The synthetic aperture radar (SAR) images are contaminated by noise called speckle, making the contaminated images difficult to understand and use. Since SAR images have the advantages of long range and all-weather, which can make up for the poor imaging effect of optical cameras in bad weather conditions, it is meaningful to study the de-speckling algorithm of SAR images. In order to solve the above problem, this paper proposes a method to improve the ability of removing speckles from SAR images using convolutional neural networks. And we use the attention mechanism to further improve the denoising ability based on the proposed denoising network CDNet. After experimental comparison, the speckle removal capability of CDNet proposed in this paper is better than the existing mainstream algorithms.

Wei Liu. Research on Speckle Reduction of SAR Image by Convolutional Neural Network. Academic Journal of Computing & Information Science (2022), Vol. 5, Issue 11: 97-103. https://doi.org/10.25236/AJCIS.2022.051115.

[1] J. -S. Lee, "Digital Image Enhancement and Noise Filtering by Use of Local Statistics," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-2, no. 2, pp. 165-168, March 1980, doi: 10.1109/TPAMI. 1980. 4766994.

[2] D. T. Kuan, A. A. Sawchuk, T. C. Strand and P. Chavel, "Adaptive Noise Smoothing Filter for Images with Signal-Dependent Noise," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-7, no. 2, pp. 165-177, March 1985, doi: 10.1109/TPAMI.1985.4767641.

[3] V. S. Frost, J. A. Stiles, K. S. Shanmugan and J. C. Holtzman, "A Model for Radar Images and Its Application to Adaptive Digital Filtering of Multiplicative Noise," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-4, no. 2, pp. 157-166, March 1982, doi: 10.1109/TPAMI.1982.4767223.

[4] S. Parrilli, M. Poderico, C. V. Angelino and L. Verdoliva, "A Nonlocal SAR Image Denoising Algorithm Based on LLMMSE Wavelet Shrinkage," in IEEE Transactions on Geoscience and Remote Sensing, vol. 50, no. 2, pp. 606-616, Feb. 2012, doi: 10.1109/TGRS.2011.2161586.

[5] Krizhevsky, Alex, Ilya Sutskever and Geoffrey E. Hinton. “ImageNet classification with deep convolutional neural networks.” Communications of the ACM 60 (2012): 84 - 90.

[6] K. Zhang, W. Zuo, Y. Chen, D. Meng and L. Zhang, "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising," in IEEE Transactions on Image Processing, vol. 26, no. 7, pp. 3142-3155, July 2017, doi: 10.1109/TIP. 2017. 2662206.

[7] G. Chierchia, D. Cozzolino, G. Poggi and L. Verdoliva, "SAR image despeckling through convolutional neural networks," 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2017, pp. 5438-5441, doi: 10.1109/IGARSS.2017.8128234.

[8] Q. Zhang, Q. Yuan, J. Li, Z. Yang, and X. Ma, “Learning a Dilated Residual Network for SAR Image Despeckling,” Remote Sensing, vol. 10, no. 2, p. 196, Jan. 2018, doi: 10.3390/rs10020196.

[9] Woo, Sanghyun, Jongchan Park, Joon-Young Lee and In-So Kweon. “CBAM: Convolutional Block Attention Module.” ECCV (2018).

[10] K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.

[11] P. Wang, H. Zhang and V. M. Patel, "SAR Image Despeckling Using a Convolutional Neural Network," in IEEE Signal Processing Letters, vol. 24, no. 12, pp. 1763-1767, Dec. 2017, doi: 10.1109/LSP.2017.2758203.