https://doi.org/10.62660/bcstu/4.2025.11

Volume 30, No. 4, 2025

11-24

  • Read article

    • Adaptive noise reduction method based on a modified Lee filter for SAR image classification tasks

    Yurii Brovka

    Received 27.06.2025, Revised 12.11.2025, Accepted 15.12.2025

    Abstract

    The study aimed to create a set of software tools for automated processing and classification of synthetic aperture radar images using adaptive image analysis algorithms. The study used archival data from Sentinel-1, TerraSAR-X and RADARSAT-2 radar satellites and applies both classical image processing methods and adaptive algorithms. The quality of filtering, segmentation, classification, and object detection was assessed in terms of accuracy, structural similarity, signal-to-noise ratio, and consistency of results. The architecture of the software package was developed, including modules for pre-processing Synthetic Aperture Radar data, adaptive spectral filtering, image segmentation, and object classification. The study implemented adaptive algorithms such as the Lee filter, the K-means variant, the support vector method and the Ordered Statistics Constant False Alarm Rate. The developed tools were tested on satellite images from Sentinel-1 and RADARSAT-2 platforms for different types of the Earth’s surface. The adaptive filtering algorithm improved image quality by 35%, and performance on key metrics increased by 15-45% compared to traditional methods. High classification accuracy, including Kappa coefficient, F1, and area under the Receiver Operating Characteristic curve (Area Under the Curve), while maintaining computational efficiency, was provided. Automatic detection of water bodies, urban areas and agricultural land was implemented with an image processing time of less than 3 minutes. Adaptive algorithms ensured stable operation in conditions of different input data quality, making them suitable for a wide range of practical applications in the field of remote sensing and geographic information systems

    Keywords:

    remote sensing; metrics; deep learning; adaptive filtering; speckle noise

    Suggested citation
    Brovka, Yu. (2025). Adaptive noise reduction method based on a modified Lee filter for SAR image classification tasks. Bulletin of Cherkasy State Technological University, 30(4), 11-24. https://doi.org/10.62660/bcstu/4.2025.11
    336 Views

    References

    1. Ahmed, S.F., Alam, M.S., Hassan, M., Rozbu, M.R., Ishtiak, T., Rafa, N., Mofijur, M., Ali, A., & Gandomi, A.H. (2023). Deep learning modelling techniques: Current progress, applications, advantages, and challenges. Artificial Intelligence Review, 56, 13521-13617. doi: 10.1007/s10462-023-10466-8.
    2. Alatalo, J. (2023). Data platform using open-source tools to support geospatial research: Case SAR satellite based change detection. Retrieved from https://urn.fi/URN:NBN:fi:amk-2023052212690.
    3. Aswani, I., Kar, N.K., Ganguly, T., Ramesh, G.P., & Tejaswini, N. (2023). A fault diagnosis of sound and vibration signals using statistical features and machine learning algorithm. In International conference on integrated circuits and communication systems (pp. 1-7). Raichur: IEEE. doi: 10.1109/ICICACS57338.2023.10100043.
    4. Declaration of Helsinki. (2024). Retrieved from https://surl.li/laafnh.
    5. European Code of Conduct for Research Integrity. (2020, June). Retrieved from https://www.ieee.org/about/ corporate/governance/p7-8.
    6. Fernando, H., Nketia, K., Ha, T., van Steenbergen, S., McNairn, H., & Shirtliffe, S. (2025). Automating Sentinel-1 SLC product processing: Parallelization and optimization for efficient polarimetric parameter extraction. MethodsX, 14, article number 103253. doi: 10.1016/j.mex.2025.103253.
    7. Ghafari, R., Kabutarkhani, F.H., & Mansouri, N. (2022). Task scheduling algorithms for energy optimization in cloud environment: A comprehensive review. Cluster Computing, 25, 1035-1093. doi: 10.1007/s10586-021-03512-z.
    8. Gujrati, A., Pradhan, R., Singh, N., Jha, V.B., & Gupta, P.K. (2024). Adaptive water delineation algorithms for L-and C-band SAR imagery: А comparative analysis. Earth Science Informatics, 17, 5011-5025. doi: 10.1007/s12145024-01417-0.
    9. Huang, M., Zhao, H., & Chen, Y. (2024). Research on SAR image quality evaluation method based on improved Harris Hawk optimization algorithm and XGBoost. Scientific Reports, 14, article number 28364. doi: 10.1038/ s41598-024-79674-8.
    10. Jiang, Y., Xie, J., & Zhang, D. (2022). An adaptive offset activation function for CNN image classification tasks. Electronics, 11(22), article number 3799. doi: 10.3390/electronics11223799.
    11. Komenchuk, O. (2024). Adaptive pre-processing methods for increasing the accuracy of segmentation of dental X-RAY images. Innovative Technologies and Scientific Solutions for Industries, 3(29), 29-38. doi: 10.30837/25229818.2024.3.029.
    12. Li, B., Ma, Y., Chu, L., Li, W., & Shi, Y. (2024). A GAN-based fast focusing method for circular SAR images. Heliyon, 10(14), article number e34133. doi: 10.1016/j.heliyon.2024.e34133.
    13. Liang, W., Wu, Y., Li, M., & Cao, Y. (2022). Adaptive multiple kernel fusion model using spatial-statistical information for high resolution SAR image classification. Neurocomputing, 492, 382-395. doi: 10.1016/j.neucom.2022.03.062.
    14. Liu, Y., & Lei, Z. (2024). Review of advances in active impulsive noise control with focus on adaptive algorithms. Applied Sciences, 14(3), article number 1218. doi: 10.3390/app14031218.
    15. Lysenko, А. (2023). Synthetic-aperture multi-polarization radar data informativity enhancement technique. Ukrainian Journal of Remote Sensing, 10(3), 10-15. doi: 10.36023/ujrs.2023.10.3.243.
    16. Metrikaityte, G., Suziedelyte Visockiene, J., & Papsys, K. (2022). Digital mapping of land cover changes using the fusion of SAR and MSI satellite data. Land, 11(7), article number 1023. doi: 10.3390/land11071023.
    17. Pasichnik, D., & Onoyko, Yu. (2024). The most important satellite systems remote sensing of the Earth and its possibilities. Scientific Notes of Young Scientists, 13.
    18. Pavlov, Y., & Kashkanov, A. (2023). Analysis of existing methods and approaches to the search of damaged armored tank vehicles during technical intelligence in the modern armies of the world. Journal of Mechanical Engineering and Transport, 18(2), 134-140. doi: 10.31649/2413-4503-2023-18-2-134-140.
    19. Raj, J.A., Idicula, S.M., & Paul, B. (2022). Lightweight SAR ship detection and 16 class classification using novel deep learning algorithm with a hybrid preprocessing technique. International Journal of Remote Sensing, 43(15-16), 5820-5847. doi: 10.1080/01431161.2021.2008544.
    20. Riapolov, I., Vasilets, V., Kukobko, S., & Bodnar, S. (2024). Modelling the surface geometry of unmanned aerial vehicles, the design of which contains elements with different electrophysical properties. Testing and Certification, 2(4), 101-110. doi: 10.37701/ts.04.2024.13.
    21. Selvam, N., Nagesa, Y., & Negesa, F. (2022). Deep learning approach with optimization algorithm for reducing the training and testing time in SAR image detection and recognition. Indian Journal of Science and Technology, 15(9), 371-385. doi: 10.17485/IJST/v15i9.1266.
    22. Shahi, A.P., Rai, P.K., & Mishra, V.N. (2023). Remote sensing data extraction and inversion techniques: A review. In A. Kumar Singh & S. Tiwari (Eds.), Atmospheric remote sensing: Principles and applications (pp. 85-104). London: Elsevier. doi: 10.1016/B978-0-323-99262-6.00021-3.
    23. Shen, S.-L., Zhang, N., Zhou, A., & Yin, Z.-Y. (2022). Enhancement of neural networks with an alternative activation function tanhLU. Expert Systems with Applications, 199, article number 117181. doi: 10.1016/j. eswa.2022.117181.
    24. Singh, T., Babu, T., Nair, R.R., & Duraisamy, P. (2024). Ship detection in synthetic aperture radar imagery: An active contour model approach in computer vision deep learning. Procedia Computer Science, 235, 1793-1802. doi: 10.1016/j.procs.2024.04.170.
    25. Skrypnyk, L., Belenok, V., Velikodsky, Y., Ishchenko, N., & Klymenko, O. (2024). Justification of the advantages of using optical and radar remote sensing data in detecting buildings damaged by natural or anthropogenic impacts. Ukrainian Journal of Remote Sensing, 11(4), 13-25. doi: 10.36023/ujrs.2024.11.4.277.
    26. Srivastava, S., Divekar, A.V., Anilkumar, C., Naik, I., Kulkarni, V., & Pattabiraman, V. (2021). Comparative analysis of deep learning image detection algorithms. Journal of Big Data, 8, article number 66. doi: 10.1186/s40537021-00434-w.
    27. Stankevich, S., Svideniuk, M., & Lysenko, A. (2021). Land surface roughness parameter retrieval by inverse simulation of dual-polarization radar backscattering. Applied Questions of Mathematical Modelling, 4(2.1), 207-215. doi: 10.32782/KNTU2618-0340/2021.4.2.1.22.
    28. Trofymchuk, O.M., Hordiienko, O.V., Anpilova, Y.S., & Yakovliev, Y.O. (2024). Monitoring vertical landslides in the Solotvyno aglomeration using Sentinel-1 satellite imagery. Environmental Safety and Natural Resources, 50(2), 102-114. doi: 10.32347/2411-4049.2024.2.102-114.
    29. Vasilenko, D.O., Martynyuk, S.E., Roman, L.O., & Medzmariashvili, E.V. (2025). Features of calibrating satellite RSAs with a multi-beam reflector antenna. Radioelectronics and Communications Systems, 67(7), 377-391.doi: 10.20535/S0021347024010047.
    30. Wu, Y., & Li, Q. (2022). The algorithm of watershed color image segmentation based on morphological gradient. Sensors, 22(21), article number 8202. doi: 10.3390/s22218202.
    31. Yasir, M., Shanwei, L., Mingming, X., Hui, S., Hossain, M.S., Colak, A.T., Wang, D., Jianhua, W., & Dang, K.B. (2023). Multi-scale ship target detection using SAR images based on improved Yolov5. Frontiers in Marine Science, 9, article number 1086140. doi: 10.3389/fmars.2022.1086140.
    32. Zhang, X., & Ding, F. (2021). Optimal adaptive filtering algorithm by using the fractional-order derivative. IEEE Signal Processing Letters, 29, 399-403. doi: 10.1109/LSP.2021.3136504.