Search

Inspection robots for early detection of potential risks in severe environments require a high accuracy like human experts. A fine mechanism is crucial for extracting target components from noisy signals. We have proposed a detection system for submillimeter-width cracks in concrete surfaces of social infrastructures, such as bridges, by using morphological component analysis (MCA), for aerial image-inspection robots. Traditional schemes like PCA have relied on linear decomposition for the separation of target signal and noise components. Recent advancement in signal decomposition focuses on the enhancement of linearity in the separation by introducing a set of nonlinear basis functions to represent the raw signal even when multiple factors are mixed in a nonlinear manner. In this sense, MCA is a core technique to be able to isolate target components to represent submillimeter-width cracks from others. We proposed a proper pre- and post-processing operations to attach MCA, which demonstrated a high accuracy yet coarse and fine image components have to be integrated redundantly. In the present study, we successfully found a simpler mechanism to set the single basis function to extract the target by introducing a new thresholding mechanism. It suggests a high potential of MCA for inspection robots for various purposes. [ABSTRACT FROM AUTHOR]

Image restoration (IR) attempts to recreate the original (ideal) scene from a degraded observation. The goal of image restoration is to avert the process of image deterioration that happens during image acquisition and processing. Blurring and noise are two common types of picture capture degradation. When the blurring function is unknown, the image restoration issue is referred to as blind image restoration. Existing methods of image restoration do not provide efficient results due to time complexity, computational complexity, large-scale scaling factor and limited input. Therefore, in order to overcome those problems, an Improved Graph Laplacian Regularization with Sparse Coding by integrating Internet of Things (IoT) is developed in this research. The process of removing de-noised portions of image to texture layer and cartoon layer is carried out by Morphological Component Analysis (MCA). An improved Graph Laplacian regularized method and Simultaneous Sparse Coding with Gaussian Scale Mixture (SSC-GSM) methods is performed on texture layer, cartoon layer and restored image. A Levin's dataset and a real-time dataset such as industrial manufacturing products are analyzed in this research. The proposed Graph Laplacian algorithm and sparse coding model are better efficient in identifying sharper texture information and getting a restored image. The proposed method proves that it has better performance in terms of Peak Signal-to-Noise Ratio (PSNR) of 35.82 and Structural Similarity Index Measure (SSIM) of 0.94 than the existing methods. [ABSTRACT FROM AUTHOR]

Infrared images have been widely employed in many fields. However, the relative motion between a target and an imaging device and the interference of salt-and-pepper noise lead to the degradation of infrared images. Traditional infrared image recovery methods require an image to be restored as a whole, which leads to mutual interference between the cartoon and texture parts of an image in the restoration process. In this study, a morphological component analysis decomposition method was developed. This method decomposes an image into cartoon and texture parts. Meanwhile, the $ {l_p} $ l p pseudo-norm is introduced to characterize the sparsity of the stationary Framelet transform coefficients and noise, and mask matrix is applied to protect parts that were not contaminated. The proposed method was then solved using an alternating-direction multiplier method. The proposed method was compared with more advanced image recovery methods. The results show that the proposed method has a significant performance improvement. [ABSTRACT FROM AUTHOR]

The sparse representation methodology has been identified to be a promising tool for gearbox fault diagnosis. The core is how to precisely reconstruct the fault signal from noisy monitoring signals. The non-convex penalty has the ability to induce sparsity more efficiently than convex penalty. However, the introduction of non-convex penalty usually influences the convexity of the model, resulting in the unstable or sub-optimal solution. In this paper, we propose the non-convex smoothing penalty framework (NSPF) and combine it with morphological component analysis (MCA) for gearbox fault diagnosis. The proposed NSPF is a unify penalty construction framework, which contains many classical penalty while a new set of non-convex smoothing penalty functions can be generated. These non-convex penalty can guarantee the convexity of the objective function while enhancing the sparsity, thus the global optimal solution can be acquired. The simulation and engineering experiments validate that the NSPF enjoys more reconstruction precision compared to the existing penalties. • A new unify framework for non-convex penalty construction is proposed for sparse representation. • The proposed penalty framework is combined with morphological component analysis for gearbox fault diagnosis. • The convexity of cost function can be preserved by setting the tuning matrix and the corresponding algorithm is presented. • The simulation and two engineering experiments proved that the proposed framework shows more reconstruction accuracy. [ABSTRACT FROM AUTHOR]

Deblending technology aims at separating simultaneous source seismic data between adjacent shots by allowing multiple sources to be shot simultaneously. Conventional deblending methods based on sparse inversion assume that the primary source is coherent, and the secondary source is randomized. The L2‐norm minimization constraint can effectively minimize the Gaussian random noise while deblending in the transform domain. Nonetheless, the L2‐norm misfit function is highly sensitive to outliers, negatively influencing the deblending performance. An effective optimization strategy is developed with deblending in pre‐stack seismic data to eliminate outliers and enhance deblending accuracy. For this reason, we introduce the deblending algorithm in the morphological component analysis framework, modify the L2‐norm misfit function to outlier‐robust L1‐norm and provide the corresponding derivation in detail via the alternating direction method of multipliers. Applications to synthetic and field data sets prove the improved robustness and efficiency of our deblending method. [ABSTRACT FROM AUTHOR]

The negative-going movement-related cortical potentials are associated with the preparation and execution of the voluntary movements. Thus far, the readiness potential (RP) for simple movements involving either the upper or lower body segments has been studied. We investigated the ability to decode the sit-to-stand movement's intention from the RP, which uses the upper and lower body segments. Therefore, we performed scalp electroencephalography in healthy volunteers. A gyro sensor was placed on the back to detect the movement of the upper body segment, and an electromyogram electrode was placed on the surface of the hamstrings and quadriceps to detect movement of the lower body segment. Our study revealed that a negative RP was evoked around 2 to 3 s before the onset of the upper body movement in the sit-to-stand movement in response to the start cue. The RP had a negative peak and a steeper negative slope from − 0.8 to − 0.001 s just before the onset of the upper body movement. Negative-going RPs reflect the intention of preparation/execution of the sit-to-stand movement. Therefore, we used the morphological component analysis method to extract the morphology of RPs from a single trial. This morphology of RPs is a promising aspect for limb neurotrophies or neurorehabilitation devices. [ABSTRACT FROM AUTHOR]

The reconstruction of data is a critical preliminary work in the seismic data processing. Compressed sensing (CS) has been well applied in the field of reconstruction. The key point of CS is random sampling, which converts the mutual interference alias caused by regular undersampling into lower-amplitude outside noise. But traditional sampling methods lack constraints on sampling points, emerging too much alias. Segmented random sampling (SRS) effectively controls the distance between sampling points. On the other hand, a single mathematical transformation will lead to incomplete sparse expression and bad restoration effects. Morphological component analysis (MCA) decomposes a signal into several components with outstanding morphological features to approximate the complex internal structure of data. In this paper, we found a new dictionary combination (shearlet + DCT) under the MCA framework and used the block coordinate relaxation algorithm to get the optimal solution to obtain reconstruction results. Tests of 2D data and 3D data have proved that the proposed method can get a better effect when reconstructing the SRS data. [ABSTRACT FROM AUTHOR]

In recent years, there has been a significant increase in the number of people suffering from eye illnesses, which should be treated as soon as possible in order to avoid blindness. Retinal Fundus images are employed for this purpose, as well as for analysing eye abnormalities and diagnosing eye illnesses. Exudates can be recognised as bright lesions in fundus pictures, which can be the first indicator of diabetic retinopathy. With that in mind, the purpose of this work is to create an Integrated Model for Exudate and Diabetic Retinopathy Diagnosis (IMEDRD) with multi-level classifications. The model uses Support Vector Machine (SVM)-based classification to separate normal and abnormal fundus images at the first level. The input pictures for SVM are pre-processed with Green Channel Extraction and the retrieved features are based on Gray Level Co-occurrence Matrix (GLCM). Furthermore, the presence of Exudate and Diabetic Retinopathy (DR) in fundus images is detected using the Adaptive Neuro Fuzzy Inference System (ANFIS) classifier at the second level of classification. Exudate detection, blood vessel extraction, and Optic Disc (OD) detection are all processed to achieve suitable results. Furthermore, the second level processing comprises Morphological Component Analysis (MCA) based image enhancement and object segmentation processes, as well as feature extraction for training the ANFIS classifier, to reliably diagnose DR. Furthermore, the findings reveal that the proposed model surpasses existing models in terms of accuracy, time efficiency, and precision rate with the lowest possible error rate. [ABSTRACT FROM AUTHOR]

Data reconstruction and data denoising are two critical preliminary steps in seismic data processing. Compressed Sensing states that a signal can be recovered by a series of solving algorithms if it is sparse in a transform domain, and has been well applied in the field of reconstruction, when, sparse representation of seismic data is the key point. Considering the complexity and diversity of seismic data, a single mathematical transformation will lead to incomplete sparse expression and bad restoration effects. Morphological Component Analysis (MCA) decomposes a signal into several components with outstanding morphological features to approximate the complex internal data structure. However, the representation ability of combined dictionaries is constrained by the number of dictionaries, and cannot be self-adaptively matched with the data features. Dictionary learning overcomes the limitation of fixed base function by training dictionaries that are fully suitable for processed data, but requires huge amount of time and considerable hardware cost. To solve the above problems, a new dictionary library (K-Singluar Value Decomposition learning dictionary and Discrete Cosine Transform dictionary) is hereby proposed based on the efficiency of fixed base dictionary and the high precision of learning dictionary. The self-adaptive sparse representation is achieved under the Morphological Component Analysis framework and is successfully applied to the reconstruction and denoising of seismic data. Real data tests have proved that the proposed method performs better than single mathematical transformation and other combined dictionaries.

This paper puts forward a denoising algorithm for low-dose computed tomography (LDCT) image based on optimal wavelet basis and morphological component analysis, which aims to solve the problem of severe noise and artifacts in LDCT imaging. First, the high-frequency (HF) component coefficients in the horizontal, vertical, and diagonal directions of LDCT after the stationary wavelet transform (SWT) are weighted to obtain the wavelet basis selection coefficients, and the wavelet basis with the smallest wavelet select coefficient is selected as the optimal wavelet basis. Second, the artifacts are processed using the MCA algorithm based on online dictionary learning (ODL) for the HF component. Third, the improved LDCT images are obtained using the inverse stationary wavelet transform (ISWT), which uses the low-frequency (LF) components and the denoised HF component. The extensive experiments on simulated and real data demonstrated the images denoised using the optimal wavelet basis algorithm showed the highest objective evaluation index, followed by the other wavelet-based algorithms. Additionally, our proposed method outperformed several classical denoising methods on both quantitative and qualitative assessments. It was therefore verified that the validity of wavelet selection and the feasibility of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Objective: Sparse representations have been utilized to identify functional connectivity (FC) of networks, while ICA employs the assumption of independence among the network sources to demonstrate FC. Here, we investigate a sparse decomposition method based on Morphological Component Analysis and K-SVD dictionary learning — MCA-KSVD — and contrast the effect of the sparsity constraint vs. the independency constraint on FC and denoising. Methods: Using a K-SVD algorithm, fMRI signals are decomposed into morphological components which have sparse spatial overlap. We present simulations when the independency assumption of ICA fails and MCA-KSVD recovers more accurate spatial-temporal structures. Denoising performance of both methods is investigated at various noise levels. A comprehensive experimental study was conducted on resting-state and task fMRI. Results: Validations show that ICA is advantageous when network components are well-separated and sparse. In such cases, the MCA-KSVD method has modest value over ICA in terms of network delineation but is significantly more effective in reducing spatial and temporal noise. Results demonstrate that the sparsity constraint yields sparser networks with higher spatial resolution while suppressing weak signals. Temporally, this localization effect yields higher contrast-to-noise ratios (CNRs) of time series. Conclusion: While marginally improving the spatial decomposition, MCA-KSVD denoises fMRI data much more effectively than ICA, preserving network structures and improving CNR, especially for weak networks. Significance: A sparsity-based decomposition approach may be useful for investigating functional connectivity in noisy cases. It may serve as an efficient decomposition method for reduced acquisition time and may prove useful for detecting weak network activations. [ABSTRACT FROM AUTHOR]

Remote sensing image fusion is a fundamental issue in the field of remote sensing. In this paper, we propose a remote sensing image fusion method based on optimal scale morphological convolutional neural networks (CNN) using the principle of entropy from information theory. We use an attentional CNN to fuse the optimal cartoon and texture components of the original images to obtain a high-resolution multispectral image. We obtain the cartoon and texture components using sparse decomposition-morphological component analysis (MCA) with an optimal threshold value determined by calculating the information entropy of the fused image. In the sparse decomposition process, the local discrete cosine transform dictionary and the curvelet transform dictionary compose the MCA dictionary. We sparsely decompose the original remote sensing images into a texture component and a cartoon component at an optimal scale using the information entropy to control the dictionary parameter. Experimental results show that the remote sensing image fusion method proposed in this paper can effectively retain the information of the original image, improve the spatial resolution and spectral fidelity, and provide a new idea for image fusion from the perspective of multi-morphological deep learning. [ABSTRACT FROM AUTHOR]

Sparsity-assisted signal decomposition (SASD) based on morphological component analysis (MCA) for bearing fault diagnosis has been studied in-depth. However, existing algorithms often use different combinations of representation dictionaries and priors, leading to difficult dictionary choice and high computational complexity. This article aims to develop a fast sparsity-assisted algorithm to decompose a vibration signal into discrete frequency and impulse components for bearing fault diagnosis. We introduce the morphological discrimination of discrete frequency and impulse components in time and frequency domains, respectively, for the first time. To use this morphological discrimination, we establish a fast SASD based on MCA with nonconvex enhancement. We further prove the necessary and sufficient condition to guarantee the convexity and use the majorization minimization algorithm to derive a fast solver. The proposed algorithm not only has low computational complexity, but also avoids choosing multiple dictionaries as well as underestimation of impulse features. Furthermore, an adaptive parameter selection algorithm to set parameters of our algorithm is designed for real applications. The effectiveness of fast SASD and its adaptive variant is verified by both simulation studies and bearing diagnosis cases. The source codes will be released at https://github.com/ZhaoZhibin/Fast_SASD. [ABSTRACT FROM AUTHOR]

Clutter suppression plays an important role in a synthetic aperture radar (SAR) system. The conventional SAR imaging methods are useful for distinguishing the echo signal and noise, but cannot separate the target signal from background clutter. Inspired by the signal separation ability of morphological component analysis (MCA), a novel SAR imaging method based on MCA is proposed to suppress the strong background clutter. In the new model, the SAR echo is considered as a linear superposition of target signal, clutter signal, and noise. According to different characteristics of morphological components, clutter dictionary and target dictionary are constructed to sparsely represent the clutter component and target component, respectively. Then, the MCA method based on the sparse representation and morphological diversity of signals is employed to decompose the SAR echo into the target signal, clutter signal, and noise. Finally, the separated target signal is processed to obtain the ultimate SAR image. Experimental results from simulated and real SAR data are provided to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

(1) Background: A typical cardiac cycle consists of a P-wave, a QRS complex, and a T-wave, and these waves are perfectly shown in electrocardiogram signals (ECG). When atrial fibrillation (AF) occurs, P-waves disappear, and F-waves emerge. F-waves contain information on the cause of atrial fibrillation. Therefore it is essential to extract F-waves from the ECG signal. However, F-waves overlap the QRS complex and T-waves in both the time and frequency domain, causing this matter to be a difficult one. (2) Methods: This paper presents an optimized resonance-based signal decomposition method for detecting F-waves in single-lead ECG signals with atrial fibrillation (AF). It represents the ECG signal utilizing morphological component analysis as a linear combination of a finite number of components selected from the high-resonance and low-resonance dictionaries, respectively. The linear combination of components in the low-resonance dictionary reconstructs the oscillatory part (F-wave) of the ECG signal. In contrast, the linear combination of components in the high-resonance dictionary reconstructs the transient components part (QRST wave). The tunable Q-factor wavelet transform generates the high and low resonance dictionaries, with a high Q-factor producing a high resonance dictionary and a low Q-factor producing a low resonance dictionary. The different Q-factor settings affect the dictionaries' characteristics, hence the F-wave extraction. A genetic algorithm was used to optimize the Q-factor selection to select the optimal Q-factor. (3) Results: The presented method helps reduce RMSE between the extracted and the simulated F-waves compared to average beat subtraction (ABS) and principal component analysis (PCA). According to the amplitude of the F-wave, RMSE is reduced by 0.24–0.32. Moreover, the dominant frequency of F-waves extracted by the presented method is clearer and more resistant to interference. The presented method outperforms the other two methods, ABS and PCA, in F-wave extraction from AF-ECG signals with the ventricular premature heartbeat. (4) Conclusion: The proposed method can potentially improve the accuracy of F-wave extraction for mobile ECG monitoring equipment, especially those with fewer leads. [ABSTRACT FROM AUTHOR]

Reliability is of great significance in ensuring the safe operation of modern industry, which mainly relies on data analysis and life tests. However, as the life of mechanical systems becomes increasingly longer with the rapid development of the manufacturing industry, the collection of historical failure data becomes progressively more time-consuming. In this paper, a few-shot reliability assessment approach is proposed in order to overcome the dependence on historical data. Firstly, the vibration response of a bearing was illustrated. Then, based on a vibration response analysis, a morphological component analysis (MCA) method based on sparse representation theory was used to decompose vibration signals and extract impulse signals. After the impulse components' reconstruction, their statistical indexes were utilized as the input observation vector of a Mixture of Gaussians Hidden Markov Model (MoG-HMM) for a reliability estimation. Finally, the experimental dataset of an aerospace bearing was analyzed via the proposed method. The comparison results illustrate the effectiveness of the proposed method of a few-shot reliability assessment. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing 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.)

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department 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.)

Traditional denoising methods based on fixed transforms are not suited for exploiting their complicated characteristics and attenuating noise due to their lack of adaptability. Recently, a novel method called morphological component analysis (MCA) was proposed to separate different geometrical components by amalgamating several irrelevance transforms. For studying the local singular and smooth linear components characteristics of seismic data, we propose a novel method that excels particularly in attenuating random and coherent noise while preserving effective signals. The proposed method, which combines MCA, dictionary learning (DL), and deep noise reduction consists of three steps: first, we separate the local singular and smooth linear components from the seismic signal using MCA. Second, we apply a DL method on these two components to suppress noise and obtain the denoised signal and noise. In the final step, we apply the DL method to the noise to obtain a little of the seismic signal. Afterwards, we integrate the two seismic signals to obtain the final denoised seismic signal. Numerical results indicate that the proposed method can effectively suppress the undesired noise, maximally preserve the information of geologic bodies and structures, and improve the signal-to-noise ratio (S/N) of the data. We also demonstrate the superior performance of this approach by comparing with other novel dictionaries such as discrete cosine transforms (DCTs), undecimated discrete wavelet transforms (UDWTs), or curvelet transforms. This algorithm provides new ideas for data processing to advance quality and S/N of seismic data. [ABSTRACT FROM AUTHOR]

Reliability is of great significance in ensuring the safe operation of modern industry, which mainly relies on data analysis and life tests. However, as the life of mechanical systems becomes increasingly longer with the rapid development of the manufacturing industry, the collection of historical failure data becomes progressively more time-consuming. In this paper, a few-shot reliability assessment approach is proposed in order to overcome the dependence on historical data. Firstly, the vibration response of a bearing was illustrated. Then, based on a vibration response analysis, a morphological component analysis (MCA) method based on sparse representation theory was used to decompose vibration signals and extract impulse signals. After the impulse components’ reconstruction, their statistical indexes were utilized as the input observation vector of a Mixture of Gaussians Hidden Markov Model (MoG-HMM) for a reliability estimation. Finally, the experimental dataset of an aerospace bearing was analyzed via the proposed method. The comparison results illustrate the effectiveness of the proposed method of a few-shot reliability assessment.

Sparse coding is widely used in image denoising, deblurring, clustering, and classification. However, most existing approaches to sparse coding failed to consider the fact that high dimensional data naturally reside on geometrical structure of the data space. It has been shown that geometric information of the data is important for both inversion and discrimination. In this paper, we proposed a generalized framework for image restoration and representation by combining sparse coding and graph based algorithms. In image denoising and deblurring problems, an image is first decomposed into cartoon layer (piecewise-smooth contents) and texture layer (textures and sharp edges) using morphological component analysis (MCA); then optimal graph Laplacian regularizer (OGLR) algorithm and simultaneous sparse coding with Gaussian scale mixture prior (SSC-GSM) algorithm are applied to cartoon layer and texture layer, respectively; final restored image is generated by aggregating the outcomes from two algorithms. The proposed hybrid image restoration algorithm outperforms state-of-the-art image denoising algorithms, such as BM3D on natural images, measured in PSNR, and performs comparatively in image deblurring. In image clustering and classification problems, we convert our generalized framework into a novel dual graph regularized sparse coding method to transform the nonlinear data space and feature space into linear space, two efficient optimization algorithms are provided for the numerical implementation. The experimental results show that our generalized graph Laplacian and sparse coding framework performs competitively with popular denoising, deblurring, clustering, and classification methods. [ABSTRACT FROM AUTHOR]

Loran-C is the most essential backup and supplementary system for the global navigation satellite system (GNSS). Continuous wave interference (CWI) is one of the main interferences in the Loran-C system, which will cause errors in the measurement of the time of arrival, thereby affecting positioning performance. The traditional adaptive notch filter method needs to know the frequency of CWI when removing it, and the number is limited. This paper presents a method based on sparseness to suppress the CWI in the Loran-C signal. According to the different morphological characteristics of the Loran-C signal and the CWI, we construct dictionaries suitable for the two components, respectively. We use the tunable Q-factor wavelet transform and the discrete cosine transform to make the two components obtain a good sparse representation in their respective dictionaries. Then, the two components are separated using the morphological component analysis theory. We illustrate this method using both synthetic data and actual data. A huge advantage of the proposed method is that there is no need to know the frequencies of the CWI for it can better cope with frequency changes of the CWI in the actual environments. Compared with the adaptive notch filter method, the results of the proposed method show that our approach is more effective and convenient.

Periodical impulses in vibration signals are key features in rolling element bearing fault diagnosis. Based on an overcomplete dictionary composed of different morphological atoms, morphological component analysis can be used to extract the signal components of different types of morphologies. A new morphological component analysis method based on a novel over-completed dictionary was proposed herein. According to morphological differences between components in rolling element bearing fault vibration signal, the method after improved dictionary could more targeted to extract impulse components containing fault feature. Then through envelope spectrum analysis, the fault characteristic frequency was extracted accurately, and rolling element bearing local faults were diagnosed. Compared with the Fast Kurtogram method for bearing fault diagnosis, the new method could avoid non-accuracy and non-optimality problems caused by artificial choice of resonance band, and improve the effectiveness of fault diagnosis. By analyzing both the simulation signal and the experimental dataset of rolling element bearing faults, the proposed method is validated.

We propose an efficient algorithm for the generalized sparse coding (SC) inference problem. The proposed framework applies to both the single dictionary setting, where each data point is represented as a sparse combination of the columns of one dictionary matrix, as well as the multiple dictionary setting as given in morphological component analysis (MCA), where the goal is to separate a signal into additive parts such that each part has distinct sparse representation within an appropriately chosen corresponding dictionary. Both the SC task and its generalization via MCA have been cast as ℓ 1 -regularized optimization problems of minimizing quadratic reconstruction error. In an effort to accelerate traditional acquisition of sparse codes, we propose a deep learning architecture that constitutes a trainable time-unfolded version of the split augmented lagrangian shrinkage algorithm (SALSA), a special case of the alternating direction method of multipliers (ADMM). We empirically validate both variants of the algorithm, that we refer to as learned-SALSA (LSALSA), on image vision tasks and demonstrate that at inference our networks achieve vast improvements in terms of the running time and the quality of estimated sparse codes on both classic SC and MCA problems over more common baselines. We also demonstrate the visual advantage of our technique on the task of source separation. Finally, we present a theoretical framework for analyzing LSALSA network: we show that the proposed approach exactly implements a truncated ADMM applied to a new, learned cost function with curvature modified by one of the learned parameterized matrices. We extend a very recent stochastic alternating optimization analysis framework to show that a gradient descent step along this learned loss landscape is equivalent to a modified gradient descent step along the original loss landscape. In this framework, the acceleration achieved by LSALSA could potentially be explained by the network's ability to learn a correction to the gradient direction of steeper descent. [ABSTRACT FROM AUTHOR]

مقدمه: شبکیه، داخلی‌ترین بافت چشم است و به کمک عصب بینایی اطلاعات تصویری را به مغز ارسال می‌نماید. این بخش از چشم، ساختار لایه‌ای دارد و طراحی روشی که بتواند بدون تأثیر گرفتن از نوع اختلال تصویر و میزان آن و همچنین پایین بودن کنتراست تصویر، مرزهای لایه‌ها را به ‌درستی مشخص نماید، از اهمیت فراوانی برخوردار می‌باشد. در این مطالعه، روش تلفیقی از دو روش تجزیه و تحلیل ریخت‌شناسی (MCA یا Morphological component analysis) و برنامه‌نویسی پویا (DP یا Dynamic programming) برای بخش‌بندی اتوماتیک شش لایه‌ی زیرین شبکیه به ‌کار گرفته شد. روش‌ها: پایگاه داده شامل 55 نمونه‌ی اخذ شده از افراد طبیعی با استفاده از دستگاه TOPCON-OCT-1000 بود. این مطالعه، در دو مرحله صورت گرفت. برای تجزیه‌ و تحلیل ریخت‌شناسی، دیکشنری هر تصویر با استفاده از خوشه‌بندی برداری به کمک مقادیر ویژه (K-SVD) محاسبه گردید و سپس روش MCA، روی دیکشنری‌های حاصل ‌شده اعمال گردید و بخش‌های کارتون و بافت تصویر با انتخاب پایه‌های مناسب تفکیک شد. بخش‌بندی به روش DP در تصویر کارتون اجرا گردید و سطوح Retinal pigment epithelium (RPE)، Verhoeff's memberane (VM)، Outer segment layer (OSL)، Inner collagenous layer (ICL)، Inner synaptic layer (ISL) و Outer limiting membrane (OLM) مشخص شدند. یافته‌ها: با مقایسه‌ی نتایج به ‌دست‌آمده با استانداردهای موجود، مشاهده شد که کمترین خطا، مربوط به سطح OSL با مقدار خطای 167/0 ± 030/0 بود. میزان خطای سطوح RPE، VM، ICL، ISL و OLM به ترتیب 33/0 ± 66/0-، 31/0 ± 59/0-، 49/0 ± 00/1-، 61/0 ± 72/1- و 51/0 ± 05/1- بود. نتیجه‌گیری: تجزیه ‌و تحلیل ریخت‌شناسی به کمک روش DP، می‌تواند به‌ صورت یک روش اتوماتیک در بخش‌بندی شش لایه‌ی زیرین شبکیه عمل کند و بدون نیاز به انجام پیش ‌پردازش، از صحت قابل قبولی در نتایج بخش‌بندی برخوردار است.

Featured Application: The proposed method is applicable for surface-wave extraction on X component in multicomponent seismic exploration. This method has application potential for the separation of PS-waves and surface waves whose frequencies and velocities are close. It is essential to extract high-fidelity surface waves in surface-wave surveys. Because reflections usually interfere with surface waves on X components in multicomponent seismic exploration, it is difficult to extract dispersion curves of surface waves. To make matters worse, the frequencies and velocities of higher-mode surface waves are close to those of PS-waves. A method for surface-wave extraction is proposed based on the morphological differences between surface waves and reflections. Frequency-domain high-resolution linear Radon transform (LRT) and time-domain high-resolution hyperbolic Radon transform (HRT) are used to represent surface waves and reflections, respectively. Then, a sparse representation problem based on morphological component analysis (MCA) is built and optimally solved to obtain high-fidelity surface waves. An advantage of our method is its ability to extract surface waves when their frequencies and velocities are close to those of reflections. Furthermore, the results of synthetic and field examples confirm that the proposed method can attenuate the distortion of surface-wave dispersive energy caused by reflections, which contributes to extraction of accurate dispersion curves. [ABSTRACT FROM AUTHOR]

Aimed at the problems of patterned fabric, a defect detection method based on sparse representation are proposed. Due to the sparseness of the fabric defect distribution, a new approach based on sparse representation to addressing patterned fabric defect detection is presented. Inspired by the blind source separation theory and morphological component analysis, the fabric defect image is regarded to consist of a linear superposition of the three part of the defective part, the background part and the noise part. Firstly, histogram equalization preprocessing is used to enhance image contrast. Then the model based on sparse representation is used to decompose the fabric image into cartoon part and texture part. Finally, the defective image is segmented by superimposed binarization to show the defective region. The experimental results demonstrate that the proposed method could efficiently detect defects with shorter time and average detection accuracy reaches 96.3% for patterned fabric defect contained star-, box-and dot-patterned fabric images. [ABSTRACT FROM AUTHOR]

In micro milling, the tool wear condition is key to the geometrical and surface integrity of the product. This study proposes a novel tool wear surface area monitoring approach based on the full tool wear image, which can reflect the tool conditions better than the traditional tool wear width criteria. To meet the challenges of heavy noise, blur boundary, and mis-alignment of the captured tool wear images, this paper develops a region growing algorithm based on morphological component analysis (MCA) to solve the problems. It decomposes the original micro milling tool image into target tool images, background image and noise image. Then, the region growing algorithm is used to detect the defect and extract the wear region of the target tool image. In addition, rotation invariant features are extracted from wear region to overcome the inconsistency of wear image orientation. The experiment results show that region growing based on MCA algorithm can extract the wear region of the target tool image effectively and the extracted wear region also has good indication of tool wear conditions. It also demonstrates that the estimation of wear area can generalize the tool wear width estimation approach, and yield more accurate results than the traditional approaches. [ABSTRACT FROM AUTHOR]

The measurement and monitoring of tool condition are keys to the product precision in the automated manufacturing. To meet the need, this study proposes a novel tool wear monitoring approach based on the monitored image edge detection. Image edge detection has been a fundamental tool to obtain features of images. This approach extracts the tool edge with morphological component analysis. Through the decomposition of original tool wear image, the approach reduces the influence of texture and noise for edge measurement. Based on the target image sparse representation and edge detection, the approach could accurately extract the tool wear edge with continuous and complete contour, and is convenient in charactering tool conditions. Compared to the celebrated algorithms developed in the literature, this approach improves the integrity and connectivity of edges, and the results have shown that it achieves better geometry accuracy and lower error rate in the estimation of tool conditions. [ABSTRACT FROM AUTHOR]

In a recent paper, a method called “texture characteristic based morphological component analysis” (TC-MCA) has been proposed to enhance the performances of texture-based image segmentation algorithms: (1) TC-MCA separates texture into multiple pairs of components each representing a different visual characteristic of the texture; (2) then the TC-MCA algorithm manipulates each component and recombines them to produce the enhanced image where textures are more different, so that the texture-based segmentation is improved. This paper proposes a novel method outperforming TC-MCA by: (1) applying dictionaries based on dual-tree complex wavelet transform (DTCWT) to decompose the image into components representing different visual characteristics of texture, and (2) manipulating the dual-tree complex wavelet coefficients of the texture components to enhance each texture component’s own property and producing an texture-difference-enhanced image by recombining the enhanced components. The wavelet-based texture characteristic morphological component analysis (WT-TC-MCA) is applied as the preprocessing step to some state-of-the-art texture-based segmentation algorithms and compared with other texture enhancing methods, including the TC-MCA, with respect to the accuracy, precision-recall curves of the segmentation results. Experiments demonstrate that our method produces better textural difference enhancement effects and improves texture-based segmentation more than the comparators. [ABSTRACT FROM AUTHOR]

It is essential to extract high-fidelity surface waves in surface-wave surveys. Because reflections usually interfere with surface waves on X components in multicomponent seismic exploration, it is difficult to extract dispersion curves of surface waves. To make matters worse, the frequencies and velocities of higher-mode surface waves are close to those of PS-waves. A method for surface-wave extraction is proposed based on the morphological differences between surface waves and reflections. Frequency-domain high-resolution linear Radon transform (LRT) and time-domain high-resolution hyperbolic Radon transform (HRT) are used to represent surface waves and reflections, respectively. Then, a sparse representation problem based on morphological component analysis (MCA) is built and optimally solved to obtain high-fidelity surface waves. An advantage of our method is its ability to extract surface waves when their frequencies and velocities are close to those of reflections. Furthermore, the results of synthetic and field examples confirm that the proposed method can attenuate the distortion of surface-wave dispersive energy caused by reflections, which contributes to extraction of accurate dispersion curves.

The extensive monitoring of shorelines is becoming important for investigating the impact of coastal erosion. Satellite synthetic aperture radar (SAR) images can cover wide areas independently of weather or time. The recent development of high-resolution satellite SAR images has made observations more detailed. Shoreline extraction using high-resolution images, however, is challenging because of the influence of speckle, crest lines, patterns in sandy beaches, etc. We develop a shoreline extraction method based on the spatial pattern analysis of satellite SAR images. The proposed method consists of image decomposition, smoothing, sea and land area segmentation, and shoreline refinement. The image decomposition step, in which the image is decomposed into its texture and outline components, is based on morphological component analysis. In the image decomposition step, a learning process involving spatial patterns is introduced. The outline images are smoothed using a non-local means filter, and then the images are segmented into sea and land areas using the graph cuts’ technique. The boundary between these two areas can be regarded as the shoreline. Finally, the snakes algorithm is applied to refine the position accuracy. The proposed method is applied to the satellite SAR images of coasts in Japan. The method can successfully extract the shorelines. Through experiments, the performance of the proposed method is confirmed.

The main focus of this work is the reconstruction of the signals f and g i , i = 1 , … , N , from the knowledge of their sums h i = f + g i , under the assumption that f and the g i 's can be sparsely represented with respect to two different dictionaries A f and A g . This generalizes the well-known “morphological component analysis” to a multi-measurement setting. The main result of the paper states that f and the g i 's can be uniquely and stably reconstructed by finding sparse representations of h i for every i with respect to the concatenated dictionary [ A f , A g ] , provided that enough incoherent measurements g i are available. The incoherence is measured in terms of their mutual disjoint sparsity. This method finds applications in the reconstruction procedures of several hybrid imaging inverse problems, where internal data are measured. These measurements usually consist of the main unknown multiplied by other unknown quantities, and so the disjoint sparsity approach can be directly applied. As an example, we show how to apply the method to the reconstruction in quantitative photoacoustic tomography, also in the case when the Grüneisen parameter, the optical absorption and the diffusion coefficient are all unknown. [ABSTRACT FROM AUTHOR]

Bearing signals are often contaminated by in-band interferences and random noise. Oscillatory Behavior-based Signal Decomposition (OBSD) is a new technique which decomposes a signal according to its oscillatory behavior, rather than frequency or scale. Due to the low oscillatory transients of bearing fault-induced signals, the OBSD can be used to effectively extract bearing fault signatures from a blurred signal. However, the quality of the result highly relies on the selection of method-related parameters. Such parameters are often subjectively selected and a systematic approach has not been reported in the literature. As such, this paper proposes a systematic approach to automatic selection of OBSD parameters for reliable extraction of bearing fault signatures. The OBSD utilizes the idea of Morphological Component Analysis (MCA) that optimally projects the original signal to low oscillatory wavelets and high oscillatory wavelets established via the Tunable Q-factor Wavelet Transform (TQWT). In this paper, the effects of the selection of each parameter on the performance of the OBSD for bearing fault signature extraction are investigated. It is found that some method-related parameters can be fixed at certain values due to the nature of bearing fault-induced impulses. To adaptively tune the remaining parameters, index-guided parameter selection algorithms are proposed. A Convergence Index (CI) is proposed and a CI-guided self-tuning algorithm is developed to tune the convergence-related parameters, namely, penalty factor and number of iterations. Furthermore, a Smoothness Index (SI) is employed to measure the effectiveness of the extracted low oscillatory component (i.e. bearing fault signature). It is shown that a minimum SI implies an optimal result with respect to the adjustment of relevant parameters. Thus, two SI-guided automatic parameter selection algorithms are also developed to specify two other parameters, i.e., Q-factor of high-oscillatory wavelets and regularization parameter. Based on the index-guided parameter selection algorithms, an automatic parameter selection method is then proposed for the application of OBSD to bearing fault signature extraction. The proposed method is then validated with simulated signals and experimental data. [ABSTRACT FROM AUTHOR]

In this paper, a novel steganography of digital watermark scheme which contains digital watermark embedding and extraction processes is proposed. The proposed scheme is based on an iterative process of Arnold scrambling transform which is controlled by secret key shared by copyright owner and authorized users, and the extension of morphological component analysis theory which utilizes morphological diversity as the kernel role in blind source separation. Since both the original cover image and watermark are not needed for recovering received watermark, the proposed scheme can be categorized into blind watermarking technique. It is the most applicable watermarking technique due to the availability of the original cover image and watermark cannot be warranted in real-world applications. The proposed scheme overcomes the problem of too narrow hidden data bandwidth in traditional Least- Significant- Bit (LSB) replacement or LSB matching schemes. Instead of only hiding limited bits is allowed, we can embed a meaningful picture into the cover image by applying proposed scheme. Compared with classic Joint Photographic Experts Group (JPEG) steganography schemes, the proposed steganography scheme has much higher embedding capacity and broader applicability scope. Images acquired in steganography experiments and the analysis of experimental results both prove the effectiveness of proposed scheme. Both subjective visual effect and objective quantitative results of the Peak Signal to Noise Ratio (PSNR) index, Structural Similarity (SSIM) index and Normalized Correlation (NC) index confirm its brilliant steganography capability as well as its fine robustness to different noise attacks through communication channel. [ABSTRACT FROM AUTHOR]

It is hard to diagnose the rolling element bearing fault occurring in gearbox due to the complexity and the probable mutual coupling among the kinds of signals. A novel diagnosis method of rolling element bearing fault arising in gearbox based on morphological component analysis (MCA) originating from sparse representation theory is proposed in the paper. By selecting proper dictionaries, different morphological components can be separated successfully from the complex rolling fault signal arising in gearbox, which helps to improve the efficiency and accuracy of diagnosis result. The effectiveness of the proposed method is verified through simulations firstly. Then the proposed method is used in fault feature extracting of complex vibration signals collected from rotating machinery, and the effectiveness of the proposed method is further verified. Besides, the advantage of the proposed method over other relative method is presented. [ABSTRACT FROM AUTHOR]

In this paper, a novel steganography of digital watermark scheme which contains digital watermark embedding and extraction processes is proposed. The proposed scheme is based on an iterative process of Arnold scrambling transform which is controlled by secret key shared by copyright owner and authorized users, and the extension of morphological component analysis theory which utilizes morphological diversity as the kernel role in blind source separation. This scheme overcomes the problem of too narrow hidden data bandwidth in traditional LSB replacement or LSB matching schemes. Compared with classic JPEG steganography schemes, the proposed scheme has much higher embedding capacity and broader applicability scope. Images acquired in experiments and the analysis of experimental results both prove the effectiveness of proposed scheme. Objective quantitative results of the peak signal to noise ratio, structural similarity, and normalized correlation indices confirm its brilliant steganography capability as well as its fine robustness to different noise attacks through communication channel. [ABSTRACT FROM AUTHOR]

An improved morphological component analysis (MCA) method is proposed for the compound fault diagnosis of gearboxes. When gear fault and bearing fault occur simultaneously, the compound fault signal of the gearbox contains meshing components (related to the gear fault) and periodic impulse components (related to the bearing fault). The corresponding fault characteristics can be separated by MCA according to the morphological differences of the components. In the proposed method, the optimal dictionary, which can represent the characteristics of bearing faults, is first selected based on the principle of minimum information entropy. Then, the compound fault signal is decomposed into the meshing component and the periodic impulse component using MCA. Finally, the separated components are subjected to the Hilbert envelope spectrum analysis. The faults of the gear and the bearing can be diagnosed according to the envelope spectra of the separated fault signal components. Simulation and experimental studies validate the effectiveness of the proposed method for the compound fault diagnosis of gearboxes. [ABSTRACT FROM AUTHOR]

We propose a novel image fusion algorithm which involves nonsubsampled shearlet transform (NSST) and morphological component analysis (MCA). The source images are decomposed into several subbands of different scales and directions by NSST. MCA is performed on the low-pass subbands to extract more salient features, and then, the separated cartoon parts and texture parts are fused, respectively. The larger high-pass subbands coefficients are selected by sum-modified-Laplacian scheme in order to obtain more useful information from the source images. The final fused image can be reconstructed by performing inverse NSST on the fused subbands. Experiments on different kinds of images verify the effectiveness of the proposed algorithm, and experimental results show that the proposed algorithm outperforms other methods in both the visual effect and objective evaluation. [ABSTRACT FROM AUTHOR]