A fast nonlocally centralized sparse representation algorithm for image denoising

Xu, Shaoping; Yang, Xiaohui; Jiang, Shunliang

doi:10.1016/j.sigpro.2016.08.006

Cited by 57 publications

(24 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sparse representations have received an increasing attention in many signal and image processing applications. These applications include denoising [21][22][23] , classification [24][25][26] or pattern recognition [27][28][29] . The use of sparse representations for AD is more original and has been considered in less applications such as hyperspectral imaging [30] , detection of abnormal motions in videos [31] , irregular heartbeat detection in electrocardiograms (ECG) or specular reflectance and shadow removal in natural images [15] .…”

Section: Sparse Representations and Dictionary Learningmentioning

confidence: 99%

Anomaly detection in mixed telemetry data using a sparse representation and dictionary learning

Pilastre¹,

Boussouf

d’Escrivan

et al. 2020

Signal Processing

View full text Add to dashboard Cite

Spacecraft he.alth monitoring and failure prevention are major issues in space operations. ln recent years, machine le.aming techniques have received an increasing interest in many fields and have been applied to housekeeping telemetiy data via semi-supervised leaming. The idea is to use past telemetry describing normal spacecraft behaviour in order to learn a reference mode(to which can be compared most recent data in order to detect potential anomalies. This paper introduces a new machine learning method for anomaly detection in telemetry time series based on a sparse representation and dictionary Jearning. The main advantage of the proposed method is the possibility to handle multivariate telemetry time series described by mixed continuous and discrete parameters, taking into account the potential correlations be tween these parameters. The proposed method is evaluated on a representative anomaly dataset obtained from real satellite telemetry with an available ground-truth and compared to state-of-the-art algorithrns.

show abstract

Section: Sparse Representations and Dictionary Learningmentioning

confidence: 99%

Anomaly detection in mixed telemetry data using a sparse representation and dictionary learning

Pilastre¹,

Boussouf

d’Escrivan

et al. 2020

Signal Processing

View full text Add to dashboard Cite

show abstract

“…The overall outcomes of the Tables (3, 4 Table 9 illustrates the average PSNR performance using nine different state-of-the-art algorithms under different noise levels on the 150 test images. In addition, this part compares the execution time and the performance outcomes between the proposed FQPSO-MP algorithm with seven denoising algorithms such as SNLM [32], BM3D [12], BM3D-SAPCA [33], FastNLM [34], FNCSR [35], K-SVD [7], and WNNM [16] to demonstrate the efficiency of the proposed FQPSO-MP algorithm in large-scale image verity. We had produced 150image from the BSD500 [25] to guarantee a suitable comparison.…”

Section: Comparison Between the Proposed Fqpso-mp And The State-of-thmentioning

confidence: 99%

A Fast Quantum Particle Swarm Optimization Algorithm for Image Denoising Problem

Elsayed¹,

Salem²,

Aly³

2020

IJIES

View full text Add to dashboard Cite

Noise can affect images while acquired, transmitted, stored or compressed. One of the best methods for noise removal is the sparse representation algorithm (SR). The Quantum Particle Swarm Optimization (QPSO) is one of the meta-heuristic algorithms. This paper shows excellent results in noise reduction in the quick version of QPSO, which uses benefit of the SRs and meta-heuristic algorithms. This approach is known as FQPSO-MP, depending on the matching pursuit algorithm (MP). A proposed Dynamic-Multi-Swarm (DMS) and a pre-learned dictionary (FQPSO-MP) method saves the time of calculating the learning dictionary. These modifications contribute to important benefits of computing efficiency (productivity improvements of approximately 90% are achieved) without sacred image quality in comparison with the initial QPSO-MP technique (the bigger reduction relative to the PSNR indexes is lower than 0.58 dB and 0.019). The proposed FQPSO-MP method compared to the original QPSO-MP method after modification. The scientific results show that the FQPSO-MP algorithm is more effective and quicker without sacrificing image quality than the FQPSO-MP algorithm. The experimental results show, in comparison to state-of-the-art denoising algorithms, that both quantitative and image quality results are achieved with the suggested FQPSO-MP method.

show abstract

“…The prediction of impulse noises from the data acquisition process is difficult, and there is also no perfect noise reduction method [1,43]. Solution: In this LR-SVM-HLOG method, the noisy image blocks are identified by computing the average intensity values of the neighborhood pixel for the respective pixel.…”

Section: Diflculty In the Prediction Of Noisementioning

confidence: 99%

Linear Regression Supporting Vector Machine and Hybrid LOG Filter-Based Image Restoration

Basha

Venkateswarlu

2019

Journal of Intelligent Systems

View full text Add to dashboard Cite

Abstract The image restoration (IR) technique is a part of image processing to improve the quality of an image that is affected by noise and blur. Thus, IR is required to attain a better quality of image. In this paper, IR is performed using linear regression-based support vector machine (LR-SVM). This LR-SVM has two steps: training and testing. The training and testing stages have a distinct windowing process for extracting blocks from the images. The LR-SVM is trained through a block-by-block training sequence. The extracted block-by-block values of images are used to enhance the classification process of IR. In training, the imperfections on the image are easily identified by setting the target vectors as the original images. Then, the noisy image is given at LR-SVM testing, based on the original image restored from the dictionary. Finally, the image block from the testing stage is enhanced using the hybrid Laplacian of Gaussian (HLOG) filter. The denoising of the HLOG filter provides enhanced results by using block-by-block values. This proposed approach is named as LR-SVM-HLOG. A dataset used in this LR-SVM-HLOG method is the Berkeley Segmentation Database. The performance of LR-SVM-HLOG was analyzed as peak signal-to-noise ratio (PSNR) and structural similarity index. The PSNR values of the house and pepper image (color image) are 40.82 and 36.56 dB, respectively, which are higher compared to the inter- and intra-block sparse estimation method and block matching and three-dimensional filtering for color images at 20% noise.

show abstract

A fast nonlocally centralized sparse representation algorithm for image denoising

Cited by 57 publications

References 46 publications

Anomaly detection in mixed telemetry data using a sparse representation and dictionary learning

Anomaly detection in mixed telemetry data using a sparse representation and dictionary learning

A Fast Quantum Particle Swarm Optimization Algorithm for Image Denoising Problem

Linear Regression Supporting Vector Machine and Hybrid LOG Filter-Based Image Restoration

Contact Info

Product

Resources

About