Hyperspectral Image Denoising Based on Spectral Dictionary Learning and Sparse Coding

Xiaorui, Song; Wu, Lei; Hao, Hongxing; Xu, Wanpeng

doi:10.3390/electronics8010086

Cited by 14 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SR algorithm is based on the principle of representing the signal with as few atoms as possible in a given super-complete dictionary, which means that the denoised spectrum must have some loss of information compared to the spectrum before denoising. Although the SR algorithm removes some of the high-frequency noise, the process of removing the noise takes away some of the valid information, making the denoised signal less similar to the original signal waveform [21,48,49].…”

Section: Construction Of Prediction Models For CL Nitrogen Contentmentioning

confidence: 99%

Hyperspectral Prediction Model of Nitrogen Content in Citrus Leaves Based on the CEEMDAN–SR Algorithm

Gao,

Tang,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Nitrogen content is one of the essential elements in citrus leaves (CL), and many studies have been conducted to determine the nutrient content in CL using hyperspectral technology. To address the key problem that the conventional spectral data-denoising algorithms directly discard high-frequency signals, resulting in missing effective signals, this study proposes a denoising preprocessing algorithm, complete ensemble empirical mode decomposition with adaptive noise joint sparse representation (CEEMDAN–SR), for CL hyperspectral data. For this purpose, 225 sets of fresh CL were collected at the Institute of Fruit Tree Research of the Guangdong Academy of Agricultural Sciences, to measure their elemental nitrogen content and the corresponding hyperspectral data. First, the spectral data were preprocessed using CEEMDAN–SR, Stein’s unbiased risk estimate and the linear expansion of thresholds (SURE–LET), sparse representation (SR), Savitzky–Golay (SG), and the first derivative (FD). Second, feature extraction was carried out using principal component analysis (PCA), uninformative variables elimination (UVE), and the competitive adaptive re-weighted sampling (CARS) algorithm. Finally, partial least squares regression (PLSR), support vector regression (SVR), random forest (RF), and Gaussian process regression (GPR) were used to construct a CL nitrogen prediction model. The results showed that most of the prediction models preprocessed using the CEEMDAN–SR algorithm had better accuracy and robustness. The prediction models based on CEEMDAN–SR preprocessing, PCA feature extraction, and GPR modeling had an R2 of 0.944, NRMSE of 0.057, and RPD of 4.219. The study showed that the CEEMDAN–SR algorithm can be effectively used to denoise CL hyperspectral data and reduce the loss of effective information. The prediction model using the CEEMDAN–SR+PCA+GPR algorithm could accurately obtain the nitrogen content of CL and provide a reference for the accurate fertilization of citrus trees.

show abstract

Section: Construction Of Prediction Models For CL Nitrogen Contentmentioning

confidence: 99%

Hyperspectral Prediction Model of Nitrogen Content in Citrus Leaves Based on the CEEMDAN–SR Algorithm

Gao,

Tang,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Thus, to handle this issue, recent HSI denoising methods, jointly considering the preservation of spatial and spectral information, directly treat the HSI as a 3D data cube for modeling from the perspective of better exploring image priors, such as non-local self-similarity across space (NSS) (Nonlocal self-similarity (NSS) across space is to explore the spatial similarity among image patches (even pixels). ), global correlation along spectral (GCS) Global correlation along spectral (GCS) mainly focuses on depicting the relationship among features along spectral direction [12,13], low-rank tensors [9,14], sparse coding [32][33][34], etc. [35].…”

Section: Related Workmentioning

confidence: 99%

Spatial and Spectral-Channel Attention Network for Denoising on Hyperspectral Remote Sensing Image

et al. 2022

View full text Add to dashboard Cite

Hyperspectral images (HSIs) are frequently contaminated by different noises (Gaussian noise, stripe noise, deadline noise, impulse noise) in the acquisition process as a result of the observation environment and imaging system limitations, which makes image information lost and difficult to recover. In this paper, we adopt a 3D-based SSCA block neural network of U-Net architecture for remote sensing HSI denoising, named SSCANet (Spatial and Spectral-Channel Attention Network), which is mainly constructed by a so-called SSCA block. By fully considering the characteristics of spatial-domain and spectral-domain of remote sensing HSIs, the SSCA block consists of a spatial attention (SA) block and a spectral-channel attention (SCA) block, in which the SA block is to extract spatial information and enhance spatial representation ability, as well as the SCA block to explore the band-wise relationship within HSIs for preserving spectral information. Compared to earlier 2D convolution, 3D convolution has a powerful spectrum preservation ability, allowing for improved extraction of HSIs characteristics. Experimental results demonstrate that our method holds better-restored results than other compared approaches, both visually and quantitatively.

show abstract

“…Mineral mapping experiments with noise-reduced AVIRIS and Hyperion HSIs demonstrate the algorithm's effectiveness and advancement in denoising performance. After using an online dictionary learning method to train the spectral dictionary, Literature [12] conceptualizes a method for denoising by taking into account HIS spectral information. Based on the test, it is confirmed that the proposed method's denoising effect is 1 dB more powerful than the conventional method's.…”

Section: Introductionmentioning

confidence: 99%

Research on the denoising algorithm for hyperspectral images based on tensor decomposition and full variational constraints

Chen

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

In this paper, based on tensor decomposition, SSTV regular constraints are combined with low-rank 3D tensor for image denoising and the effect of the algorithm is enhanced by the augmented Lagrangian method to construct a hyperspectral image denoising algorithm based on tensor decomposition and full variational constraints. After the algorithm design is completed, image restoration is performed based on the use of objective evaluation, standard mean square error, and peak signal-to-noise ratio to test the specific effect of the algorithm. 2 sets of experiments were designed and analyzed the sensitivity of the algorithm parameters. The test results show that for the penalty parameter μ = C max ( m , n ) σ \mu = C\max \left( {\sqrt {\rm{m}} ,\sqrt {\rm{n}} } \right)\sigma , the optimal results are achieved when C=8 and K values are 13-15. The PSNR index of this paper's algorithm is always greater than 45 when the noise intensity is 0.025-0.1, the highest is 58.817, and the lowest is 45.837. The DN value of the image denoised by the algorithm floats 0.012-0.085 on the basis of the original curve, which is less than 0.1. The performance of the algorithm decreases as the noise becomes more and more complex, and the noise intensity of 0.1 finally drops to 45.837, but the output image is still clear.

show abstract

Hyperspectral Image Denoising Based on Spectral Dictionary Learning and Sparse Coding

Cited by 14 publications

References 31 publications

Hyperspectral Prediction Model of Nitrogen Content in Citrus Leaves Based on the CEEMDAN–SR Algorithm

Hyperspectral Prediction Model of Nitrogen Content in Citrus Leaves Based on the CEEMDAN–SR Algorithm

Spatial and Spectral-Channel Attention Network for Denoising on Hyperspectral Remote Sensing Image

Research on the denoising algorithm for hyperspectral images based on tensor decomposition and full variational constraints

Contact Info

Product

Resources

About