Adaptive Spatial-Spectral Dictionary Learning for Hyperspectral Image Denoising

Fu, Ying; Lam, Antony; Sato, Iwao; Sato, Yoichi

doi:10.1109/iccv.2015.47

Cited by 36 publications

(21 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the augmented Lagrangian multiplier method (ALM) [42] is considered to solve (11). So the augmented Lagrange function of (11) is written as…”

Section: A Kernel Regression In Hs Imagesmentioning

confidence: 99%

“…Qian et al [10] introduced the spatial and spectral structure into sparse representation for HS denoising, in which similar patches are collected to ensure the sparsity. Fu et al [11] learned an adaptive spatial-spectral dictionary from the noisy HS images for noise removal. Subsequently, Zhuang et al [12] combined low-rank and sparse representation to capture the spatial and spectral correlation in HS images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral Image Denoising Using 3-D Geometrical Kernel With Local Similarity Prior

Zhang

Sun

et al. 2021

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

View full text Add to dashboard Cite

The majority of existing hyperspectral (HS) image denoising methods exploit local similarity in HS images by rearranging them into the matrix or vector forms. As the typical 3D data, the inherent spatial and spectral properties in HS images should be simultaneously explored for denoising. Therefore, a 3D geometrical kernel (3DGK) is developed in this paper to describe the local structure. The proposed method assumes that the pixel can be represented by other pixels within a 3D block efficiently owing to the local similarity with adjacent positions. Then, the HS image is modeled by the 3D kernel regression with L1-norm constraint, in which the local similarity is captured by the proposed 3DGK. To efficiently compute the parameters in 3DGK, geometrical structures, such as scale, shape, and orientation in the 3D block, are estimated from the gradient information approximately. Finally, the noises are effectively removed while preserving the structures in HS images. Moreover, experimental results on simulated and real datasets demonstrate that the performance of 3DGK is better than those of the methods based on local similarity prior.

show abstract

“…Then, the augmented Lagrangian multiplier method (ALM) [42] is considered to solve (11). So the augmented Lagrange function of (11) is written as…”

Section: A Kernel Regression In Hs Imagesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Denoising Using 3-D Geometrical Kernel With Local Similarity Prior

Zhang

Sun

et al. 2021

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

View full text Add to dashboard Cite

show abstract

“…The third type of HSI denoising methods combines spatial and spectral information to achieve better denoising performance [14][15][16][17][18][19]. Fu et al make use of the spectral correlation along the bands and the non-local spatial similarity to learn the adaptive dictionary for HSI denoising [16].…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Destriping and Denoising Using Stripe and Spectral Low-Rank Matrix Recovery and Global Spatial-Spectral Total Variation

2021

View full text Add to dashboard Cite

Hyperspectral image (HSI) is easily corrupted by different kinds of noise, such as stripes, dead pixels, impulse noise, Gaussian noise, etc. Due to less consideration of the structural specificity of stripes, many existing HSI denoising methods cannot effectively remove the heavy stripes in mixed noise. In this paper, we classify the noise on HSI into three types: sparse noise, stripe noise, and Gaussian noise. The clean image and different types of noise are treated as independent components. In this way, the image denoising task can be naturally regarded as an image decomposition problem. Thanks to the structural characteristic of stripes and the low-rank property of HSI, we propose to destripe and denoise the HSI by using stripe and spectral low-rank matrix recovery and combine it with the global spatial-spectral TV regularization (SSLR-SSTV). By considering different properties of different HSI ingredients, the proposed method separates the original image from the noise components perfectly. Both simulation and real image denoising experiments demonstrate that the proposed method can achieve a satisfactory denoising result compared with the state-of-the-art methods. Especially, it outperforms the other methods in the task of stripe noise removal visually and quantitatively.

show abstract

“…In recent years, dictionary learning has been widely applied in various fields due to its excellent performance, such as face recognition [1][2][3], image denoising [4,5] and blurring [6,7], image segmentation [8,9], and image recognition [10]. For face recognition [11,12], the conventional dictionary learning method first learns a dictionary through the training samples.…”

Section: Introductionmentioning

confidence: 99%

A Dictionary Learning Algorithm Based on Dictionary Reconstruction and Its Application in Face Recognition

Zheng

Zhang

Liu

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In recent years, dictionary learning has received more and more attention in the study of face recognition. However, most dictionary learning algorithms directly use the original training samples to learn the dictionary, ignoring noise existing in the training samples. For example, there are differences between different images of the same subject due to changes in illumination, expression, etc. To address the above problems, this paper proposes the dictionary relearning algorithm (DRLA) based on locality constraint and label embedding, which can effectively reduce the influence of noise on the dictionary learning algorithm. In our proposed dictionary learning algorithm, first, the initial dictionary and coding coefficient matrix are directly obtained from the training samples, and then the original training samples are reconstructed by the product of the initial dictionary and coding coefficient matrix. Finally, the dictionary learning algorithm is reapplied to obtain a new dictionary and coding coefficient matrix, and the newly obtained dictionary and coding coefficient matrix are used for subsequent image classification. The dictionary reconstruction method can partially eliminate noise in the original training samples. Therefore, the proposed algorithm can obtain more robust classification results. The experimental results demonstrate that the proposed algorithm performs better in recognition accuracy than some state-of-the-art algorithms.

show abstract

Adaptive Spatial-Spectral Dictionary Learning for Hyperspectral Image Denoising

Cited by 36 publications

References 44 publications

Hyperspectral Image Denoising Using 3-D Geometrical Kernel With Local Similarity Prior

Hyperspectral Image Denoising Using 3-D Geometrical Kernel With Local Similarity Prior

Hyperspectral Image Destriping and Denoising Using Stripe and Spectral Low-Rank Matrix Recovery and Global Spatial-Spectral Total Variation

A Dictionary Learning Algorithm Based on Dictionary Reconstruction and Its Application in Face Recognition

Contact Info

Product

Resources

About