Search

Abstract During the acquisition of a hyperspectral image (HSI), it is easily corrupted by many kinds of noises, which limits the subsequent applications. For decades, numerous HSI denoising methods have been proposed. However, these methods rarely consider the stripe noise as an independent component, thus cannot effectively remove the stripe noise. In this paper, we propose a mixed noise removal algorithm to destripe an HSI by taking advantage of the low-rank property of stripe noise. In the meantime, sparse representation and graph Laplacian regularization are utilized to remove Gaussian and sparse noise. Roughly speaking, the sparse representation helps achieve the approximation of the original image. A graph Laplacian regularization term can ensure the non-local spatial similarity of an HSI. Separate constraints on the sparse coefficient matrix and stripe noise components can help remove different types of noises. Experimental results on both simulated and real data demonstrate the effectiveness of the proposed method for HSI restoration.

Under the unbalance-bearing coupling fault of the rotor system, the unbalance fault features and bearing faults modulate each other, and the weak fault features are easily submerged by the strong fault features and strong noise components. Thus, a multi-step grid search optimization sparse diagnosis method is proposed to improve the anti-interference ability of sparse representation algorithm by selecting the optimal parameters of sparse representation to reduce the sparse reconstruction error. Firstly, based on the multi-step grid search theory, a multi-step grid search optimization sparse representation method model is established to improve the calculation accuracy. Secondly, the signal reconstruction based on adaptive Gabor atom dictionary orthogonal matching tracking algorithm is realized by optimizing the displacement factor and frequency factor. Finally, the coupling simulation fault data with different SNR are analyzed. The results show that the anti-interference ability of the proposed method increases with the increase of noise interference and different experimental cases further verify the accuracy and applicability of the proposed method.

Abstract Many methods based on deep learning have achieved amazing results in image sentiment analysis. However, these existing methods usually pursue high accuracy, ignoring the effect on model training efficiency. Considering that when faced with large‐scale sentiment analysis tasks, the high accuracy rate often requires long experimental time. In view of the weakness, a method that can greatly improve experimental efficiency with only small fluctuations in model accuracy is proposed, and singular value decomposition (SVD) is used to find the sparse feature of the image, which are sparse vectors with strong discriminativeness and effectively reduce redundant information; The authors propose the Fast Dictionary Learning algorithm (FDL), which can combine neural network with sparse representation. This method is based on K‐Singular Value Decomposition, and through iteration, it can effectively reduce the calculation time and greatly improve the training efficiency in the case of small fluctuation of accuracy. Moreover, the effectiveness of the proposed method is evaluated on the FER2013 dataset. By adding singular value decomposition, the accuracy of the test suite increased by 0.53%, and the total experiment time was shortened by 8.2%; Fast Dictionary Learning shortened the total experiment time by 36.3%.

In this paper, a sparse representation based compression of fused images is proposed using Multi-Resolution Singular Value Decomposition (MSVD). The main idea of this work is to identify significant and less significant details using MSVD. The core information is fused using the absolute maximum rule while the less significant information is fused using sparse representation. The fused significant information is compressed using wavelet difference reduction coding. On the flip side, the fused less significant information is compressed using quantization and Huffman encoding. On the receiver side, the proposed recovery algorithm can be used to obtain the fused image. The superiority of the proposed technique can be analyzed from the comparison of the proposed work with some related work.

In this paper, we provide a sparse image restoration algorithm with a SSIM-based objective function. The proposed technique is a modification to the SSIM-inspired OMP (iOMP) and, and it has two parallel sparse restoration paths. One of them is L2-sense OMP and the other is SSIM-sense OMP (iOMP). Both paths intersects only at the starting point and gives different quality levels after each iteration. This distinction enables us to select the coefficients of the best quality and to avoid the uncertainty issue of iOMP. From the point of view of the SSIM levels, the conducted experiments proved that, the proposed methodology works better than iOMP and OMP. Also, the performance of this method is checked for significance by the t-test, and the obtained results proved that the method works well especially for large images and the data-independent based dictionary.

Abstract Biometric verification is generally considered a one-to-one matching task. In contrast, in this paper, we argue that the one-to-many competitive matching via sparse representation-based classification (SRC) can bring enhanced verification security and accuracy. SRC-based verification introduces non-target subjects to construct dynamic dictionary together with the client claimed and encodes the submitted feature. Owing to the sparsity constraint, a client can only be accepted when it defeats almost all non-target classes and wins a convincing sparsity-based matching score. This will make the verification more secure than those using one-to-one matching. However, intense competition may also lead to extremely inferior genuine scores when data degeneration occurs. Motivated by the latent benefits and concerns, we study SRC-based verification using two sparsity-based matching measures, three biometric modalities (i.e., face, palmprint, and ear) and their multimodal combinations based on both handcrafted and deep learning features. We finally approach a comprehensive study of SRC-based verification, including its methodology, characteristics, merits, challenges and the directions to resolve. Extensive experimental results demonstrate the superiority of SRC-based verification, especially when using multimodal fusion and advanced deep learning features. The concerns about its efficiency in large-scale user applications can be readily solved using a simple dictionary shrinkage strategy based on cluster analysis and random selection of non-target subjects.

In order to improve the sparse coding ability of over-complete dictionary and take advantage of the similarity between damaged pixels and their neighbors, we propose an inpainting method based on sparse representation using self-similar joint sparse coding. First, we perform singular value decomposition on the gradient vector of the image patches, and then divide the image patches into three categories: smooth patches, edge patches and texture patches according to the relationship between the primary direction and the secondary direction. Second, we use the KSVD method to train these three types of image patches respectively, and obtain three over-complete dictionaries that adapt to different local features. Third, we define a non-local self-similar matching function and use it to search for the most similar image patch to the current patch in the target region, and then use the similar patch and the current patch for joint sparse coding. Finally, we use the calculated sparse coding and the corresponding over-complete dictionary to reconstruct the current patch. A series of experimental results show that the self-similar joint sparse coding we proposed can not only improve the restoration effect of sparse representation methods to a certain extent, but also has good adaptability and can be combined with other sparse representation methods to improve their restoration effect. [ABSTRACT FROM AUTHOR]

This study proposes a data condensation method for multivariate kernel density estimation by genetic algorithm. First, our proposed algorithm generates multiple subsamples of a given size with replacement from the original sample. The subsamples and their constituting data points are regarded as chromosome and gene, respectively, in the terminology of genetic algorithm. Second, each pair of subsamples breeds two new subsamples, where each data point faces either crossover, mutation, or reproduction with a certain probability. The dominant subsamples in terms of fitness values are inherited by the next generation. This process is repeated generation by generation and results in a kernel density estimator with sparse representation in its completion. We confirmed from simulation studies that the resulting estimator can perform better than other well-known density estimators. [ABSTRACT FROM AUTHOR]

The Convolutional Sparse Coding (CSC) model has recently attracted a lot of attention in the signal and image processing communities. Since, in traditional sparse coding methods, a significant assumption is that all input samples are independent, so it is not well for most dependent works. In such cases, CSC models are a good choice. In this paper, we proposed a novel CSC-based classification model which combines the local block coordinate descent (LoBCoD) algorithm with the classification strategy. For this, in the training phase, the convolutional dictionary atoms (filters) of each class are learned by all training samples of the same class. In the test phase, the label of the query sample can be determined based on the reconstruction error of the filters related to every subject. Experimental results on five benchmark databases at the different number of training samples clearly demonstrate the superiority of our method to many state-of-the-art classification methods. Besides, we have shown that our method is less dependent on the number of training samples and therefore it can better work than other methods in small databases with fewer samples. For instance, increases of 26.27%, 18.32%, 11.35%, 13.5%, and 19.3% in recognition rates are observed for our method when compared to conventional SRC for five used databases at the least number of training samples per class. [ABSTRACT FROM AUTHOR]

The wheelset bearing is an indispensable part of the high-speed train, and monitoring its service performance is a concern of many researchers. Effective extraction of those impulse signals induced by the defects on the bearing elements is the key to fault detection and behaviour analysis. However, the presence of considerable noise and irrelevant components brings difficulties to extracting the wheelset bearing fault impulse signals from the measured vibration signals. This paper proposes an improved explicit shift-invariant dictionary learning (IE-SIDL) method to address this issue. Based on the shift-invariant characteristics of the wheelset bearing fault impulse signal in the time-domain, the circulant matrix is used to construct a shift-invariant dictionary and explicitly characterize the fault impulses at any time. To improve the efficiency of dictionary learning, a method of three flips is introduced to realize fast dictionary construction, and the frequency-domain reconstruction property of the circulant matrix is employed to quickly update the dictionary. Besides, an indicator-guided subspace pursuit (SP) method based on the sparsity of envelope spectrum (SES) is adopted for the sparse coding to improve sparse solution accuracy and adaptation. The effectiveness of the IE-SIDL method is proved through the simulated and experimental signals. The results demonstrate that the improved dictionary learning method has an excellent capacity in extracting fault impulse signal of the wheelset bearings, and the good time- and frequency-domain characteristics of the processed signals facilitate fault detection and behaviour analysis. • The method of three flips is employed to fast construct the explicit dictionary. • Subspace pursuit is adopted to improve the accuracy of the sparse solution. • Proposing one key parameter selection strategy for the SP method. • Good time-domain characteristics facilitate fault dynamic behaviour analysis. [ABSTRACT FROM AUTHOR]

In multimedia devices such as mobile phones, surveillance cameras, and web cameras, image sensors have limited spatial resolution. As a result, the image captured from these devices misses high-frequency content and exhibits visual artifacts. Image super-resolution (SR) algorithms can minimize these artifacts by reconstructing missing high-frequency textures. Image SR algorithm estimates a high resolution (HR) image from a given low-resolution (LR) image. Given a single LR image, reconstructing an HR image makes SR be an extremely ill-posed problem. Over the past decade, dictionary learning-based methods have shown promising results in SR reconstruction. These methods extract numerous patches from external images for training dictionaries via sparse representation. However, these methods do not involve any patch selection mechanism that enhances the learning process. This paper proposes a dictionary learning-based SR algorithm that extracts selective patches from an input LR image based on the iScore criterion. Results show that patch selection criteria keep only 36% of all extracted patches for training while improving the peak signal-to-noise ratio (PSNR). Furthermore, we have proposed a method to initialize dictionaries to achieve better convergence that enhances PSNR. [ABSTRACT FROM AUTHOR]

• A novel joint sparse representation is constructed based on global statistical and local patch dictionaries from visual data. • The proposed method can be utilized for both image and image-set classification tasks with an efficient yet effective algorithm. • The proposed method achieves superior results on both image and imageset classification tasks. • Extensive experiments on few-shot and robust scenarios demonstrate the effectiveness and generalizibility of the proposed method. Recent image classification algorithms, by learning deep features from large-scale datasets, have achieved significantly better results comparing to the classic feature-based approaches. However, there are still various challenges of image classifications in practice, such as classifying noisy image or image-set queries, and training deep image classification models over the limited-scale dataset. Instead of applying generic deep features, the model-based approaches can be more effective and data-efficient for robust image and image-set classification tasks, as various image priors are exploited for modeling the inter- and intra-set data variations while preventing over-fitting. In this work, we propose a novel Joint Statistical and Spatial Sparse representation scheme, dubbed J3S , to model the image or image-set data for classification. J3S utilized joint sparse representation to reconcile both the local image structures and global Gaussian distribution mapped into Riemannian manifold. The learned J3S models are used for robust image and image-set classification tasks. Experiments show that the proposed J3S-based image classification scheme outperforms the popular or state-of-the-art competing methods over FMD, UIUC, ETH-80 and YTC databases. [ABSTRACT FROM AUTHOR]

The vital signs are estimated from remote photoplethysmography (rPPG) using the sparse representation signal reconstruction approach. The rPPG signal is used to estimate the physical parameters with the help of a non-invasive smartphone camera. This paper presents a health monitoring method by estimating vital signs using an RGB video camera and uses a pre-specified dictionary based on a hybrid discrete ridgelet transform with a Ricker wavelet basis function, to reconstruct a sparse signal prone to less error. The physical parameters such as heart rate (HR), breathing rate (BR), heart rate variability (HRV), and SpO2 are estimated using a smartphone video camera with the proposed sparse signal reconstruction technique. The inter-beat intervals (IBIs) are used to extract the power ratio in the frequency domain. Changes in HRV are more discriminative indicators of cognitive stress than those in HR and BR. The physiological states such as stress and fatigue could be measured using IBIs ratio in the frequency domain. The morning and evening dataset sessions are recruited for this experiment to check the stress and fatigue factors based on the power ratio extracted from the IBI signal. In the results, a lower mean absolute probability error value shows that the proposed method produces better results than state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel framework to reconstruct image of a buried object from the ground-penetrating radar (GPR) reflection hyperbolas. The first reflection hyperbola of a buried object determines its relative permittivity and shape class (circle, rectangle, and triangle). The first two reflections are used to reconstruct image of a homogeneous buried object. After five preprocessing steps to extract region of interest of b-scan corresponding to a buried object, a Convolutional Neural Network (CNN) estimates the relative permittivity value of the buried object. Then, two novel schemes, including CNN and Dictionary Learning (DL) methods are proposed to reconstruct 2D image of the buried object. Image reconstructors are trained with a dataset containing buried objects with different shapes, sizes, and reference relative permittivity. Since two objects having the same size but different materials lead to different hyperbola reflections in their B-scans, we propose a novel transformation to convert the reflection scans from the estimated relative permittivity to a reference relative permittivity so that the image reconstructors can be used to rebuild images. The results reveal that the DL method outperforms the CNN method on noisy measurements, while the CNN method performs better when dealing with fewer traces. [ABSTRACT FROM AUTHOR]

Super-resolution techniques are used to reconstruct an image with a high resolution from one or more low-resolution image(s). In this paper, we proposed a single image super-resolution algorithm. It uses the nonlocal mean filter as a prior step to produce a denoised image. The proposed algorithm is based on curvelet transform. It converts the denoised image into low and high frequencies (sub-bands). Then we applied a multi-dimensional interpolation called Lancozos interpolation over both sub-bands. In parallel, we applied sparse representation with over complete dictionary for the denoised image. The proposed algorithm then combines the dictionary learning in the sparse representation and the interpolated sub-bands using inverse curvelet transform to have an image with a higher resolution. The experimental results of the proposed super-resolution algorithm show superior performance and obviously better-recovering images with enhanced edges. The comparison study shows that the proposed super-resolution algorithm outperforms the state-of-the-art. The mean absolute error is 0.021 ± 0.008 and the structural similarity index measure is 0.89 ± 0.08. [ABSTRACT FROM AUTHOR]

Biometric verification is generally considered a one-to-one matching task. In contrast, in this paper, we argue that the one-to-many competitive matching via sparse representation-based classification (SRC) can bring enhanced verification security and accuracy. SRC-based verification introduces non-target subjects to construct dynamic dictionary together with the client claimed and encodes the submitted feature. Owing to the sparsity constraint, a client can only be accepted when it defeats almost all non-target classes and wins a convincing sparsity-based matching score. This will make the verification more secure than those using one-to-one matching. However, intense competition may also lead to extremely inferior genuine scores when data degeneration occurs. Motivated by the latent benefits and concerns, we study SRC-based verification using two sparsity-based matching measures, three biometric modalities (i.e., face, palmprint, and ear) and their multimodal combinations based on both handcrafted and deep learning features. We finally approach a comprehensive study of SRC-based verification, including its methodology, characteristics, merits, challenges and the directions to resolve. Extensive experimental results demonstrate the superiority of SRC-based verification, especially when using multimodal fusion and advanced deep learning features. The concerns about its efficiency in large-scale user applications can be readily solved using a simple dictionary shrinkage strategy based on cluster analysis and random selection of non-target subjects. [ABSTRACT FROM AUTHOR]

Dictionary learning has drawn increasing attention for its impressive performance in obtaining the high-fidelity representations of data and extracting semantics. However, when there exists distribution divergence between source and target data, the representations of target data based on the learned dictionary from source data fail to reveal the intrinsic nature of target tasks, which consequently degrades the target performance severely. To tackle this problem, we propose a Shared Dictionary Learning (SDL) method in this paper. SDL learns a shared dictionary by implementing both geometric and statistical adaptations. SDL utilizes the Nyström method to exploit the geometric relationships between domains. Specifically, SDL uses the Nyström method to construct a variable source graph based on the target graph eigensystem and employs the Nyström approximation error to measure the distance between the variable source graph and the ground truth source graph to formalize the geometric divergence. Thus, a domain-invariant graph can be constructed by minimizing the approximation error and can be used to bridge two domains geometrically. Simultaneously, SDL captures the latent statistical commonality underlying two domains via minimizing the Maximum Mean Discrepancy (MMD) distance between domains. Finally, SDL achieves a shared dictionary and a set of corresponding new representations to handle cross-distribution data classification. Extensive experimental results on several popular datasets demonstrate the superiority of SDL. [ABSTRACT FROM AUTHOR]

Halftone image is widely used in printing and scanning equipment. It is significant for the halftone image to be preserved and processed. For the different resolution of the display devices, the processing and displaying of halftone image are faced with great challenges, such as Moore pattern and image blurring. The inverse halftone technique is required to remove the halftone screen. In this paper, we propose an inverse halftone algorithm based on sparse representation with the dictionary learned by two steps: deconvolution and sparse optimization in the transform domain to remove the noise. The main contributions of this paper include three aspects: first, we analysis the denoising effects for different training sets and the dictionary; Then we propose the denoising algorithm through adaptively learning the dictionary, which iteratively remove the noise of the training set and improve the dictionary; Then the inverse halftone algorithm is proposed. Finally, we verify that the noise level in the error diffusion linear model is fixed, and the noise level is only related to the diffusion operator. Experimental results show that the proposed algorithm has better PSNR and visual performance than state-of-the-art methods. The codes and constructed models are available at https://github.com/juneryoung2022/IH-WNNM. [ABSTRACT FROM AUTHOR]

Vascular cognitive impairment (VCI) is a critical issue in moyamoya disease (MMD). However, the glucose metabolic pattern in these patients is still unknown. This study aimed to identify the metabolic signature of cognitive impairment in patients with MMD using 18F-2-fluoro-2-deoxy-D-glucose positron emission tomography (18F-FDG PET) and establish a classifier to identify VCI in patients with MMD. One hundred fifty-two patients with MMD who underwent brain 18F-FDG PET scans before surgery were enrolled and classified into nonvascular cognitive impairment (non-VCI, n = 52) and vascular cognitive impairment (VCI, n = 100) groups according to neuropsychological test results. Additionally, thirty-three health controls (HCs) were also enrolled. Compared to HCs, patients in the VCI group exhibited extensive hypometabolism in the bilateral frontal and cingulate regions and hypermetabolism in the bilateral cerebellum, while patients in the non-VCI group showed hypermetabolism only in the cerebellum and slight hypometabolism in the frontal and temporal regions. In addition, we found that the patients in the VCI group showed hypometabolism mainly in the left basal ganglia compared to those in the non-VCI group. The sparse representation-based classifier algorithm taking the SUVr of 116 Anatomical Automatic Labeling (AAL) areas as features distinguished patients in the VCI and non-VCI groups with an accuracy of 82.4%. This study demonstrated a characteristic metabolic pattern that can distinguish patients with MMD without VCI from those with VCI, namely, hypometabolic lesions in the left hemisphere played a more important role in cognitive decline in patients with MMD. [ABSTRACT FROM AUTHOR]

Multi-focus image fusion plays an important role in the application of computer vision. In the process of image fusion, there may be blurring and information loss, so it is our goal to obtain high-definition and information-rich fusion images. In this paper, a novel multi-focus image fusion method via local energy and sparse representation in the shearlet domain is proposed. The source images are decomposed into low- and high-frequency sub-bands according to the shearlet transform. The low-frequency sub-bands are fused by sparse representation, and the high-frequency sub-bands are fused by local energy. The inverse shearlet transform is used to reconstruct the fused image. The Lytro dataset with 20 pairs of images is used to verify the proposed method, and 8 state-of-the-art fusion methods and 8 metrics are used for comparison. According to the experimental results, our method can generate good performance for multi-focus image fusion. [ABSTRACT FROM AUTHOR]

• A sparse representation method of heterogeneous information networks is proposed. • The heterogeneous information atoms are found by the sparse representation method. • The heterogeneous information atoms describe the main patterns of the heterogeneous information network. • The heterogeneous information atoms are helpful to understand the complex patterns of the heterogeneous information network. A complex network is a fundamental tool to describe real-world complex systems, with most real-world systems containing multiple object types and relationships that can be described as heterogeneous information networks. However, with the increasing network complexity, understanding the complex patterns and finding the meta paths or meta-structures of the heterogeneous information networks has become challenging. This paper proposes a sparse representation for heterogeneous information networks and extracts the heterogeneous information atoms that describe the basic connection pattern of the original heterogeneous information network. The heterogeneous information atoms help extract the main meta-paths or meta-structures and understand the complex patterns of the original heterogeneous information network. Furthermore, the heterogeneous information networks can be decomposed, dimension-reduced, and reconstructed through the heterogeneous information atoms. Extensive experimental results demonstrate that heterogeneous information atoms and sparse coding represent the basic connection pattern of real-world heterogeneous information networks. Indeed, the developed method can reconstruct a network with a recovery exceeding 90%. [ABSTRACT FROM AUTHOR]

LiDAR point clouds are characterized by high geometric and radiometric resolution and are therefore of great use for large-scale forest analysis. Although the analysis of 3D geometries and shapes has improved at different resolutions, processing large-scale 3D LiDAR point clouds is difficult due to their enormous volume. From the perspective of using LiDAR point clouds for forests, the challenge lies in learning local and global features, as the number of points in a typical 3D LiDAR point cloud is in the range of millions. In this research, we present a novel end-to-end deep learning framework called ADCoSNet, capable of adaptively reconstructing 3D LiDAR point clouds from a few sparse measurements. ADCoSNet uses empirical mode decomposition (EMD), a data-driven signal processing approach with Deep Learning, to decompose input signals into intrinsic mode functions (IMFs). These IMFs capture hierarchical implicit features in the form of decreasing spatial frequency. This research proposes using the last IMF (least varying component), also known as the Residual function, as a statistical prior for capturing local features, followed by fusing with the hierarchical convolutional features from the deep compressive sensing (CS) network. The central idea is that the Residue approximately represents the overall forest structure considering it is relatively homogenous due to the presence of vegetation. ADCoSNet utilizes this last IMF for generating sparse representation based on a set of CS measurement ratios. The research presents extensive experiments for reconstructing 3D LiDAR point clouds with high fidelity for various CS measurement ratios. Our approach achieves a maximum peak signal-to-noise ratio (PSNR) of 48.96 dB (approx. 8 dB better than reconstruction without data-dependent transforms) with reconstruction root mean square error (RMSE) of 7.21. It is envisaged that the proposed framework finds high potential as an end-to-end learning framework for generating adaptive and sparse representations to capture geometrical features for the 3D reconstruction of forests. [ABSTRACT FROM AUTHOR]

Carbon fiber composites are commonly used in aerospace and other fields due to their excellent properties, and fatigue damage will occur in the process of service. Damage imaging can be performed using damage probability imaging methods to obtain the fatigue damage condition of carbon fiber composites. At present, the damage factor commonly used in the damage probability imaging algorithm has low contrast and poor anti-noise performance, which leads to artifacts in the imaging and misjudgment of the damaged area. Therefore, this paper proposes a fatigue damage probability imaging method for carbon fiber composite materials based on the sparse representation of Lamb wave signals. Based on constructing the Lamb wave dictionary, a fast block sparse Bayesian learning algorithm is used to represent the Lamb wave signals sparsely, and the definition of Lamb wave sparse representing the damage factor calculates the damage probability of the monitoring area and then images the fatigue damage of the carbon fiber composite materials. The imaging research was carried out using the fatigue monitoring experiment data of NASA's carbon fiber composite materials. The results show that the proposed damage factor can clearly distinguish the damaged area from the undamaged area and has strong noise immunity. Compared with the energy damage factor and the cross-correlation damage factor, the error percentages are reduced by at least 58.63%, 28.11%, and 8.43% for signal-to-noise ratios of 6 dB, 3 dB, and 0.1 dB, respectively, after adding noise to the signal. The results can more accurately reflect the real location and area of fatigue damage in carbon fiber composites. [ABSTRACT FROM AUTHOR]

For conventional image reconstruction based on dictionary learning in low-dose computed tomography (CT) imaging, all image blocks are represented by the same dictionary, thus limiting the reconstructed image quality. To improve the outcome, a low-dose CT iterative reconstruction algorithm based on image block classification and dictionary learning is proposed. First, each image block is classified as a smooth block or a detail block according to the local image variance. The detail block is subsequently divided into irregular blocks and edge blocks with different angles according to the pointing angle obtained from its gradient field information. Then, the conventional k-singular value decomposition algorithm is applied to train dictionaries for different types of image blocks, and orthogonal matching pursuit determines the sparse coefficients during training. Further, a variety of dictionary learning algorithms are used in penalty-weighted least-squares reconstruction as regular terms. Finally, the relaxed linearized augmented Lagrangian method with ordered subsets is used to solve the objective function. Experimental results show that the proposed algorithm suppresses noise and sharpens edges in reconstructed CT images. The code of the proposed algorithm is available at https://github.com/LIUyi827728/PWLS_BCDL. [ABSTRACT FROM AUTHOR]

Periodic noise is a well-known problem in seismic exploration, caused by power lines, pump jacks, engine operation, or other interferences. It contaminates seismic data and affects subsequent processing and interpretation. The conventional methods to attenuate periodic noise are notch filtering and some model-based methods. However, these methods either simultaneously attenuate noise and seismic events around the same frequencies, or need expensive computation time. In this work, a new method is proposed to attenuate periodic noise based on sparse representation. We use a noise dictionary to sparsely represent periodic noise. The noise dictionary is constructed based on ambient noise. An advantage of our method is that it can automatically suppress monochromatic periodic noise, multitoned periodic noise and even periodic noise with complex waveforms without pre-known noise frequencies. In addition, the method does not result in any notches in the spectrum. Synthetic and field examples demonstrate that our method can effectively subtract periodic noise from raw seismic data without damaging the useful seismic signal. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)