Dictionary learning based on dip patch selection training for random noise attenuation
- 1 May 2019
- journal article
- research article
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 84 (3) , V169-V183
Abstract
In recent years, sparse representation is seeing increasing application to fundamental signal and image-processing tasks. In sparse representation, a signal can be expressed as a linear combination of a dictionary (atom signals) and sparse coefficients. Dictionary learning has a critical role in obtaining a state-of-the-art sparse representation. A good dictionary should capture the representative features of the data. The whole signal can be used as training patches to learn a dictionary. However, this approach suffers from high computational costs, especially for a 3D cube. A common method is to randomly select some patches from given data as training patches to accelerate the learning process. However, the random selection method without any prior information will damage the signal if the selected patches for training are inappropriately chosen from a simple structure (e.g., training patches are chosen from a simple structure to recover the complex structure). We have developed a dip-oriented dictionary learning method, which incorporates an estimation of the dip field into the selection procedure of training patches. In the proposed approach, patches with a large dip value are selected for the training. However, it is not easy to estimate an accurate dip field from the noisy data directly. Hence, we first apply a curvelet-transform noise reduction method to remove some fine-scale components that presumably contain mostly random noise, and we then calculate a more reliable dip field from the preprocessed data to guide the patch selection. Numerical tests on synthetic shot records and field seismic image examples demonstrate that the proposed method can obtain a similar result compared with the method trained on the entire data set and obtain a better denoised result compared with the random selection method. We also compare the performance using of the proposed method and those methods based on curvelet thresholding and rank reduction on a synthetic shot record.Keywords
Funding Information
- National Natural Science Foundation of China (41630314)
- National Major Science and Technology Program (2016ZX05010-001)
- Major Project of the China National Petroleum Corporation (2016A-3304, 2017D-5006-16)
This publication has 75 references indexed in Scilit:
- Nonlinear structure‐enhancing filtering using plane‐wave prediction*Geophysical Prospecting, 2010
- Nonequispaced curvelet transform for seismic data reconstruction: A sparsity-promoting approachGeophysics, 2010
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006
- Fast Discrete Curvelet TransformsMultiscale Modeling & Simulation, 2006
- Applications of plane-wave destruction filtersGeophysics, 2002
- Atomic Decomposition by Basis PursuitSIAM Review, 2001
- Noncausal spatial prediction filtering for random noise reduction on 3-D poststack dataGeophysics, 2000
- Lateral prediction for noise attenuation by t-x and f-x techniquesGeophysics, 1995
- Estimating two-dimensional frequencies by matrix enhancement and matrix pencilIEEE Transactions on Signal Processing, 1992
- Signal enhancement-a composite property mapping algorithmIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988