基于小波变换与组稀疏相结合的遥感图像复原算法
Remote Sensing Image Restoration Method Based on Wavelet Transform Combined with Group Sparse
摘要: 针对脉冲噪声下的遥感图像的复原问题，本文设计一种基于小波变换与组稀疏相结合的遥感图像复原算法。该算法模型采用L0范数作为数据保真项，可以有效地去除脉冲噪声；在正则项上，本文采用重叠组稀疏正则化器与梯度图像在小波变换下的L0范数进行稀疏建模。使用优化最小化方法分别与交替方向乘子法对算法模型进行求解。将本文复原算法与L0-OGSTV、HNHOTV-OGS、L0-TV三种算法进行实验对比。实验结果表明，在峰值信噪比和结构相似性的指标上，本文算法均优于以上几种算法。
Abstract: To solve the restoration problem of remote sensing images under impulse noise, an image restora-tion algorithm based on wavelet transform combined with Group sparse is designed in this paper. The proposed algorithm utilizes L0 norm as the data fidelity term, providing an effective means for removing pulse noise. In the regularization term, a L0 norm of gradient images under wavelet transform is implemented and an overlap-group sparsity regularizer for sparse modeling. The algo-rithm is solved through optimization minimization methods and alternating direction of multiplier approach, respectively. The restoration algorithm in this paper is compared with L0-OGSTV, HNHOTV-OGS and L0-TV. The experimental results show that this algorithm is superior to the above algorithms in terms of peak signal-to-noise ratio (PSNR) and structure similarity (SSIM).
文章引用：董伦, 成丽波, 李喆, 贾小宁. 基于小波变换与组稀疏相结合的遥感图像复原算法[J]. 应用数学进展, 2023, 12(8): 3537-3547. https://doi.org/10.12677/AAM.2023.128352

参考文献

[1] 杨航. 非盲图像复原综述[J]. 中国光学(中英文), 2022, 15(5): 954-972.
[2] Liu, N., Li, W., Wang, Y., et al. (2023) A Survey on Hyperspectral Image Restoration: From the View of Low-Rank Tensor Approximation. Science China In-formation Sciences, 66, Article No. 140302. [Google Scholar] [CrossRef] 
[3] Liu, M.M., Tang, L., Fan, L.J., Zhong, S., Luo, H.Z. and Peng, J.Y. (2022) CARNet: Context-Aware Residual Learning for JPEG-LS Compressed Remote Sensing Image Restoration. Remote Sensing, 14, 6318-6318. [Google Scholar] [CrossRef] 
[4] Xie, S., Zheng, X., Shao, W., et al. (2019) Non-Blind Image Deblurring Method by the Total Variation Deep Network. IEEE Access, 7, 37536-37544. [Google Scholar] [CrossRef] 
[5] Dong, W.S., Zhang, L., Shi, G.M. and Wu, X.L. (2011) Im-age Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization. IEEE Trans-actions on Image Processing, 20, 1838-1857. [Google Scholar] [CrossRef] 
[6] Wang, Y., Yang, J., Yin, W. and Zhang, Y. (2008) A New Alter-nating Minimization Algorithm for Total Variation Image Reconstruction. SIAM Journal on Imaging Sciences, 1, 248-272. [Google Scholar] [CrossRef] 
[7] Zhu, J.G., Wei, J. and Hao, B.B. (2022) Fast Algorithm for Box Constrained Fractional-Order Total Variation Image Restoration with Impulse Noise. IET Image Processing, 16, 3359-3373. [Google Scholar] [CrossRef] 
[8] 崔金鸽, 陈炳权, 徐庆. 基于Dual-Tree CWT和自适应双边滤波器的图像去噪算法[J]. 计算机工程与应用, 2018, 54(18): 223-228.
[9] 陶星朋, 徐宏辉, 郑建炜, 等. 基于非凸低秩矩阵逼近和全变分正则化的高光谱图像去噪[J]. 计算机科学, 2021, 48(8): 125-133.
[10] Rudin, L.I., Osher, S. and Fatemi, E. (1992) Nonlinear Total Variation Based Noise Removal Algorithms. Physica D: Nonlinear Phenomena, 60, 259-268. [Google Scholar] [CrossRef] 
[11] 钟秋祥, 吴传生, 刘文. 含脉冲噪声模糊图像复原的自适应二阶变分模型[J]. 计算机应用研究, 2018, 35(10): 3158-3163.
[12] Liu, X. (2019) Pri-mal-Dual Method for Hybrid Regularizers-Based Image Restoration with Impulse Noise. Circuits, Systems, and Signal Processing, 38, 1318-1332. [Google Scholar] [CrossRef] 
[13] Cui, Z.X. and Fan, Q.B. (2018) A “Nonconvex + Nonconvex” Approach for Image Restoration with Impulse Noise Removal. Applied Mathematical Mod-elling, 62, 254-271. [Google Scholar] [CrossRef] 
[14] Liu, J.J., Ma, R.J., Zeng, X.Y., et al. (2021) An efficient Non-Convex Total Variation Approach for Image Deblurring and Denoising. Applied Mathematics and Computation, 397, Article ID: 125977. [Google Scholar] [CrossRef] 
[15] Luo, Z.J., Zhu, Z.B. and Zhang, B.X. (2021) A LogTVSCAD Nonconvex Regularization Model for Image Deblurring in the Presence of Impulse Noise. Discrete Dynamics in Nature and Society, 2021, Article ID: 3289477. [Google Scholar] [CrossRef] 
[16] Yuan, G. and Ghanem, B. (2019) ℓ0TV: A Sparse Optimization Method for Impulse Noise Image Restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41, 352-364. [Google Scholar] [CrossRef] 
[17] Liu, J., Huang, T.Z., Selesnick, I.W., Lv, X.G. and Chen, P.Y. (2015) Image Restoration Using Total Variation with Overlapping Group Sparsity. Information Sciences, 295, 232-246. [Google Scholar] [CrossRef] 
[18] 田进, 陈秀宏, 傅俊鹏, 等. 基于重叠稀疏组深度信念网络的图像识别[J]. 计算机工程与科学, 2018, 40(3): 515-524.
[19] 陈育群, 陈颖频, 林凡, 等. 基于高阶交叠组稀疏正则项的图像恢复方法[J]. 科学技术与工程, 2020, 20(33): 13747-13756.
[20] Selesnick, I.W. and Chen, P.Y. (2013) Total Variation Denoising with Overlapping Group Sparsity. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, 26-31 May 2013, 5696-5700. [Google Scholar] [CrossRef] 
[21] 骆骏, 刘辉, 尚振宏. 组稀疏表示的双重l1范数优化图像去噪算法[J]. 四川大学学报(自然科学版), 2019, 56(6): 1065-1072.
[22] 易开宇, 戴贞明. 基于混合非凸性二阶全变分和重叠组稀疏的非盲图像去模糊算法[J]. 电子测量与仪器学报, 2021, 35(9): 229-235.
[23] Adam, T., Paramesran, R., Yin, M.M. and Ratnavelu, K. (2021) Combined Higher Order Non-Convex Total Variation with Over-lapping Group Sparsity for Impulse Noise Removal. Multimedia Tools and Applications, 80, 18503-18530. [Google Scholar] [CrossRef] 
[24] Yin, M., Adam, T., Paramesran, R. and Hassan, M.F. (2022) An ℓ0-Overlapping Group Sparse Total Variation for Impulse Noise Image Restoration. Signal Processing: Image Commu-nication, 102, Article ID: 116620. [Google Scholar] [CrossRef] 
[25] Adam, T., Paramesran, R. and Ratnavelu, K. (2022) A Combined Higher Order Non-Convex Total Variation with Overlapping Group Sparsity for Poisson Noise Removal. Computation-al and Applied Mathematics, 41, Article No. 130. [Google Scholar] [CrossRef] 
[26] Zhang, S.Z. (2023) Remote Sensing Image Fusion Based on Wavelet Transform. Academic Journal of Computing & Information Science, 6, 1-9. [Google Scholar] [CrossRef] 
[27] You, N., Han, L.B., Zhu, D.M. and Song, W.W. (2023) Re-search on Image Denoising in Edge Detection Based on Wavelet Transform. Applied Sciences, 13, Article 1837. [Google Scholar] [CrossRef] 
[28] Liu, S.J., Li, W.T., Cao, J.X., Zhang, K. and Hu, S.D. (2023) Image Restoration via Wavelet-Based Low-Rank Tensor Regularization. Optik, 273, Article ID: 170415. [Google Scholar] [CrossRef] 

为你推荐