Tensor Decomposition and PCA Jointed Algorithm for Hyperspectral Image Denoising

Meng, Shushu; Huang, Longting; Wang, Wen-Qin

doi:10.1109/lgrs.2016.2552403

Cited by 38 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Ahmadi-Asl et al (2021) utilized randomized algorithms to accelerate Tucker decomposition and higher-order SVD. A hyperspectral image denoising method, joint tensor decomposition and principal component analysis (PCA) algorithm were proposed (Meng et al, 2016). The method outperformed existing methods in terms of peak signal-to-noise ratio (PSNR).…”

Section: Tucker Decompositionmentioning

confidence: 99%

Improved Tucker decomposition algorithm for noise suppression of 3D GPR data in road detection

Yan

Zhang

2023

Near Surface Geophysics

View full text Add to dashboard Cite

The echo data of ground‐penetrating radar (GPR) have a low signal‐to‐noise ratio. Denoising and interference suppression are important for improving the accuracy of underground target recognition and detection. In this paper, a new method of noise analysis and suppression of 3D GPR is proposed, transforming the problem of noise reduction into an optimization problem regarding a third‐order tensor. This method is improved with the following features; a bidimensional empirical mode decomposition (BEMD) algorithm is employed to decompose the 3D GPR noise. The main source of the noise is determined by computing the standard deviation of each component decomposed. For the shortcoming of the existing GPR denoising methods that reduce the dimension of 3D GPR data, the proposed approach can denoise 3D GPR data directly to avoid the loss of data caused by reducing the dimension. This preserves the desired signal and extracts noise through the Tucker decomposition of 3D GPR data. An improved high‐order orthogonal iteration algorithm is utilized to optimize the decomposition. The peak signal‐to‐noise ratio (PSNR) of the signal for each survey line is calculated to evaluate the effectiveness of noise reduction. Simulations and real data sets are provided to compare the performance of algorithms. The results show that the mean PSNR after noise suppression with our method is 8.915 dB and 16.458 dB higher than wavelet transform and singular value decomposition algorithms, respectively. This demonstrates that the proposed approach can better suppress 3D GPR noise and provides technical support for improving 3D GPR data quality and road detection accuracy.

show abstract

Section: Tucker Decompositionmentioning

confidence: 99%

Improved Tucker decomposition algorithm for noise suppression of 3D GPR data in road detection

Yan

Zhang

2023

Near Surface Geophysics

View full text Add to dashboard Cite

show abstract

“…Due to the improvement in optimization methods, the accuracy of infrared small target detection is constantly improving [30]- [38]. In optimization methods, principal component analysis (PCA) is a classic model [39], which reduces the dimensionality of high-dimensional data, removes sparse irrelevant information, and obtains the main information. From another perspective, we can also treat cirrus as the sparse component in infrared images and obtain it by PCA.…”

Section: A Related Workmentioning

confidence: 99%

Cirrus Detection Based on Tensor Multi-Mode Expansion Sum Nuclear Norm in Infrared Imagery

et al. 2020

View full text Add to dashboard Cite

Infrared small target detection systems are an important part of space infrared imaging satellites. However, small infrared target detection is often affected by cirrus false alarm sources with similar grayscales. In this paper, an infrared cirrus detection method based on the tensor robust principal component analysis model (TRPCA) is proposed. The method treats multiple bands of remote sensing data as tensors, but classical tensor nuclear norms cannot represent the tensor rank well; therefore, we use tensor multi-mode expansion sum nuclear norm (TMESNN) to approximate the tensor rank better. First, a set of Landsat-8 data is transformed into a tensor model, and a TRPCA model is constructed by TMESNN and the 1 L norm. Then, this model is solved by Ket augments and the alternating direction method of multipliers (ADMM). Finally, Mallat wavelet transform is used to supplement information and remove clutter, and the final detection result is obtained by adaptive threshold segmentation. Compared with other optimizationbased methods, this method has better detection performance and accuracy.

show abstract

“…e experimental results prove the effectiveness of the proposed method [5]. In order to overcome this shortcoming, Meng S solved the HSI denoising problem by combining Tucker decomposition and principal component analysis (PCA) [6]. Bawane et al believe that there have been many successful applications of the first two generations of neural networks.…”

Section: Introductionmentioning

confidence: 98%

Language and Literature Layout Integrating Text Image Preprocessing Algorithm

Wang

Fu³

2022

Mobile Information Systems

View full text Add to dashboard Cite

The Chinese language and literature layout has important application value. How to quickly and efficiently deal with the huge amount, diverse forms, and complex content of Chinese language and literature is a problem that people pay more attention to. In addition, a large number of digital resources exist in the form of images instead of text encoding. How to efficiently manage and use this document information, especially the fast retrieval of document content, is an important research direction. This paper mainly discusses the processing of Chinese language and literature layout combined with text image preprocessing algorithm and researches into the skew correction of document images. There are many types of documents, and many tilt correction methods are based on prior knowledge. If such a sample quality situation occurs, the image needs to be preprocessed. Using denoising to remove useless noise information and using correction technology to leave and strengthen the classified effective information, we can carry out the next step of retrieval and recognition. The preprocessing avoids interference and destruction of the feature description algorithm by other factors as much as possible and guarantees the effect of recognition and retrieval to a certain extent. This paper proposes a method of document image tilt correction based on the content of the document. According to different document contents, we select the corresponding strategy to estimate the document tilt. This paper uses two-dimensional wavelet transform, runs length smoothing and thinning preprocessing to extract the lines and text lines in the document image, and uses the least square method of linear parameters to estimate the inclination angle of the document. This method has the characteristics of high accuracy of tilt estimation and strong adaptability. The accuracy of feature line matching in geometric structure classification can reach 97%. This research helps to promote the continuous development of Chinese language and literature.

show abstract

Tensor Decomposition and PCA Jointed Algorithm for Hyperspectral Image Denoising

Cited by 38 publications

References 17 publications

Improved Tucker decomposition algorithm for noise suppression of 3D GPR data in road detection

Improved Tucker decomposition algorithm for noise suppression of 3D GPR data in road detection

Cirrus Detection Based on Tensor Multi-Mode Expansion Sum Nuclear Norm in Infrared Imagery

Language and Literature Layout Integrating Text Image Preprocessing Algorithm

Contact Info

Product

Resources

About