[1]徐 辉,杨 敏.基于低秩矩阵恢复的高光谱图像去噪[J].计算机技术与发展,2022,32(10):46-50.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 008]
　XU Hui,YANG Min.Hyperspectral Image Denoising Based on Low Rank Matrix Restoration[J].,2022,32(10):46-50.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 008]
点击复制

基于低秩矩阵恢复的高光谱图像去噪()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年10期
页码:
46-50
栏目:
媒体计算
出版日期:
2022-10-10

文章信息/Info

Title:
Hyperspectral Image Denoising Based on Low Rank Matrix Restoration
文章编号:
1673-629X(2022)10-0046-05
作者:
徐 辉; 杨 敏
南京邮电大学 自动化学院、人工智能学院,江苏 南京 210023
Author(s):
XU Hui; YANG Min
School of Automation & School of Artificial Intelligence,Nanjing University of Posts and Telecommunications,Nanjing 210023,China
关键词:
高光谱图像; 图像去噪; 低秩矩阵; 全变分正则化; 稀疏噪声
Keywords:
hyperspectral image; image denoising; low-rank matrix; total variation regularization; sparse noise
分类号:
TP39
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 10. 008
摘要:
高光谱图像在采集中通常受到各类噪声的污染, 存在多种不同程度的退化, 传统的高光谱图像去噪仅考虑图像的低秩性而忽略了高光谱图像的相邻波段之间的相似性,缺乏空间信息。 基于低秩矩阵模型和空间光谱全变分正则化,该文提出一种将不同噪声统一去除的框架,从而对退化的高光谱数据进行复原。 算法基于低秩矩阵恢复抑制分离稀疏噪声,并保证图像的局部低秩性;采用空间光谱全变分正则化模型,增强全局空间光谱的平滑性,减少伪影。 由此,建立两者相结合的正则化模型,并用增广拉格朗日乘子法优化求解。 仿真实验结果表明:与其他高光谱复原方法相比,在峰值信噪比和结构相似性方面,所提算法数值指标较高,提高了去噪性能。
Abstract:
Hyperspectral images are usually contaminated by various types of noise during the acquisition,and there are many different degrees of degradation. The traditional hyperspectral image denoising only considers the low rank of the image and ignores the similarity between adjacent bands of the hyperspectral image, lacking spatial information. Based on the low - rank matrix model and the full variational regularization of the spatial spectrum, we propose a unified removal framework for different noises, so as to restore the degraded hyperspectral data. The algorithm is based on low-rank matrix restoration to suppress and separate sparse noise,and to ensure the local low-rank of the image. The spatial spectrum full variation regularization model is used to enhance the smoothness of the globalspatial spectrum and reduce artifacts. Therefore,a regularized model combining the two is established,and the augmented Lagrangian multiplier method is used to optimize the solution. The simulation experiment results show that compared with other hyper spectral restoration methods,in terms of peak signal-to-noise ratio and structural similarity,the proposed algorithm has a higher numerical index,which improves the denoising performance.

相似文献/References:

[1]宋世刚 粘永健 李纲.面向目标检测的高光谱图像压缩技术[J].计算机技术与发展,2009,(11):1.
　SONG Shi-gang,NIAN Yong-jian,LI Gang.Hyperspectral Image Compression Employing Target Detection[J].,2009,(10):1.
[2]黄伟 王书文.一种基于图像边缘检测的全变分的去噪方法[J].计算机技术与发展,2009,(02):24.
　HUANG Wei,WANG Shu-wen.Total Variation Image Denoising Based on Image Edge Detection[J].,2009,(10):24.
[3]周先国 李开宇.基于提升小波结合DCT变换的图像去噪研究[J].计算机技术与发展,2009,(02):62.
　ZHOU Xian-guo,LI Kai-yu.Image De - noising Research Based on Lifting Wavelet and Discrete Cosine Transform[J].,2009,(10):62.
[4]邢丹俊 王继成.基于提升小波的自适应阈值图像去噪[J].计算机技术与发展,2008,(02):42.
　XING Dan-jun,WPNG Ji-cheng.Adaptive Threshold Based on Lifting Wavelet Transform for Image Denoising[J].,2008,(10):42.
[5]于梅 殷兵 梁栋 王璐.基于边缘检测的Contourlet变换图像去噪[J].计算机技术与发展,2008,(06):104.
　YU Mei,YIN Bing,LIANG Dong,et al.Image Denoising with Contourlet Transform Based on Edge Detection[J].,2008,(10):104.
[6]林德贵 何建农 郑玉燕.基于分水岭的提升小波图像去噪[J].计算机技术与发展,2008,(08):29.
　LIN De-gui,HE Jian-nong,ZHENG Yu-yan.Lifting Wavelet Image De- Noising Based on Watershed[J].,2008,(10):29.
[7]汪继文 林胜华 沈玉峰 邱剑锋.一种基于各向异性扩散的图像处理方法[J].计算机技术与发展,2008,(08):98.
　WANG Ji-wen,LIN Sheng-hua,SHEN Yu-feng,et al.An Approach for Image Restoration Based on Anisotropic Diffusion[J].,2008,(10):98.
[8]李瑶 董瑞 何韬 梁栋.一种基于Contourlet变换的图像去噪方法[J].计算机技术与发展,2007,(03):81.
　LI Yao,DONG Rui,HE Tao,et al.A Method for Image Denoising Based on Contourlet Transform[J].,2007,(10):81.
[9]王国权 刘亮.FoE模型的训练方法研究[J].计算机技术与发展,2010,(12):86.
　WANG Guo-quan,LIU Liang.A Study on Training Methods of FoE Model[J].,2010,(10):86.
[10]方洁.基于非抽样Contourlet变换的最佳软阈值图像去噪[J].计算机技术与发展,2011,(02):102.
　FANG Jie.Image Denoising Based on Nonsubsampled Contourlet Transform and Best Soft Threshold[J].,2011,(10):102.
[11]姜 斌,叶 军.基于群稀疏正则化的高光谱图像去噪[J].计算机技术与发展,2023,33(12):171.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 024]
　JIANG Bin,YE Jun.Hyperspectral Image Denoising Based on Group Sparse Regularization[J].,2023,33(10):171.[doi:10. 3969 / j. issn. 1673-629X. 2023. 12. 024]

更新日期/Last Update: 2022-10-10