一种改进的即插即用张量纤维秩约束的高光谱图像恢复
An Improved Plug and Play Tensor Fiber Rank Constrained Hyperspectral Image Restoration
摘要: 高光谱图像(HSI)中的噪声去除是遥感技术中的一项基础而关键的任务，它对于图像的后续处理和分析至关重要。本项研究针对高光谱图像的去噪挑战，针对张量纤维秩约束优化与即插即用正则化的去噪技术对其中的不足进行了改进，即根据条带噪声的组稀疏性质，通过L2-1范数对噪声中条带噪声组稀疏性质进行描述。有效提升了以往L1范数刻画条带噪声的去噪能力。最后通过应用乘子交替方向法(ADMM)来解决这一非凸优化问题。在多个遥感图像数据集上进行的实验验证了该方法在峰值信噪比(PSNR)和结构相似度(SSIM)等评价标准上的优越性，证明了其在处理复杂噪声条件下的高效性和广泛的应用前景。
Abstract: The noise removal in hyperspectral images (HSI) is a fundamental and crucial task in remote sensing technology, which is crucial for the subsequent processing and analysis of images. This study addresses the denoising challenge of hyperspectral images by improving the denoising techniques of tensor fiber rank constrained optimization and plug and play regularization. Based on the sparsity of band noise, the L2-1 norm is used to describe the band noise in the noise. It has improved the denoising ability of previous L1 norm characterization of stripe noise. Finally, by applying the Multiplier Alternating Directions Method (ADMM) to solve this non convex optimization problem, this method achieved a significant improvement in computational efficiency. Experiments conducted on multiple remote sensing image datasets have verified the superiority of this method in evaluation criteria such as peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), demonstrating its efficiency and broad application prospects in dealing with complex noise conditions.
文章引用：冉启刚, 江传富. 一种改进的即插即用张量纤维秩约束的高光谱图像恢复[J]. 应用数学进展, 2024, 13(8): 3788-3802. https://doi.org/10.12677/aam.2024.138361

参考文献

[1] Li, D., Qiu, X., Zhu, Z. and Liu, Y. (2018). Criminal Investigation Image Classification Based on Spatial CNN Features and ELM. 2018 10th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), Hangzhou, 25-26 August 2018, 294-298.[CrossRef] 
[2] Hou, B., Yang, C., Ren, B. and Jiao, L. (2018) Decomposition-Feature-Iterative-Clustering-Based Superpixel Segmentation for PolSAR Image Classification. IEEE Geoscience and Remote Sensing Letters, 15, 1239-1243. [Google Scholar] [CrossRef] 
[3] Dai, D. and Yang, W. (2011) Satellite Image Classification via Two-Layer Sparse Coding with Biased Image Representation. IEEE Geoscience and Remote Sensing Letters, 8, 173-176. [Google Scholar] [CrossRef] 
[4] Srinivas, U., Mousavi, H.S., Monga, V., Hattel, A. and Jayarao, B. (2014) Simultaneous Sparsity Model for Histopathological Image Representation and Classification. IEEE Transactions on Medical Imaging, 33, 1163-1179. [Google Scholar] [CrossRef] [PubMed]
[5] Ma, J., Li, C., Ma, Y. and Wang, Z. (2016). Hyperspectral Image Denoising Based on Low-Rank Representation and Superpixel Segmentation. 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, 25-28 September 2016, 3086-3090.[CrossRef] 
[6] Bioucas-Dias, J.M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., et al. (2012) Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5, 354-379. [Google Scholar] [CrossRef] 
[7] Fu, X., Ma, W., Chan, T. and Bioucas-Dias, J.M. (2015) Self-Dictionary Sparse Regression for Hyperspectral Unmixing: Greedy Pursuit and Pure Pixel Search Are Related. IEEE Journal of Selected Topics in Signal Processing, 9, 1128-1141. [Google Scholar] [CrossRef] 
[8] Fu, X., Ma, W., Bioucas-Dias, J.M. and Chan, T. (2016) Semiblind Hyperspectral Unmixing in the Presence of Spectral Library Mismatches. IEEE Transactions on Geoscience and Remote Sensing, 54, 5171-5184. [Google Scholar] [CrossRef] 
[9] He, W., Zhang, H. and Zhang, L. (2017) Total Variation Regularized Reweighted Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing. IEEE Transactions on Geoscience and Remote Sensing, 55, 3909-3921. [Google Scholar] [CrossRef] 
[10] Hong, D., Yokoya, N., Chanussot, J. and Zhu, X.X. (2019) An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing. IEEE Transactions on Image Processing, 28, 1923-1938. [Google Scholar] [CrossRef] [PubMed]
[11] Yao, J., Meng, D., Zhao, Q., Cao, W. and Xu, Z. (2019) Nonconvex-Sparsity and Nonlocal-Smoothness-Based Blind Hyperspectral Unmixing. IEEE Transactions on Image Processing, 28, 2991-3006. [Google Scholar] [CrossRef] [PubMed]
[12] Sofuoglu, S.E. and Aviyente, S. (2018). Sparse Discriminative Tensor Dictionary Learning for Object Classification. 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Anaheim, 26-28 November 2018, 1341-1345.[CrossRef] 
[13] Joshi, N., Jain, S. and Agarwal, A. (2016). An Improved Approach for Denoising MRI Using Non Local Means Filter. 2016 2nd International Conference on Next Generation Computing Technologies (NGCT), Dehradun, 14-16 October 2016, 650-653.[CrossRef] 
[14] Liu, X. (2023) Simple MKKM: Simple Multiple Kernel K-Means. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 5174-5186. [Google Scholar] [CrossRef] [PubMed]
[15] Zhuang, L. and Bioucas-Dias, J.M. (2018) Fast Hyperspectral Image Denoising and Inpainting Based on Low-Rank and Sparse Representations. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11, 730-742. [Google Scholar] [CrossRef] 
[16] Daneshmand, P.G. and Rabbani, H. (2024) Tensor Ring Decomposition Guided Dictionary Learning for OCT Image Denoising. IEEE Transactions on Medical Imaging, 43, 2547-2562. [Google Scholar] [CrossRef] [PubMed]
[17] Chen, Q., She, H. and Du, Y.P. (2021) Whole Brain Myelin Water Mapping in One Minute Using Tensor Dictionary Learning with Low-Rank Plus Sparse Regularization. IEEE Transactions on Medical Imaging, 40, 1253-1266. [Google Scholar] [CrossRef] [PubMed]
[18] Yuan, Y., Zheng, X. and Lu, X. (2015) Spectral-Spatial Kernel Regularized for Hyperspectral Image Denoising. IEEE Transactions on Geoscience and Remote Sensing, 53, 3815-3832. [Google Scholar] [CrossRef] 
[19] Fonal, K. and Zdunek, R. (2019) Fast Recursive Nonnegative Standard and Hierarchical Tucker Decomposition. IEEE Signal Processing Letters, 26, 1265-1269. [Google Scholar] [CrossRef] 
[20] Shi, Y., Du, S. and Wang, W. (2021). Robust Low-Rank and Sparse Tensor Decomposition for Low-Rank Tensor Completion. 2021 33rd Chinese Control and Decision Conference (CCDC), Kunming, 22-24 May 2021, 7138-7143.[CrossRef] 
[21] Peng, Y., Suo, J., Dai, Q. and Xu, W. (2014) Reweighted Low-Rank Matrix Recovery and Its Application in Image Restoration. IEEE Transactions on Cybernetics, 44, 2418-2430. [Google Scholar] [CrossRef] [PubMed]
[22] Ji, H., Liu, C., Shen, Z. and Xu, Y. (2010). Robust Video Denoising Using Low Rank Matrix Completion. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, 13-18 June 2010, 1791-1798.[CrossRef] 
[23] Bai, X., Xu, F., Zhou, L., Xing, Y., Bai, L. and Zhou, J. (2018) Nonlocal Similarity Based Nonnegative Tucker Decomposition for Hyperspectral Image Denoising. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11, 701-712. [Google Scholar] [CrossRef] 
[24] Chen, Y., He, W., Yokoya, N. and Huang, T. (2020) Hyperspectral Image Restoration Using Weighted Group Sparsity-Regularized Low-Rank Tensor Decomposition. IEEE Transactions on Cybernetics, 50, 3556-3570. [Google Scholar] [CrossRef] [PubMed]
[25] Chen, Y., Huang, T. and Zhao, X. (2018) Destriping of Multispectral Remote Sensing Image Using Low-Rank Tensor Decomposition. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11, 4950-4967. [Google Scholar] [CrossRef] 
[26] Su, X., Zhang, Z. and Yang, F. (2023) Fast Hyperspectral Image Denoising and Destriping Method Based on Graph Laplacian Regularization. IEEE Transactions on Geoscience and Remote Sensing, 61, Article ID: 5511214. [Google Scholar] [CrossRef] 
[27] Chen, Y., Cao, W., Pang, L., Peng, J. and Cao, X. (2023) Hyperspectral Image Denoising via Texture-Preserved Total Variation Regularizer. IEEE Transactions on Geoscience and Remote Sensing, 61, Article ID: 5516114. [Google Scholar] [CrossRef] 
[28] Chen, Y., Huang, T., He, W., Zhao, X., Zhang, H. and Zeng, J. (2022) Hyperspectral Image Denoising Using Factor Group Sparsity-Regularized Nonconvex Low-Rank Approximation. IEEE Transactions on Geoscience and Remote Sensing, 60, Article ID: 5515916. [Google Scholar] [CrossRef] 
[29] Liu, H., Su, T., Du, X., Zhai, Y. and Zhao, J. (2023) Nl3dlogtnn: An Effective Hyperspectral Image Denoising Method Combined Non-Local Self-Similarity and Low-Fibered-Rank Regularization. IEEE Access, 11, 91082-91099. [Google Scholar] [CrossRef] 

为你推荐