Speckle Noise Suppression in Digital Images Utilizing Deep Refinement Network
Abstract
This paper proposes a deep learning model for speckle noise suppression in digital images. The model consists of two interconnected networks: the first network focuses on the initial suppression of speckle noise. The second network refines these features, capturing more complex patterns, and preserving the texture details of the input images. The performance of the proposed model is evaluated with different backbones for the two networks: ResNet-18, ResNet-50, and SENet-154. Experimental results on two datasets, the Boss steganography, and COVIDx CXR-3, demonstrate that the proposed method yields competitive despeckling results. The proposed model with the SENet-154 encoder achieves PSNR and SNR values higher than 37 dB with the two datasets and outperforms other state-of-the-art methods (Pixel2Pixel, DiscoGAN, and BicycleGAN).
References
Baraha, S., Sahoo, A. K., and Modalavalasa, S. A systematic review on recent developments in nonlocal and variational methods for sar image despeckling. Signal Processing 196 (2022), 108521.
Huynh-Thu, Q., and Ghanbari, M. Scope of validity of psnr in image/video quality assessment. Electronics letters 44, 13 (2008), 800–801.
Isola, P., Zhu, J.-Y., Zhou, T., and Efros, A. A. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (2017), pp. 1125–1134.
Karaoglu, O., Bilge, H. S., and Uluer, I. Removal of speckle noises from ultrasound images using five different deep learning networks. Engineering Science and Technology, an International Journal 29 (2022), 101030.
Kim, T., Cha, M., Kim, H., Lee, J. K., and Kim, J. Learning to discover cross-domain relations with generative adversarial networks. In International conference on machine learning (2017), PMLR, pp. 1857–1865.
Li, X., Wang, Y., Zhao, Y., and Wei, Y. Fast speckle noise suppression algorithm in breast ultrasound image using three-dimensional deep learning. Frontiers in Physiology 13 (2022), 698.
Marmolin, H. Subjective mse measures. IEEE transactions on systems, man, and cybernetics 16, 3 (1986), 486–489.
Paszke, A., Gross, S., Chintala, S., and Chanan, G. Pytorch: Tensors and dynamic neural networks in python with strong gpu acceleration, 2017.
Pavlova, M., Tuinstra, T., Aboutalebi, H., Zhao, A., Gunraj, H., and Wong, A. Covidx cxr-3: A large-scale, open-source benchmark dataset of chest x-ray images for computeraided covid-19 diagnostics. arXiv preprint arXiv:2206.03671 (2022).
Schuler, J. P. S., Romani, S., Abdel-Nasser, M., Rashwan, H., and Puig, D. Grouped pointwise convolutions reduce parameters in convolutional neural networks. Mendel 28, 1 (2022), 23–31.
Shukla, A. K., Dwivedi, S. K., Chandra, G., and Shree, R. Deep learning-based suppression of speckle-noise in synthetic aperture radar (sar) images: A comprehensive review. In Proceedings of the International Conference on Cognitive and Intelligent Computing: ICCIC 2021, Volume 2 (2023), Springer, pp. 693–705.
Sudha, S., Suresh, G., and Sukanesh, R. Speckle noise reduction in ultrasound images by wavelet thresholding based on weighted variance. International journal of computer theory and engineering 1, 1 (2009), 7.
Tandra, R., and Sahai, A. Snr walls for signal detection. IEEE Journal of selected topics in Signal Processing 2, 1 (2008), 4–17.
Wen, Z., He, Y., Yao, S., Yang, W., and Zhang, L. A self-attention multi-scale convolutional neural network method for sar image despeckling. International Journal of Remote Sensing 44, 3 (2023), 902–923.
Willmott, C. J., and Matsuura, K. Advantages of the mean absolute error (mae) over the root mean square error (rmse) in assessing average model performance. Climate research 30, 1 (2005), 79–82.
Xue, W., Mou, X., Zhang, L., and Feng, X. Perceptual fidelity aware mean squared error. In Proceedings of the IEEE International Conference on Computer Vision (2013), pp. 705–712.
Zhu, J.-Y., Park, T., Isola, P., and Efros, A. A. Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint (2017).
Zhu, J.-Y., Zhang, R., Pathak, D., Darrell, T., Efros, A. A., Wang, O., and Shechtman, E. Toward multimodal image-to-image translation. Advances in neural information processing systems 30 (2017).
Copyright (c) 2024 MENDEL
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
MENDEL open access articles are normally published under a Creative Commons Attribution-NonCommercial-ShareAlike (CC BY-NC-SA 4.0) https://creativecommons.org/licenses/by-nc-sa/4.0/ . Under the CC BY-NC-SA 4.0 license permitted 3rd party reuse is only applicable for non-commercial purposes. Articles posted under the CC BY-NC-SA 4.0 license allow users to share, copy, and redistribute the material in any medium of format, and adapt, remix, transform, and build upon the material for any purpose. Reusing under the CC BY-NC-SA 4.0 license requires that appropriate attribution to the source of the material must be included along with a link to the license, with any changes made to the original material indicated.
