Projection onto Convex Sets Method in Space-frequency Domain for Super Resolution

Shen, Wanqiang; Fang, Lincong; Chen, Xiang; Xu, Huaxi

doi:10.4304/jcp.9.8.1959-1966

Cited by 14 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [18] define the following nu mber o f classical methods: methods of iterative back project ion, iterative adaptive filtering, direct methods, methods based on the theory of projections on convex sets and probabilistic methods. It should be added that this classification is inco mplete, since in recent years' methods that combine various mathematical apparatus of the above mentioned groups and form a group of hybrid methods have developed [19,20,21,22,24].…”

Section: Analysis Of Previous Studiesmentioning

confidence: 99%

“…Methods group [25,28,27] on the basis of projections theory on convex sets is based on iterative finding of acceptable region element which is defined by the intersection of a nu mber of convex constraints, starting fro m an arbit rary point. The main problem here is the definit ion of p rojections, wh ich may occur as a not triv ial task.…”

Section: Analysis Of Previous Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Image Superresolution via Divergence Matrix and Automatic Detection of Crossover

Peleshko¹,

Rak²,

Izonin³

2016

IJISA

View full text Add to dashboard Cite

The paper describes the image superresolution method with aggregate divergence matrix and automatic detection of crossover. Formulation of the problem, building extreme optimization task and its solution for solving the automation determination of the crossover coefficient is presented. Different ways for building oversampling images algorith ms based on the proposed method are shows. Based on practical experiments shows the effectiveness of the procedure of automatically the determination of the crossover coefficient. Experimentally established the effectiveness of the procedures oversampling images at high zoo m resolution by the developed method.

show abstract

Section: Analysis Of Previous Studiesmentioning

confidence: 99%

Section: Analysis Of Previous Studiesmentioning

confidence: 99%

Image Superresolution via Divergence Matrix and Automatic Detection of Crossover

Peleshko¹,

Rak²,

Izonin³

2016

IJISA

View full text Add to dashboard Cite

show abstract

“…The reconstruction-based method extracts high-frequency information from multiple frames of LR images in the same scene and fuses them to generate high-resolution (HR) images. It mainly includes an iterative back projection, projection onto convex sets, and the maximum posterior probability method (42,43). However, these methods are relatively complicated to calculate, and the complexity of the CXR imaging content affects the accuracy, which is difficult to guarantee.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification

Sun¹,

Ren²,

Teng³

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: The coronavirus disease 2019 (COVID-19) led to a dramatic increase in the number of cases of patients with pneumonia worldwide. In this study, we aimed to develop an AI-assisted multistrategy image enhancement technique for chest X-ray (CXR) images to improve the accuracy of COVID-19 classification. Methods: Our new classification strategy consisted of 3 parts. First, the improved U-Net model with a variational encoder segmented the lung region in the CXR images processed by histogram equalization. Second, the residual net (ResNet) model with multidilated-rate convolution layers was used to suppress the bone signals in the 217 lung-only CXR images. A total of 80% of the available data were allocated for training and validation. The other 20% of the remaining data were used for testing. The enhanced CXR images containing only soft tissue information were obtained. Third, the neural network model with a residual cascade was used for the super-resolution reconstruction of low-resolution bone-suppressed CXR images. The training and testing data consisted of 1,200 and 100 CXR images, respectively. To evaluate the new strategy, improved visual geometry group (VGG)-16 and ResNet-18 models were used for the COVID-19 classification task of 2,767 CXR images. The accuracy of the multistrategy enhanced CXR images was verified through comparative experiments with various enhancement images. In terms of quantitative verification, 8-fold cross-validation was performed on the bone suppression model. In terms of evaluating the COVID-19 classification, the CXR images obtained by the improved method were used to train 2 classification models.Results: Compared with other methods, the CXR images obtained based on the proposed model had better performance in the metrics of peak signal-to-noise ratio and root mean square error. The super-resolution CXR images of bone suppression obtained based on the neural network model were also anatomically close to the real CXR images. Compared with the initial CXR images, the classification accuracy rates of the internal and external testing data on the VGG-16 model increased by 5.09% and 12.81%, respectively, while the values increased by 3.51% and 18.20%, respectively, for the ResNet-18 model. The numerical results were better than those of the single-enhancement, double-enhancement, and no-enhancement CXR images. Conclusions:The multistrategy enhanced CXR images can help to classify COVID-19 more accurately than the other existing methods.

show abstract

“…Conventional SR methods include projection onto convex sets (POCS) [19,20], Bayesian analysis [21,22], example-based [23,24] and sparse representation [25,26]. However, these conventional SR methods have drawbacks that limit their practical use, for instance, example-based approaches need to learn from large dictionary pairs at the expense of excessive computational times [27] and POCS-based approaches usually cause under-constrained solutions [28].…”

Section: Introductionmentioning

confidence: 99%

Deep learning of multi-resolution X-Ray micro-CT images for multi-scale modelling

Jackson¹,

Niu²,

Manoorkar³

et al. 2021

Preprint

View full text Add to dashboard Cite

There are inherent field-of-view and resolution trade-offs in X-Ray micro-computed tomography (micro-CT) imaging, which limit the characterization, analysis and model development of multi-scale porous systems. In this paper, we overcome these tradeoffs by developing a 3D Enhanced Deep Super Resolution (EDSR) convolutional neural network to create enhanced, high-resolution data over large spatial scales from low-resolution data. Paired high-resolution (HR, 2µm) and low resolution (LR, 6µm) image data from a Bentheimer rock sample are used to train the network. Unseen LR and HR data from the training sample, and another sample with a distinct micro-structure, are used to validate the network with various metrics: textual analysis, segmentation behaviour and porenetwork model (PNM) multiphase flow simulations. The validated EDSR network is then used to generate ≈1000 high-resolution REV subvolume images for each full core sample of length 6-7cm (total image sizes are ≈6000×6000×32000 voxels). Each subvolume has distinct petrophysical properties predicted from PNM simulations, which are combined to create a 3D continuum-scale model of each sample. Drainage immiscible flow at low capillary number is simulated with the models across a range of fractional flows and flow rates and compared directly to experimental pressures and 3D saturations on a 1:1 basis. The EDSR generated model is found to be more accurate than the base LR model at predicting experimental behaviour in the presence of heterogeneities, especially in flow regimes where a wide distribution of pore-sizes are encountered. The models are generally accurate at predicting saturations to within the experimental repeatability and relative permeability across three orders of magnitude. The demonstrated workflow is a fully predictive modelling approach, without calibration, and opens up the possibility to image, simulate and analyse flow in truly multiscale heterogeneous systems that are otherwise intractable.

show abstract

Projection onto Convex Sets Method in Space-frequency Domain for Super Resolution

Cited by 14 publications

References 28 publications

Image Superresolution via Divergence Matrix and Automatic Detection of Crossover

Image Superresolution via Divergence Matrix and Automatic Detection of Crossover

Artificial intelligence-assisted multistrategy image enhancement of chest X-rays for COVID-19 classification

Deep learning of multi-resolution X-Ray micro-CT images for multi-scale modelling

Contact Info

Product

Resources

About