Enhancing Satellite Imagery: A Novel Approach to Gaussian Noise Reduction Using Convolutional Neural Networks and Nonlinear Filtering Techniques
DOI:
https://doi.org/10.62933/37j8tb47Abstract
Image denoising is one of the fundamental aspects of removing noise from an image and enhancing its features containing visual information. Based on this, Convolutional Neural Networks (CNNs) have been a latest topic of study, with a wide range of applications in fields as diverse as diagnostic image denoising and low-light image denoising. In this paper, an image denoising method is proposed based on converting the noisy image to YUV colon space, extracting the noisy Y channel, and obtaining an appropriate smoothing parameter for the noisy Y channel using the cross-validation smoothing techniques that are used to estimate the Y density function, then using an appropriate noise reduction method (total variation denoising) on the estimated density function to extract the denoised Y channel by removing the Gaussian noise. The results showed that the new proposed method effectively removed noise from the image, which is attributed to the approach adopted in this proposed filter.
References
1. Abdul Wadood, M., & Ghalib, A. (2024). Gaussian Denoising for the First Image from The James Webb Space Telescope “Carina Nebula” using Non-Linear Filters. Journal of Economics and Administrative Sciences, 30(143), 420-434.
2. Araveeporn, A. (2011). The Comparison of Bandwidth Selection Methods using Kernel Function. KMITL Sci. Tech. J., 11 (2), 64-78. Retrieved from https://www.thaiscience.info/Journals/Article/KLST/10896091.pdf
3. Bora, P., & Chaudhary, K. (2021, 5). Improved Image Denoising Methodology using Deep CNN Bilateral Filter Compared to Additional Methods. International Journal of Engineering and Advanced Technology (IJEAT), 10(5), 191-196. doi:https://doi.org/10.35940/ijeat.d2372.0610521
4. Chac´on, J., & Duong, T. (2019). Multivariate plug-in bandwidth selection with unconstrained pilot bandwidth matrices. International Journal of Development Research, 7(9), 15048–15053. doi:https://doi.org/10.1007/s11749-009-0168-4
5. Dong, C., Loy, C., & Tang, X. (2015). Image Super-Resolution Using Deep Convolutional Networks. 1-14.
6. Dong, C., Loy, C., He, K., & Tang, X. (2014). Learning a Deep Convolutional Network for Image Super-Resolutio. 184–199.
7. Florence, K., Aggrey, A., & Leonard, K. (2018, 5 24). Efficiency of various Bandwidth Selection Methods across Different Kernels. IOSR Journal of Mathematics (IOSR-JM), 15(3), 55-62. doi:https://doi.org/10.9790/5728-1503015562
8. Ghalib, A., & Abdul Wadood, M. (2020). Using multidimensional scaling technique in image dimension reduction for satellite image. Periodicals of Engineering and Natural Sciences, 8(1), p.447-454.
9. Herbreteau, S., & Kervrann, C. (2021). DCT2net: an interpretable shallow CNN for image denoising. Journal Of Latex Class Files, 14(8), 1-13.
10. Hmood, Munaf. (2005). Comparing Nonparametric Estimators For Probability Density Estimation. PH.D. Dissertation University of Baghdad, College of Administration & Economics.
11. Hmood, Munaf. (2010), Comparing Variable Bandwidth Estimators Using Local Linear Estimator with Application. Journal of Statistical Sciences, Vol. (3), PP1-21.
12. Horova, I., Kolacek, J., Zelinka, J., & Vopatova, K. (2008, 12). Bandwidth choice for kernel density estimates. 1-10. Retrieved from https://link.springer.com/article/10.1007/s10182-013-0216-y
13. Ilesanmi, A. E., & Ilesanmi, T. O. (2021). Methods for image denoising using convolutional neural network: a review. Complex & Intelligent Systems, 7, 2179–2198. doi:https://doi.org/10.1007/s40747-021-00428-4
14. Li, M.-M., & Li, B.-Z. (2021). A novel weighted total variation model for image denoising. IET Image Process, 15, 2749–2760. doi:https://doi.org/10.1049/ipr2.12259
15. Li, Y., & Chen, Y. (2023). NSNet: An N-Shaped Convolutional Neural Network with Multi-Scale Information for Image Denoising. 11(2772), 1-19. doi:https://doi.org/10.3390/math11122772
16. Malik, J., Kiranyaz, S., & Gabbouj, M. (2020). Operational vs Convolutional Neural Networks for Image Denoising. 1-16.
17. Ortelli, F., & van de Geer, S. (2020). Adaptive Rates for Total Variation Image Denoising. Journal of Machine Learning Research, 21, 1-38.
18. Pana, H., Wena, Y.-W., & Zhu, H.-M. (2019, 11 23). A regularization parameter selection model for total variation-based image noise removal. Applied Mathematical Modelling, 68, 353-376. doi:https://doi.org/10.1016/j.apm.2018.11.032
19. Pm, N., & Chezian, R. M. (2013, 1). Various Colour Spaces And Colour Space Conversion Algorithms. Journal Of Global Research In Computer Science, 4(1), 44-48. Retrieved from http://www.jgrcs.info/
20. Rothfuss, J., Ferreira, F., Walther, S., & Ulrich, M. (2019, 4 3). Conditional Density Estimation with Neural Networks: Best Practices and Benchmarks. 1-36. Retrieved from https://arxiv.org/abs/1903.00954
21. Salgado-Ugarte, I. H., & Perez-Hernandez, M. A. (2003). Exploring the use of variable bandwidth kernel density estimators. The Stata Journal, 3(2), 133-137. Retrieved from https://www.stata-journal.com/abstracts/st0036.pdf
22. Sharma, A., Lall, U., & Tarboton, D. G. (1998). Kernel bandwidth selection for a first-order nonparametric streamflow simulation model. Statistic Hydrology and Hydraulics, 12, 33-52. Retrieved from https://link.springer.com/article/10.1007/s004770050008
23. Thayammal, Sankaramalliga, Priyadarsini, & Ramalakshmi. (2021). Performance Analysis of Image Denoising using Deep Convolutional Neural Network. IOP Conf. Series: Materials Science and Engineering, 1070, 1-8. doi:https://doi.org/10.1088/1757-899X/1070/1/012085
24. Tian, C., Xu, Y., & Zuo, W. (2020). Image denoising using deep CNN with batch renormalization. Neural Networks, 121, 461-473. doi:https://doi.org/10.1016/j.neunet.2019.08.022
25. Tian, C., Xu, Y., Fei, L., Wang, J., Wen, J., & Luo, N. (2018, 2 7). Enhanced CNN for image denoising. CAAI Transactions on Intelligence Technology, 7(4), 1-7. doi:https://doi.org/10.1049/trit.2018.1054
26. Varol, E., & Nejatbakhsh, A. (n.d.). Wasserstein Total Variation Filtering.
27. Xie, S., Song, J., Hu, Y., Zhang, C., & Zhang, S. (2023, 5 20). Using CNN with Multi-Level Information Fusion for Image Denoising. Electronics, 12(6), 2146–2146. doi:https://doi.org/10.3390/electronics12092146
28. You, S. J., & Cho, N. I. (2013). An adaptive bandwidth nonlocal means image denoising in the wavelet domain. o EURASIP Journal on Image and Video Processing, 60, 1-22. Retrieved from http://jivp.eurasipjournals.com/content/2013/1/60
29. Zeng, X., & Li, S. (2013). An efficient adaptive total variation regularization for image denoising. Conference: Image and Graphics (ICIG), 7, 1-6. doi:https://doi.org/10.1109/ICIG.2013.17
30. Zhang, K., Zuo, W., & Zhang, L. (2018). FFDNet: Toward a Fast and Flexible Solution for CNN-based Image Denoising. 1-15.
31. Zhang, Q., Xiao, J., Tian, C., Lin, J., & Zhang, S. (2022). A robust deformed convolutional neural network (CNN) for image denoising. CAAI Transactions on Intelligence Technology, 331-342. doi:https://doi.org/10.1049/cit2.12110
32. Zheng, M., Zhi, K., Zeng, J., Tian, C., & You, L. (2022). A Hybrid CNN for Image Denoising. Journal of Artificial Intelligence and Technology, 2, 93-99. doi:https://doi.org/10.37965/jait.2022.0101
33. Zhu, J., Li, K., & Hao, B. (2019, 5 6). Image Restoration by Second-Order Total Generalized Variation and Wavelet Frame Regularization. Complexity, 1-17. doi:https://doi.org/10.1155/2019/3650128
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Mohammed Abdul Wadood Mohammed, Assma Ghalib Jaber (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Licensed under a CC-BY license: https://creativecommons.org/licenses/by-nc-sa/4.0/
