Image Reconstruction Based on Compressive Sensing via CoSaMP

2014 ◽  
Vol 631-632 ◽  
pp. 436-440 ◽  
Author(s):  
Lin Zhang
Keyword(s):  
Image Reconstruction ◽  
Compressive Sensing ◽  
Matching Pursuit ◽  
Curvelet Transform ◽  
Stopping Rule ◽  
Compressive Sampling ◽  
New Method ◽  
Signal Recovery ◽  
Recovery Algorithm ◽  
Number Of Iterations

Compressive Sampling Matching Pursuit (CoSaMP) is a new iterative recovery algorithm which has splendid theoretical guarantees for convergence and delivers the same guarantees as the best optimization-based approaches. In this paper, we propose a new signal recovery framework which combines CoSaMP and Curvelet transform for better performance. In classic CoSaMP, the number of iterations is fixed. We discuss a new stopping rule to halting the algorithm in this paper. In addition, the choice of several adjustable parameters in algorithm such as the number of measurements and the sparse level of the signal also will impact the performance. So we gain above parameters via a large number of experiments. According to experiments, we determine an optimum value for the parameters to use in this application. The experiments show that the new method not only has better recovery quality and higher PSNRs, but also can achieve optimization steadily and effectively.

Image Adaptive Denoising Method Based on Compressive Sensing

2014 ◽  
Vol 635-637 ◽  
pp. 993-996
Author(s):  
Lin Zhang ◽  
Xia Ling Zeng ◽  
Sun Li
Keyword(s):  
Genetic Algorithm ◽  
Image Quality ◽  
Compressive Sensing ◽  
Matching Pursuit ◽  
Experimental Results ◽  
New Method ◽  
Denoising Method ◽  
Edge Information ◽  
Fast Speed ◽  
Adaptive Denoising

We present a new adaptive denosing method using compressive sensing (CS) and genetic algorithm (GA). We use Regularized Orthogonal Matching Pursuit (ROMP) to remove the noise of image. ROMP algorithm has the advantage of correct performance, stability and fast speed. In order to obtain the optimal denoising effect, we determine the values of the parameters of ROMP by GA. Experimental results show that the proposed method can remove the noise of image effectively. Compared with other traditional methods, the new method retains the most abundant edge information and important details of the image. Therefore, our method has optimal image quality and a good performance on PSNR.

An Improvement of Physics Based Compressive Sensing With Domain Decomposition to Monitor Temperature in Fused Filament Fabrication Process

2019 ◽  
Author(s):  
Yanglong Lu ◽  
Yan Wang
Keyword(s):  
Domain Decomposition ◽  
Compressive Sensing ◽  
Manufacturing Systems ◽  
Matching Pursuit ◽  
Domain Decomposition Method ◽  
Mass Matrix ◽  
Fused Filament Fabrication ◽  
Basis Matrix ◽  
Decomposition Approach ◽  
Recovery Algorithm

Abstract Sensors in manufacturing play an important role in monitoring and improving the quality of products. However, the rising cost of sensing subsystems and the bandwidth limitation of data transmission are challenges in modern manufacturing systems, which rely on a large number of sensors. Recently, a physics based compressive sensing (PBCS) approach was proposed to monitor manufacturing processes with reduced number of sensors and amount of collected data. PBCS significantly improves the compression ratio from classical compressed sensing by incorporating the knowledge of physical phenomena in specific applications. In this paper, a modified orthogonal matching pursuit (OMP) recovery algorithm, called constrained OMP, is developed for PBCS when coherence exists between the measurement matrix and basis matrix. The efficiency of PBCS recovery is also improved by introducing a domain decomposition approach, which can reduce the size of model matrices, such as the conduction matrix and mass matrix in the transient heat transfer application. The improved PBCS with the domain decomposition method is used to monitor the temperature distribution in the cooling process and real-time printing process of fused filament fabrication.

A new method using the convolutional neural network with compressive sensing for fabric defect classification based on small sample sizes

2018 ◽  
Vol 89 (17) ◽  
pp. 3539-3555 ◽  
Author(s):  
Bing Wei ◽  
Kuangrong Hao ◽  
Xue-song Tang ◽  
Yongsheng Ding
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Compressive Sensing ◽  
Classification Accuracy ◽  
Small Sample ◽  
Compressive Sampling ◽  
New Method ◽  
Sample Sizes ◽  
Fabric Defect ◽  
Small Sample Sizes

The convolutional neural network (CNN) has recently achieved great breakthroughs in many computer vision tasks. However, its application in fabric texture defects classification has not been thoroughly researched. To this end, this paper carries out a research on its application based on the CNN model. Meanwhile, since the CNN cannot achieve good classification accuracy in small sample sizes, a new method combining compressive sensing and the convolutional neural network (CS-CNN) is proposed. Specifically, this paper uses the compressive sampling theorem to compress and augment the data in small sample sizes; then the CNN can be employed to classify the data features directly from compressive sampling; finally, we use the test data to verify the classification performance of the method. The explanatory experimental results demonstrate that, in comparison with the state-of-the-art methods for running time, our CS-CNN approach can effectively improve the classification accuracy in fabric defect samples, even with a small number of defect samples.

Sign in / Sign up

Export Citation Format

Share Document