Spectral–Spatial Adaptive Sparse Representation for Hyperspectral Image Denoising

Lu, Ting; Li, Shutao; Fang, Leyuan; Ma, Yi; Benediktsson, Jón Atli

doi:10.1109/tgrs.2015.2457614

Cited by 128 publications

(45 citation statements)

References 47 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In many cases, only local spectral correlation between a few adjacent bands is considered, and the high spectral redundancy in all continuous spectral bands has not been fully used. Novel denoising methods [22]- [24] have been proposed recently by combining non-local similarity across the spatial space and global redundancy along the spectral space. However, when the noises are strong, image denoising methods based on sparse coding and low rank constraint perform poorly because the dictionary learning step tends to remove some inherent information, e.g.…”

Section: Introductionmentioning

confidence: 99%

Nonlocal Similarity Based Nonnegative Tucker Decomposition for Hyperspectral Image Denoising

Bai

Zhou

et al. 2018

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Compared with color or grayscale images, hyperspectral images deliver more informative representation of ground objects and enhance the performance of many recognition and classification applications. However, hyperspectral images are normally corrupted by various types noises, which has serious impact on the subsequent image processing tasks. In this paper, we propose a novel hyperspectral image denoising method based on tucker decomposition to model the non-local similarity across the spatial domain and global similarity along the spectral domain. In this method, 3D full band patches extracted from a hyperspectral image are grouped to form a 3rd-order tensor by utilizing the non-local similarity in a proper window size. In this way the task of image denoising is transformed into a high order tensor approximation problem, which can be solved by nonnegative tucker decomposition. Instead of traditional alternative least square based tucker decomposition, we propose a hierarchical least square based nonnegative tucker decomposition method to reduce the computational cost and improve the denoising effect. In addition, an iterative denoising strategy is adopted to achieve better denoising outcome in practice. Experimental results on three datasets show that the proposed method outperforms several state-of-the-art methods and significantly enhances the quality of the corrupted hyperspectral image.

show abstract

Section: Introductionmentioning

confidence: 99%

Nonlocal Similarity Based Nonnegative Tucker Decomposition for Hyperspectral Image Denoising

Bai

Zhou

et al. 2018

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…It exploited both intraband and interband structures in the course of learning. To fully use the highly correlated spectral information and similar spatial information, a novel spatial and spectral adaptive SR (SSASR) method [24] was introduced to further improve the performance of estimation. More literatures for HSI denoising related to SR or dictionary learning can be found in [25][26][27] and therein references.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Mixed Denoising via Spectral Difference-Induced Total Variation and Low-Rank Approximation

Sun

Zhan

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Exploration of multiple priors on observed signals has been demonstrated to be one of the effective ways for recovering underlying signals. In this paper, a new spectral difference-induced total variation and low-rank approximation (termed SDTVLA) method is proposed for hyperspectral mixed denoising. Spectral difference transform, which projects data into spectral difference space (SDS), has been proven to be powerful at changing the structures of noises (especially for sparse noise with a specific pattern, e.g., stripes or dead lines present at the same position in a series of bands) in an original hyperspectral image (HSI), thus allowing low-rank techniques to get rid of mixed noises more efficiently without treating them as low-rank features. In addition, because the neighboring pixels are highly correlated and the spectra of homogeneous objects in a hyperspectral scene are always in the same low-dimensional manifold, we are inspired to combine total variation and the nuclear norm to simultaneously exploit the local piecewise smoothness and global low rankness in SDS for mixed noise reduction of HSI. Finally, the alternating direction methods of multipliers (ADMM) is employed to effectively solve the SDTVLA model. Extensive experiments on three simulated and two real HSI datasets demonstrate that, in terms of quantitative metrics (i.e., the mean peak signal-to-noise ratio (MPSNR), the mean structural similarity index (MSSIM) and the mean spectral angle (MSA)), the proposed SDTVLA method is, on average, 1.5 dB higher MPSNR values than the competitive methods as well as performing better in terms of visual effect.

show abstract

“…Moreover, the combination of sparse reduced-rank regression and wavelet transform is another way to produce appealing results [21]. Except for wavelet transform-based methods, there are still a number of techniques developed for hyperspectral restoration, e.g., tensor decomposition methods [22,23], sparse representation [24,25] or sparse dictionary learning methods [26,27], kernel-based methods [28], deep learning [29] or neural network [30,31] methods and Bayesian methods [32,33]. These methods have been proved to produce outstanding results.…”

Section: Introductionmentioning

confidence: 99%

A Novel 3D Anisotropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed Denoising

Sun

Zhan

2018

IJGI

View full text Add to dashboard Cite

Known to be structured in several patterns at the same time, the prior image of interest is always modeled with the idea of enforcing multiple constraints on unknown signals. For instance, when dealing with a hyperspectral restoration problem, the combination of constraints with piece-wise smoothness and low rank has yielded promising reconstruction results. In this paper, we propose a novel mixed-noise removal method by employing 3D anisotropic total variation and low rank constraints simultaneously for the problem of hyperspectral image (HSI) restoration. The main idea of the proposed method is based on the assumption that the spectra in an HSI lies in the same low rank subspace and both spatial and spectral domains exhibit the property of piecewise smoothness. The low rankness of an HSI is approximately exploited by the nuclear norm, while the spectral-spatial smoothness is explored using 3D anisotropic total variation (3DATV), which is defined as a combination of 2D spatial TV and 1D spectral TV of the HSI cube. Finally, the proposed restoration model is effectively solved by the alternating direction method of multipliers (ADMM). Experimental results of both simulated and real HSI datasets validate the superior performance of the proposed method in terms of quantitative assessment and visual quality.

show abstract

Spectral–Spatial Adaptive Sparse Representation for Hyperspectral Image Denoising

Cited by 128 publications

References 47 publications

Nonlocal Similarity Based Nonnegative Tucker Decomposition for Hyperspectral Image Denoising

Nonlocal Similarity Based Nonnegative Tucker Decomposition for Hyperspectral Image Denoising

Hyperspectral Mixed Denoising via Spectral Difference-Induced Total Variation and Low-Rank Approximation

A Novel 3D Anisotropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed Denoising

Contact Info

Product

Resources

About