Hyperspectral Imagery Denoising Research Articles

Hyperspectral Imagery Denoising Using Minimum Noise Fraction and Video Non-Local Bayes Algorithms

Hyperspectral imagery (HSI) denoising is a popular research topic in remote sensing. In this paper, we propose a novel method for HSI denoising by performing Minimum Noise Fraction (MNF) to the original HSI data cube, thresholding the noisy output bands with the Video Non-Local Bayes (VNLB) algorithm, and then conducting the inverse MNF transform to obtain the denoised data cube. Our experiments demonstrate that the proposed method usually achieves the best denoising results among several existing denoising methods for two HSI data cubes. In addition, it is much faster for HSI denoising than the VNLB algorithm which was originally developed for video denoising.

Hyperspectral imagery denoising using minimum noise fraction and VBM3D

Hyperspectral imagery denoising is a classical problem in hyperspectral remote sensing applications. In our previous work, we combined principal component analysis with wavelet shrinkage, and good denoising results were obtained. We combine minimum noise fraction (MNF) with video block matching and 3D filtering (VBM3D), which is a powerful video denoising method. After MNF transform, we automatically select k0, the number of spectral band images as a threshold for denoising. We reduce the noise in spectral band images of MNF transformed data from k0 to the last band image and do not denoise the first k0 − 1 spectral band images. Finally, we perform an inverse MNF transform to obtain the denoised data cubes. We compare our MNF + VBM3D method with different denoising methods such as bivariate wavelet shrinkage (BivShrink), non-local means, SURELET, and block matching and 3D filtering (BM3D). Experimental results demonstrate that MNF + VBM3D achieves the best denoising results among almost all methods for three testing data cubes and with different noise levels.

Noise reduction of shot-noise-dominated hyperspectral imagery by combining PCA with existing denoising methods

In this paper, we revisit the effects of principal component analysis (PCA) on hyperspectral imagery denoising. Our previous work combined PCA with wavelet shrinkage and particularly good denoising results has been achieved. We debate that any denoising methods can be used to replace wavelet shrinkage in our PCA+wavelet shrinkage algorithm. The major difference between this work and our previous PCA-based denoising method is that we consider a mixture of Gaussian and shot noise in this work whereas our previous methods studied Gaussian white noise alone. In addition, we retain [Formula: see text] [Formula: see text] PCA output components in our forward PCA transform in this paper whereas we keep all PCA output components [Formula: see text] in our previous works. The [Formula: see text] above is the number of spectral bands in the original hyperspectral imagery data cube. In addition, PCA is much better than nonlinear PCA for hyperspectral imagery denoising when Gaussian white noise and shot noise are introduced as demonstrated in this paper. Extensive experiments demonstrate that the method proposed in this paper outperforms the existing methods significantly in terms of signal-to-noise ratio for two testing hyperspectral imagery data cubes.

A new MNF–BM4D denoising algorithm based on guided filtering for hyperspectral images

This paper proposed a new MNF–BM4D denoising algorithm based on guided filtering to improve the denoising performance of the state-of-the-art Block-Matching and 4D filtering(BM4D) algorithm for hyperspectral images in the spatial and spectral domain. BM4D is firstly used to denoise hyperspectral images. Then Minimum Noise Fraction(MNF) algorithm is introduced to distinguish between the main component and the noisy component. Finally, the guided image filtering technology is utilized to further improve the denoising performance. A number of experiments on both simulated and real data are conducted to validate the effective denoising performance of the proposed method. Therefore, the proposed algorithm can be considered as a promising technique for hyperspectral imagery denoising.

Hyperspectral Imagery Denoising by Deep Learning With Trainable Nonlinearity Function

Hyperspectral images (HSIs) can describe subtle differences in the spectral signatures of objects, and thus they are effective in a wide array of applications. However, an HSI is inevitably contaminated with some unwanted components like noise resulting in spectral distortion, which significantly decreases the performance of postprocessing. In this letter, a deep stage convolutional neural network (CNN) with trainable nonlinearity functions is applied for the first time to remove noise in HSIs. Besides the fact that the weight and bias matrices are learned from cubic training clean-noisy HSI patches, the nonlinearity functions in each stage are also trainable, which differ from the conventional CNN with a fixed nonlinearity function. Compared with the state-of-the-art HSI denoising methods, the experimental results on both synthetic and real HSIs confirm that the proposed method can obtain a more effective and efficient performance.

Minimum Noise Fraction versus Principal Component Analysis as a Preprocessing Step for Hyperspectral Imagery Denoising

. Minimum noise fraction (MNF) is a well-known technique for hyperspectral imagery denoising. It transforms a noisy data cube into output channel images with steadily increasing noise levels, which means that the MNF output images contain steadily decreasing image quality. Principal component analysis (PCA) can also be used for hyperspectral imagery denoising. The PCA is defined in such a way that the first principal component has the largest possible variance, and each succeeding component has the highest variance possible under the constraint that it is orthogonal to the preceding components. It can be shown that these components are the Eigenvectors of the covariance matrix of the samples. In this study, we compare PCA-based methods with MNF-based methods for hyperspectral imagery denoising. Our comparison consists of the following 3 steps: (1) forward MNF/PCA transform of a noisy hyperspectral data cube; (2) reduce noise in selected output channel images with index k > k0, a channel number cutoff threshold; (3) inverse MNF/PCA transform of the noise-reduced channel images to obtain the denoised hyperspectral data cube. Our experiments demonstrate that MNF-based methods achieve higher signal-to-noise ratios than PCA-based methods for signal-dependent noise, whereas PCA-based methods produce higher SNRs than MNF-based methods for Gaussian white noise.

Multitask Sparse Nonnegative Matrix Factorization for Joint Spectral–Spatial Hyperspectral Imagery Denoising

Hyperspectral imagery (HSI) denoising is a challenging problem because of the difficulty in preserving both spectral and spatial structures simultaneously. In recent years, sparse coding, among many methods dedicated to the problem, has attracted much attention and showed state-of-the-art performance. Due to the low-rank property of natural images, an assumption can be made that the latent clean signal is a linear combination of a minority of basis atoms in a dictionary, while the noise component is not. Based on this assumption, denoising can be explored as a sparse signal recovery task with the support of a dictionary. In this paper, we propose to solve the HSI denoising problem by sparse nonnegative matrix factorization (SNMF), which is an integrated model that combines parts-based dictionary learning and sparse coding. The noisy image is used as the training data to learn a dictionary, and sparse coding is used to recover the image based on this dictionary. Unlike most HSI denoising approaches, which treat each band image separately, we take the joint spectral–spatial structure of HSI into account. Inspired by multitask learning, a multitask SNMF (MTSNMF) method is developed, in which bandwise denoising is linked across the spectral domain by sharing a common coefficient matrix. The intrinsic image structures are treated differently but interdependently within the spatial and spectral domains, which allows the physical properties of the image in both spatial and spectral domains to be reflected in the denoising model. The experimental results show that MTSNMF has superior performance on both synthetic and real-world data compared with several other denoising methods.

Three-dimensional wavelets-based denoising of hyperspectral imagery

We propose a three-dimensional (3-D) denoising approach and coding scheme. The suggested denoising algorithm is taking full advantage of the supplied volumetric data by decomposing the original hyperspectral imagery into individual subspaces, applying an orthogonal isotropic 3-D divergence-free wavelet transformation. The delineated capability of hierarchically structured wavelet coefficients improves the efficiency of the suggested denoising algorithm and effectively preserves the finest details and the relevant image features by emphasizing a nonlocal similarity and spectral-spatial structure of hyperspectral imagery into sparse representation. The proposed method is evaluated using spectral angle distance for a ground-truth spectral dataset and by classification accuracies using water quality indices, which are particularly sensitive to the presence of noise. The reported results are based on a real dataset, presenting three different airborne hyperspectral systems: AHS, CASI-1500i, and AisaEAGLE. Several qualitative and quantitative evaluation measures are applied to validate the ability of the suggested method for noise reduction and image quality enhancement. Experimental results demonstrate that the proposed denoising algorithm achieves better performance when applied on the suggested wavelet transformation compared with other examined noise reduction and hyperspectral image restoration techniques.

Denoising Hyperspectral Imagery Using Principal Component Analysis and Block-Matching 4D Filtering

In this article, we propose a new method for denoising hyperspectral imagery. Hyperspectral imagery normally contains a small amount of noise, which can hardly be seen by human eyes thanks to its relatively high signal-to-noise ratio. However, in many remote sensing applications, this amount of noise is still troublesome. In this study, we first perform principal component analysis (PCA) to the hyperspectral data cube to be denoised in order to separate the fine features from the noise in the hyperspectral data cube. Because the first few PCA output channels contain the majority of information in the hyperspectral data cube, we do not denoise these PCA output channel images. We use the block-matching 4D (BM4D) filtering to reduce the noise in the remaining low-energy noisy PCA output channel images. Finally, an inverse PCA transform is performed in order to obtain the denoised hyperspectral data cube. Experimental results show that our proposed method in this work is very competitive when compared with existing methods for hyperspectral imagery denoising.

Multiple-Spectral-Band CRFs for Denoising Junk Bands of Hyperspectral Imagery

Denoising of hyperspectral imagery in the domain of imaging spectroscopy by conditional random fields (CRFs) is addressed in this work. For denoising of hyperspectral imagery, the strong dependencies across spatial and spectral neighbors have been proved to be very useful. Many available hyperspectral image denoising algorithms adopt multidimensional tools to deal with the problems and thus naturally focus on the use of the spectral dependencies. However, few of them were specifically designed to use the spatial dependencies. In this paper, we propose a multiple-spectral-band CRF (MSB-CRF) to simultaneously model and use the spatial and spectral dependencies in a unified probabilistic framework. Furthermore, under the proposed MSB-CRF framework, we develop two hyperspectral image denoising algorithms, which, thanks to the incorporated spatial and spectral dependencies, can significantly remove the noise, while maintaining the important image details. The experiments are conducted in both simulated and real noisy conditions to test the proposed denoising algorithms, which are shown to outperform the popular denoising methods described in the previous literatures.

Denoising of hyperspectral imagery by combining PCA with block-matching 3-D filtering

Even though the noise level in a hyperspectral data cube may be low, it still can affect most remote sensing applications. In this paper, a novel method is proposed for reducing noise in a hyperspectral data cube. The method first used principal component analysis (PCA) to decorrelate the useful information from noise and then applied block-matching and 3-D filtering to selectively reduce noise in the noisy PCA components. Finally, an inverse PCA was conducted to obtain a denoised data cube. The first few PCA components contained the majority of information in the hyperspectral data cube and very little noise. Because the method did not denoise the first few PCA components, most fine feature details in the data cube were retained after denoising. The signal-to-noise ratio after denoising the Greater Victoria Watershed District and the Cuprite data cubes improved significantly. From our experiments, the proposed method was very competitive when compared with other existing denoising methods published in the literature.

Simultaneous dimensionality reduction and denoising of hyperspectral imagery using bivariate wavelet shrinking and principal component analysis

In this paper, we propose a method that not only reduces the dimensionality of a hyperspectral data cube but also removes noise in the data cube by combining the bivariate wavelet thresholding with principal component analysis (PCA). The data cube thus obtained is applied to mineral endmember extraction and mineral detection. The reason why we incorporate bivariate wavelet denoising into PCA dimensionality reduction is because the dimensionality-reduced channels using PCA often contain significant amounts of noise. By reducing noise in the data cube, we can get better dimensionality-reduced output channels for hyperspectral data analysis and processing. Experiments reported in this paper confirm that the proposed method outperforms PCA for endmember extraction and mineral detection using the Cuprite data cube.