Study of Parameters in Dictionary Learning Method for Seismic Denoising

Kuruguntla, Lakshmi; Dodda, Vineela Chandra; Elumalai, Karthikeyan

doi:10.1109/tgrs.2021.3107541

Cited by 13 publications

(3 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was estimated, based on our simulations, an 8 × 8 patch size provides a superior result in terms of peak signal-to-noise ratio (PSNR). It is worth to mention the fact that the selection of smaller patch size gives the finer details while the larger patch size may lose the finer details from an inputted image 42 . To note, we used 20% of the PCSI patches for validation and 60% of patches are allotted for training purpose.…”

Section: Resultsmentioning

confidence: 99%

“…As the denoising network does not require clean labels, the method is feasible for use in a wide variety of scenarios. It is therefore planned to extend this investigation by more closely identifying the patching process and parameter tuning in the architecture to achieve better denoised results 42 . This includes examining such network on some classical optical imaging systems that suffer from inevitable noises.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A denoising framework for 3D and 2D imaging techniques based on photon detection statistics

Dodda

Kuruguntla

Elumalai

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

A method to capture three-dimensional (3D) objects image data under extremely low light level conditions, also known as Photon Counting Imaging (PCI), was reported. It is demonstrated that by combining a PCI system with computational integral imaging algorithms, a 3D scene reconstruction and recognition is possible. The resulting reconstructed 3D images often look degraded (due to the limited number of photons detected in a scene) and they, therefore, require the application of superior image restoration techniques to improve object recognition. Recently, Deep Learning (DL) frameworks have been shown to perform well when used for denoising processes. In this paper, for the first time, a fully unsupervised network (i.e., U-Net) is proposed to denoise the photon counted 3D sectional images. In conjunction with classical U-Net architecture, a skip block is used to extract meaningful patterns from the photons counted 3D images. The encoder and decoder blocks in the U-Net are connected with skip blocks in a symmetric manner. It is demonstrated that the proposed DL network performs better, in terms of peak signal-to-noise ratio, in comparison with the classical TV denoising algorithm.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

A denoising framework for 3D and 2D imaging techniques based on photon detection statistics

Dodda

Kuruguntla

Elumalai

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…The introduction of self-adaptation can realize blind denoising of seismic data and obtain signals with a high SNR. Kuruguntla et al (2021) introduced a double sparse dictionary learning constraint to improve the denoising performance. This method combines the strength of the analytical transform and adaptive transform to suppress mixing noise.…”

Section: Introductionmentioning

confidence: 99%

Prestack seismic random noise attenuation using the wavelet-inspired invertible network with atrous convolutions spatial pyramid

Wu²,

Xu³

2023

Front. Earth Sci.

View full text Add to dashboard Cite

Convolutional Neural Network (CNN) is widely used in seismic data denoising due to its simplicity and effectiveness. However, traditional seismic denoising methods based on CNN ignore multi-scale features of seismic data in the wavelet domain. The lack of these features will decrease the accuracy of denoising results. To address this barrier, a seismic denoise method based on the wavelet-inspired invertible network with atrous convolutions spatial pyramid (WINNet_ACSP) is proposed. WINNet_ACSP follows the principle of lifting wavelet transform. The proposed method utilizes the redundant orthogonal wavelet transform to obtain frequency multi-scale information from noisy seismic data. Then predict update network (PUNet) extracts spatial multi-scale features of approximate and detailed parts. The sparse driven network (SDN) learns the complex multi-scale information and obtains sparse features. These sparse features are processed to eliminate random noise. Compared to standard convolution, the atrous convolutions spatial pyramid (ACSP) can extract more features. The redundant features are the key to ensure the precision of multi-scale information. Therefore, the introduction of ACSP in PUNet can guarantee the denoising effect of the network. WINNet_ASCP combines the characteristics of wavelet transform and neural network and has a high generalization. Besides, transfer learning is used to overcome the difficulty caused by the training sample size of seismic data. The training process includes pre-training and post-training. The former is trained to obtain the initial denoising network by natural image samples. The latter is trained with a small sample of seismic data to enhance stratigraphic continuity. Finally, the proposed method is tested with synthetic and field data. The experimental results show that the proposed method can effectively remove random noise and reduce the loss of detailed information in prestack seismic data. In the future, we will make further improvements on this basis and conduct experiments on 3D prestack data.

show abstract

Advanced Signal Processing in Distributed Acoustic Sensors Based on Submarine Cables for Seismology Applications

Chen

Jun

Sui

et al. 2023

J. Lightwave Technol.

View full text Add to dashboard Cite

Study of Parameters in Dictionary Learning Method for Seismic Denoising

Cited by 13 publications

References 62 publications

A denoising framework for 3D and 2D imaging techniques based on photon detection statistics

A denoising framework for 3D and 2D imaging techniques based on photon detection statistics

Prestack seismic random noise attenuation using the wavelet-inspired invertible network with atrous convolutions spatial pyramid

Advanced Signal Processing in Distributed Acoustic Sensors Based on Submarine Cables for Seismology Applications

Contact Info

Product

Resources

About