Showing papers on "Sparse approximation published in 2022"

Compound Fault Diagnosis Using Optimized MCKD and Sparse Representation for Rolling Bearings

Abstract: The effective separation of fault characteristic components is the core of compound fault diagnosis of rolling bearings. The intelligent optimization algorithm has better global optimization performance and fast convergence speed. Aiming at the problem of poor diagnosis effect caused by mutual interference between multiple fault responses, a novel compound fault diagnosis method based on optimized maximum correlation kurtosis deconvolution (MCKD) and sparse representation, namely MDSRCFD, is proposed in this article. For the MCKD, because it is very difficult to set reasonable parameter combination values, artificial fish school (AFS) with global search capability and strong robustness is fully utilized to optimize the key parameters of MCKD to achieve the best deconvolution and fault feature separation. Aiming at the problem that orthogonal matching pursuit (OMP) is difficult to be solved in sparse representation, an artificial bee colony (ABC) with global optimization ability and faster convergence speed is employed to solve OMP to obtain the approximate best atom and realize the reconstruction of signal transient components. The envelope demodulation analysis method is applied to realize feature extraction and fault diagnosis. The simulation and practical application results show that the proposed MDSRCFD can effectively separate and extract the compound fault characteristics of rolling bearings, which can realize the accurate compound fault diagnosis.

Improved Image Fusion Method Based on Sparse Decomposition

Abstract: In the principle of lens imaging, when we project a three-dimensional object onto a photosensitive element through a convex lens, the point intersecting the focal plane can show a clear image of the photosensitive element, and the object point far away from the focal plane presents a fuzzy image point. The imaging position is considered to be clear within the limited size of the front and back of the focal plane. Otherwise, the image is considered to be fuzzy. In microscopic scenes, an electron microscope is usually used as the shooting equipment, which can basically eliminate the factors of defocus between the lens and the object. Most of the blur is caused by the shallow depth of field of the microscope, which makes the image defocused. Based on this, this paper analyzes the causes of defocusing in a video microscope and finds out that the shallow depth of field is the main reason, so we choose the corresponding deblurring method: the multi-focus image fusion method. We proposed a new multi-focus image fusion method based on sparse representation (DWT-SR). The operation burden is reduced by decomposing multiple frequency bands, and multi-channel operation is carried out by GPU parallel operation. The running time of the algorithm is further reduced. The results indicate that the DWT-SR algorithm introduced in this paper is higher in contrast and has much more details. It also solves the problem that dictionary training sparse approximation takes a long time.

Low-Rank and Sparse Representation for Hyperspectral Image Processing: A review

Abstract: Combining rich spectral and spatial information, a hyperspectral image (HSI) can provide a more comprehensive characterization of the Earth’s surface. To better exploit HSIs, a large number of algorithms have been developed during the past few decades. Due to their very high correlation between spectral channels and spatial pixels, HSIs have intrinsically sparse and low-rank structures. The sparse representation (SR) and low-rank representation (LRR)-based methods have proven to be powerful tools for HSI processing and are widely used in different HS fields. In this article, we present a survey of low-rank and sparse-based HSI processing methods in the fields of denoising, superresolution, dimension reduction, unmixing, classification, and anomaly detection. The purpose is to provide guidelines and inspiration to practitioners for promoting the development of HSI processing. For a listing of the key terms discussed in this article, see “Nomenclature.”

Semisupervised Feature Extraction of Hyperspectral Image Using Nonlinear Geodesic Sparse Hypergraphs

Abstract: Recently, the sparse representation (SR)-based graph embedding method has been extensively used in feature extraction (FE) tasks, but it is hard to reveal the complex manifold structure and multivariate relationship of samples in the hyperspectral image (HSI). Meanwhile, the small size sample problem in HSI data also limits the performance of the traditional SR approach. To tackle this problem, this article develops a new semisupervised FE algorithm called a geodesic-based sparse manifold hypergraph (GSMH). The presented method first utilizes the geodesic distance to measure the nonlinear similarity between samples lying on manifold space and further constructs the manifold neighborhood of each sample. Then, a geodesic-based neighborhood SR (GNSR) model is designed to explore the multivariate sparse correlations of different manifold neighborhoods. Considering the multivariate sparse manifold correlations among samples, a pair of semisupervised hypergraphs (HGs) is constructed to effectively incorporate the labeled and unlabeled training information in the embedding process and obtain the nonlinear discriminative feature representation for HSI. Experimental results on three HSI datasets indicate that the proposed method not only achieves satisfying FE performance with limited labeled training samples but also shows superiority compared with other state-of-the-art methods.

Focal Sparse Convolutional Networks for 3D Object Detection

Abstract: Non-uniformed 3D sparse data, e.g., point clouds or voxels in different spatial positions, make contribution to the task of 3D object detection in different ways. Existing basic components in sparse convolutional networks (Sparse CNNs) process all sparse data, regardless of regular or submanifold sparse convolution. In this paper, we introduce two new modules to enhance the capability of Sparse CNNs, both are based on making feature sparsity learnable with position-wise importance prediction. They are focal sparse convolution (Focals Conv) and its multi-modal variant of focal sparse convolution with fusion, or Focals Conv-F for short. The new modules can readily substitute their plain counterparts in existing Sparse CNNs and be jointly trained in an end-to-end fashion. For the first time, we show that spatially learnable sparsity in sparse convolution is essential for sophisticated 3D object detection. Extensive experiments on the KITTI, nuScenes and Waymo benchmarks validate the effectiveness of our approach. Without bells and whistles, our results outperform all existing single-model entries on the nuScenes test benchmark. Code and models are at github.com/dvlab-research/FocalsConv.

Deep sparse representation network for feature learning of vibration signals and its application in gearbox fault diagnosis

Abstract: Vibration signals play a key role in machinery fault diagnosis, which are often buried by strong noises due to complex working conditions. Typical deep neural networks (e.g., convolutional neural networks (CNNs)) can effectively learn features from vibration data and perform well in machinery fault diagnosis. Nonetheless, the vibration signals collected from real industry are often noised and nonstationary. It is still difficult for CNNs to implement feature extraction and noise reduction from large number of vibration signals. In this paper, a novel deep learning model, deep sparse representation network (DSRNet) is proposed to suppress noise and learn effective features from noised signals directly. Firstly, a sparse representation layer is developed to extract impulsive components and suppress noise hidden in vibration signals in an end-to-end manner. Secondly, an adaptive densely stacked convolutional structure is proposed to extract effective features from the filtered signals by the sparse representation layer. Finally, the effectiveness of DSRNet for feature learning on vibration signals is verified on two gearbox cases. The experimental results show that DSRNet has good feature learning and signal denoising performance, which outperforms those famous CNNs (e.g., ResNet, DenseNet).

A Study of Improved Methods on Image Inpainting

Abstract: Inpainting is the ancient art technique of modifying the image when it can’t be detected. This current study discusses the various approaches in image inpainting and compares the methods with their time of detection and accuracy. There are many different approaches to solve the inpainting problem. These approaches such as feature distribution, sparse representation, Markov random field, multiscale graph cuts, neural networks, and GAN-based methods are studied. The limitations that are imposed on the regions of the images to be inpainted are studied in the current work. The applications of such approaches are discussed in brief.

A Hyperspectral Anomaly Detection Method Based on Low-Rank and Sparse Decomposition With Density Peak Guided Collaborative Representation

Abstract: The low-rank and sparse decomposition model (LSDM) has been widely studied by researchers and has successfully solved the problem of hyperspectral image (HSI) anomaly detection (AD). The traditional LSDM usually ignores the information of the low-rank matrix, which only detects the anomalous targets by using the sparse component. To utilize both the sparse component and the low-rank component comprehensively, an anomaly detector for HSIs based on LSDM with density peak guided collaborative representation (LSDDPCRD) is proposed in this article. First, the LSDM technique with the mixture of Gaussian model is used to decompose the original HSI, which can also alleviate the background noise contamination problem. Then, the low-rank matrix is detected by the density peak guided collaborative representation detection algorithm, while the sparse matrix is calculated according to the Manhattan distance. In addition, an entropy-based adaptive fusing method is designed to combine the results obtained from the low-rank matrix and the sparse component. It could choose the fusing weights adaptively according to the characteristics of an HSI. The experimental results indicate that the LSDDPCRD performs better than eight classical and state-of-the-art AD algorithms (GRX, LRX, SRX-Segmented, CRD, RPCA-RX, LSMAD, LRASR, and LSDM-MoG) on four real HSIs.

Adaptive Sparse Representation-Based Minimum Entropy Deconvolution for Bearing Fault Detection

Abstract: Deconvolution methods have been extensively applied for enhancing the impulsive feature of those bearing signals, which promotes the accuracy of the bearing fault diagnosis. However, these methods are sensitive to the inverse filter length, which leads to poor effect. To overcome the existing problems, a new adaptive sparse representation-based minimum entropy deconvolution (AdaSRMED) is proposed on basis of the impulsive feature extraction of sparse representation, which promotes the robustness for inverse filter length and its effectiveness of impulse enhancement. In AdaSRMED, a new adaptive sparse representation (SR) is proposed based on the features of fault impulsive signals for solving these existing problems of previous SR methods. Moreover, the new adaptive SR is integrated with the minimum entropy deconvolution (MED) for improving the performance of MED, which avoids the shortcomings of MED and MED-related methods. A series of simulation signal and real fault signal experiments are performed to illustrate the superiority of AdaSRMED in fault detection. The comparison analysis with the conventional MED and improved MEDs shows that AdaSRMED can effectively enhance the impulsive features and show good bearing fault detection performance.

Denoising algorithm of OCT images via sparse representation based on noise estimation and global dictionary.

Abstract: Optical coherence tomography (OCT) is a high-resolution and non-invasive optical imaging technology, which is widely used in many fields. Nevertheless, OCT images are disturbed by speckle noise due to the low-coherent interference properties of light, resulting in significant degradation of OCT image quality. Therefore, a denoising algorithm of OCT images via sparse representation based on noise estimation and global dictionary is proposed in this paper. To remove noise and improve image quality, the algorithm first constructs a global dictionary from high-quality OCT images as training samples and then estimates the noise intensity for each input image. Finally, the OCT images are sparsely decomposed and reconstructed according to the global dictionary and noise intensity. Experimental results indicate that the proposed algorithm efficiently removes speckle noise from OCT images and yield high-quality images. The denoising effect and execution efficiency are evaluated based on quantitative metrics and running time, respectively. Compared with the mainstream adaptive dictionary denoising algorithm in sparse representation and other denoising algorithms, the proposed algorithm exhibits satisfying results in terms of speckle-noise reduction as well as edge preservation, at a reduced computational cost. Moreover, the final denoising effect is significantly better for sets of images with significant variations in noise intensity.

Sparse DNN Model for Frequency Expanding of Higher Order Ambisonics Encoding Process

Abstract: The performance of higherorder Ambisonics (HOA) signals obtained using spherical harmonics decomposition method is disturbed by two primary sources of errors, the noise pollution in low-frequency band and the spatial aliasing in high-frequency band. Inspired by the HOA signals upscale method, which is performed using the sparse character of the sound field, this paper propose a sound field decomposition model based on a sparse deep neural network that offers HOA signals with wider frequency bandwidth. We use the frequency domain multi-scale convolutional network to realize the spherical harmonics decomposition, as well as learning the spatial aliasing pattern, based on which the aliasing-free HOA signals can be derived. Besides, we apply a sparse encoding network to cpature the sparse feature of the sound field which will improve the model performance when the sparse condition is satisfied. The experiments results prove that the proposed model can obtain HOA signals with wider frequency range of operation under multiple sources (up to 10 sources) and low reverberant environments ($T_{60}\le$ 400 ms). When the sparsity feature cannot be satisfied ($T_{60} =$ 800 ms), the proposed network model still maintain the same performance as the traditional methods.

Low-Dose CT Image Post-Processing Based on Learn-Type Sparse Transform

Abstract: As a detection method, X-ray Computed Tomography (CT) technology has the advantages of clear imaging, short detection time, and low detection cost. This makes it more widely used in clinical disease screening, detection, and disease tracking. This study exploits the ability of sparse representation to learn sparse transformations of information and combines it with image decomposition theory. The structural information of low-dose CT images is separated from noise and artifact information, and the sparse expression of sparse transformation is used to improve the imaging effect. In this paper, two different learned sparse transformations are used. The first covers more organizational information about the scanned object. The other can cover more noise artifacts. Both methods can improve the ability to learn sparse transformations to express various image information. Experimental results show that the algorithm is effective.