<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>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 <inline-formula>
<alternatives>
<inline-graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="graphic/j_amns-2024-0172_eq_001.png"></inline-graphic>
<math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"><mrow><mi>μ</mi><mo>=</mo><mi>C</mi><mo>max</mo><mrow><mo>(</mo><mrow><msqrt><mtext>m</mtext></msqrt><mo>,</mo><msqrt><mtext>n</mtext></msqrt></mrow><mo>)</mo></mrow><mi>σ</mi></mrow></math>
<tex-math>\mu  = C\max \left( {\sqrt {\rm{m}} ,\sqrt {\rm{n}} } \right)\sigma</tex-math>
</alternatives>
</inline-formula>, 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.</p>
</abstract>

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=Cmax(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.

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

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

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...

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

Published Online: Jan 31, 2024

Page range: -

Received: Dec 18, 2023

Accepted: Dec 27, 2023

DOI: https://doi.org/10.2478/amns-2024-0172

Keywords
Low tensor decomposition, Full variational model, Hyperspectral image denoising, Generalized Lagrangian method

© 2024 Chushen Chen, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

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

Published Online: Jan 31, 2024

Page range: -

Received: Dec 18, 2023

Accepted: Dec 27, 2023

DOI: https://doi.org/10.2478/amns-2024-0172

KeywordsLow tensor decomposition, Full variational model, Hyperspectral image denoising, Generalized Lagrangian method

© 2024 Chushen Chen, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Keywords
Low tensor decomposition, Full variational model, Hyperspectral image denoising, Generalized Lagrangian method