Seismic Random Noise Attenuation Using Sparse Low-Rank Estimation of the Signal in the Time–Frequency Domain

Anvari, Rasoul; Kahoo, Amin Roshandel; Mohammadi, Mokhtar; Khan, Nabeel Ali; Chen, Yangkang

doi:10.1109/jstars.2019.2906360

Cited by 42 publications

(14 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 (a) and 1 (c). This shows the local correlation values between estimated noise and denoised image using [13]. Here, blue color indicates less signal leakage.…”

Section: Motivation and Problem Formulationmentioning

confidence: 99%

“…To this end, we propose a novel unsupervised deep learning method augmenting patch-based dictionary learning (DL) and residual learning (RL) in order to learn the noise in augmented manner and construct a novel dictionary-based deep residue network (DRN) for denoising of 2D and 3D MRI and CT data including LDCT images. We perform ablation studies on the proposed DL and DRN parts in order to show signal (image) leakage [13] in the estimated denoised images and for better dissemination of results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Augmented Noise Learning Framework for Enhancing Medical Image Denoising

2021

View full text Add to dashboard Cite

Deep learning attempts medical image denoising either by directly learning the noise present or via first learning the image content. We observe that residual learning (RL) often suffers from signal leakage while dictionary learning (DL) is prone to Gibbs (ringing) artifacts. In this paper, we propose an unsupervised noise learning framework that enhances denoising by augmenting the limitation of RL with the strength of DL and vice versa. To this end, we propose a ten-layer deep residue network (DRN) augmented with patch-based dictionaries. The input images are presented to patch-based DL to indirectly learn the noise via sparse representation while given to the DRN to directly learn the noise. An optimum noise characterization is captured by iterating DL/DRN network against proposed loss. The denoised images are obtained by subtracting the learned noise from available data. We show that augmented DRN effectively handles high-frequency regions to avoid Gibbs artifacts due to DL while augmented DL helps to reduce the overfitting due to RL. Comparative experiments with many state-of-the-arts on MRI and CT datasets (2D/3D) including low-dose CT (LDCT) are conducted on a GPU-based supercomputer. The ablation studies are carried out that demonstrate enhanced denoising performance with minimal signal leakage and least artifacts by proposed augmented approach.

show abstract

“…1 (a) and 1 (c). This shows the local correlation values between estimated noise and denoised image using [13]. Here, blue color indicates less signal leakage.…”

Section: Motivation and Problem Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Augmented Noise Learning Framework for Enhancing Medical Image Denoising

2021

View full text Add to dashboard Cite

show abstract

“…According to Ref. [ 49 ], if the unconstrained convex optimization problem is differentiable, it can be solved by proximal gradient descends algorithm. The following minimization optimization problem can be depicted as follows:

…”

Section: Proposed Slrgsd Framework For Bearing Fault Diagnosismentioning

confidence: 99%

Simultaneously Low Rank and Group Sparse Decomposition for Rolling Bearing Fault Diagnosis

Zheng

Yin

Xiong

et al. 2020

Sensors

View full text Add to dashboard Cite

Singular value decomposition (SVD) methods have aroused wide concern to extract the periodic impulses for bearing fault diagnosis. The state-of-the-art SVD methods mainly focus on the low rank property of the Hankel matrix for the fault feature, which cannot achieve satisfied performance when the background noise is strong. Different to the existing low rank-based approaches, we proposed a simultaneously low rank and group sparse decomposition (SLRGSD) method for bearing fault diagnosis. The major contribution is that the simultaneously low rank and group sparse (SLRGS) property of the Hankel matrix for fault feature is first revealed to improve performance of the proposed method. Firstly, we exploit the SLRGS property of the Hankel matrix for the fault feature. On this basis, a regularization model is formulated to construct the new diagnostic framework. Furthermore, the incremental proximal algorithm is adopted to achieve a stationary solution. Finally, the effectiveness of the SLRGSD method for enhancing the fault feature are profoundly validated by the numerical analysis, the artificial bearing fault experiment and the wind turbine bearing fault experiment. Simulation and experimental results indicate that the SLRGSD method can obtain superior results of extracting the incipient fault feature in both performance and visual quality as compared with the state-of-the-art methods.

show abstract

“…Fault detection is a basic and important aspect of seismic data interpretation, the reliability of which is greatly affected by the signal-to-noise ratio (SNR). Due to the influence of various complex factors, such as the vibration of the external environment, the interference of industrial alternating currents, and complex shallow surfaces, seismic data inevitably contain random noise, which results in a relatively low SNR [1][2][3]. Thus, reducing random noise during seismic data processing, while preserving complex structural information has important practical significance.…”

Section: Introductionmentioning

confidence: 99%

A local binary patterns/variance operator based on guided filtering for seismic fault detection

2021

View full text Add to dashboard Cite

Aiming at suppressing noise interference, improving the fault detection ability of seismic data, fully excavating the effective information in seismic data, and further improving the accuracy of fault detection, this study proposes a seismic fault detection method that combines the local binary pattern/variance (LBP/VAR) operator with guided filtering. The proposed method combines the advantages of LBP/VAR and guided filtering to remove noise from seismic data, and can simultaneously smooth the data and preserve linear features. When compared with several existing methods (coherent operator, LBP/VAR operator, LBP/VAR operator based on median filtering, and Canny operator based on guided filtering), the proposed method exhibits a better SNR, a better ability to identify small faults, and robustness to noise. This novel algorithm can control the balance between noise attenuation and effective signal preservation as well as effectively detect faults in seismic data. Therefore, the proposed method effectively improves the fault identification accuracy, facilitates the gas-bearing analysis of the structure, provides guidance for the actual well location deployment of the project, and has important practical significance for oil and gas exploration and development.

show abstract

Seismic Random Noise Attenuation Using Sparse Low-Rank Estimation of the Signal in the Time–Frequency Domain

Cited by 42 publications

References 32 publications

Augmented Noise Learning Framework for Enhancing Medical Image Denoising

Augmented Noise Learning Framework for Enhancing Medical Image Denoising

Simultaneously Low Rank and Group Sparse Decomposition for Rolling Bearing Fault Diagnosis

A local binary patterns/variance operator based on guided filtering for seismic fault detection

Contact Info

Product

Resources

About