Circuits Syst Video Technol 2007; 17(4): 500-507.
  12. Coll B, Morel J-M. A review of image denoising algorithms, with a new one. Multiscale Model Simul 2005; 4(2): 490-530. DOI: 10.1137/040616024.
  13. Deledalle C, Denis L, Tupin F. Iterative weighted maximum likelihood denoising with probabilistic patch-based weights. IEEE Trans Image Process 2009; 18(12): 2661-2672.
  14. Chierchia G, Cozzolino D, Poggi G, Verdoliva L. SAR image despeckling through convolutional neural networks. IEEE Int Geoscience and Remote Sensing Symposium (IGARSS) 2017: 5438-5441.
  15. Zhang K, Zuo W, Chen Y, Meng D, Zhang L. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Trans Image Process 2017; 26(7): 3142-3155.
  16. Wang P, Zhang H, Patel VM. SAR image despeckling using a convolutional neural network. IEEE Signal Process Lett 2017; 24(12): 1763-1767.
  17. Wang P, Zhang H, Patel VM. Generative adversarial network-based restoration of speckled SAR images. IEEE 7th Int Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP) 2017: 1-5.
  18. Gui Y, Xue L, Li X. SAR image despeckling using a dilated densely connected network. Remote Sensing Lett 2018; 9: 857-866.
  19. Li J, Li Y, Xiao Y, Bai Y. Hdranet: Hybrid dilated residual attention network for SAR image despeckling. Remote Sens 2019; 11(24): 2921.
  20. Zhang Q, Sun R. SAR image despeckling based on convolutional denoising autoencoder. arXiv Preprint. 2020. Source: <https://arxiv.org/abs/2011.14627>.
  21. Pavlov V, Tuzova A, Belov A, Matveev Y. An automated method for finding the optimal parameters of adaptive filters for speckle denoising of SAR images. Computer Optics 2022; 46(6): 914-920. DOI: 10.18287/2412-6179-CO-1132.
  22. Tuzova AA, Pavlov VA, Belov AA. Suppressing multiplicative noise in radar images [In Russian]. Journal of the Russian Universities. Radioelectronics 2021; 24(4): 6-18.
  23. Wang Z, Bovik AC, Sheikh HR. Image quality assessment: From error visibility to structural similarity. IEEE Trans Image Process 2004; 13(4): 600-612.
  24. Xue W, Zhang L, Mou X, Bovik AC. Gradient magnitude similarity deviation: A highly efficient perceptual image quality index. IEEE Trans Image Process 2014; 23(2): 684-695.
  25. ICEYE. 2023. Source: <https://www.iceye.com/>.

© 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