Variant Wasserstein Generative Adversarial Network Applied on Low Dose CT Image Denoising

Computed Tomography(CT)images have been extensively employed in disease diagnosis and treatment,causing a huge concern over the dose of radiation to which patients are exposed.Increasing the radiation dose to get a better image may lead to the development of genetic disorders and cancer in the patients;on the other hand,decreasing it by using a Low-Dose CT(LDCT)image may cause more noise and increased artifacts,which can compromise the diagnosis.So,image reconstruction from LDCT image data is necessary to improve radiologists’judgment and confidence.This study proposed three novel models for denoising LDCT images based on Wasserstein Generative Adversarial Network(WGAN).They were incorporated with different loss functions,including Visual Geometry Group(VGG),Structural Similarity Loss(SSIM),and Structurally Sensitive Loss(SSL),to reduce noise and preserve important information on LDCT images and investigate the effect of different types of loss functions.Furthermore,experiments have been conducted on the Graphical Processing Unit(GPU)and Central Processing Unit(CPU)to compare the performance of the proposed models.The results demonstrated that images from the proposed WGAN-SSIM,WGAN-VGG-SSIM,and WGAN-VGG-SSL were denoised better than those from state-of-the-art models(WGAN,WGAN-VGG,and SMGAN)and converged to a stable equilibrium compared with WGAN and WGAN-VGG.The proposed models are effective in reducing noise,suppressing artifacts,and maintaining informative structure and texture details,especially WGAN-VGG-SSL which achieved a high peak-signalto-noise ratio(PNSR)on both GPU(26.1336)and CPU(25.8270).The average accuracy of WGAN-VGG-SSL outperformed that of the state-ofthe-art methods by 1 percent.Experiments prove that theWGAN-VGG-SSL is more stable than the other models on both GPU and CPU.

Novel Double Modular Redundancy Based Fault-Tolerant FIR Filter for Image Denoising

In signal processing and communication systems,digital filters are widely employed.In some circumstances,the reliability of those systems is crucial,necessitating the use of fault tolerant filter implementations.Many strategies have been presented throughout the years to achieve fault tolerance by utilising the structure and properties of the filters.As technology advances,more complicated systems with several filters become possible.Some of the filters in those complicated systems frequently function in parallel,for example,by applying the same filter to various input signals.Recently,a simple strategy for achieving fault tolerance that takes advantage of the availability of parallel filters was given.Many fault-tolerant ways that take advantage of the filter’s structure and properties have been proposed throughout the years.The primary idea is to use structured authentication scan chains to study the internal states of finite impulse response(FIR)components in order to detect and recover the exact state of faulty modules through the state of non-faulty modules.Finally,a simple solution of Double modular redundancy(DMR)based fault tolerance was developed that takes advantage of the availability of parallel filters for image denoising.This approach is expanded in this short to display how parallel filters can be protected using error correction codes(ECCs)in which each filter is comparable to a bit in a standard ECC.“Advanced error recovery for parallel systems,”the suggested technique,can find and eliminate hidden defects in FIR modules,and also restore the system from multiple failures impacting two FIR modules.From the implementation,Xilinx ISE 14.7 was found to have given significant error reduction capability in the fault calculations and reduction in the area which reduces the cost of implementation.Faults were introduced in all the outputs of the functional filters and found that the fault in every output is corrected.

Image denoising algorithm of refuge chamber by combining wavelet transform and bilateral filtering

In order to preferably identify infrared image of refuge chamber, reduce image noises of refuge chamber and retain more image details, we propose the method of combining two-dimensional discrete wavelet transform and bilateral denoising. First, the wavelet transform is adopted to decompose the image of refuge chamber, of which low frequency component remains unchanged. Then, three high-frequency components are treated by bilateral filtering, and the image is reconstructed. The result shows that the combination of bilateral filtering and wavelet transform for image denoising can better retain the details which are included in the image, while providing better visual effect. This is superior to using either bilateral filtering or wavelet transform alone. It is useful for perfecting emergency refuge system of coal mines.

Fractional-order Sparse Representation for Image Denoising

Sparse representation models have been shown promising results for image denoising. However, conventional sparse representation-based models cannot obtain satisfactory estimations for sparse coefficients and the dictionary. To address this weakness, in this paper, we propose a novel fractional-order sparse representation(FSR) model. Specifically, we cluster the image patches into K groups, and calculate the singular values for each clean/noisy patch pair in the wavelet domain. Then the uniform fractional-order parameters are learned for each cluster.Then a novel fractional-order sample space is constructed using adaptive fractional-order parameters in the wavelet domain to obtain more accurate sparse coefficients and dictionary for image denoising. Extensive experimental results show that the proposed model outperforms state-of-the-art sparse representation-based models and the block-matching and 3D filtering algorithm in terms of denoising performance and the computational efficiency.

Brief review of image denoising techniques

With the explosion in the number of digital images taken every day,the demand for more accurate and visually pleasing images is increasing.However,the images captured by modern cameras are inevitably degraded by noise,which leads to deteriorated visual image quality.Therefore,work is required to reduce noise without losing image features(edges,corners,and other sharp structures).So far,researchers have already proposed various methods for decreasing noise.Each method has its own advantages and disadvantages.In this paper,we summarize some important research in the field of image denoising.First,we give the formulation of the image denoising problem,and then we present several image denoising techniques.In addition,we discuss the characteristics of these techniques.Finally,we provide several promising directions for future research.

A Hybrid CNN for Image Denoising

Deep convolutional neural networks(CNNs)with strong learning abilities have been used in the field of image denoising.However,some CNNs depend on a single deep network to train an image denoising model,which will have poor performance in complex screens.To address this problem,we propose a hybrid denoising CNN(HDCNN).HDCNN is composed of a dilated block(DB),RepVGG block(RVB),feature refinement block(FB),and a single convolution.DB combines a dilated convolution,batch normalization(BN),common convolutions,and activation function of ReLU to obtain more context information.RVB uses parallel combination of convolution,BN,and ReLU to extract complementary width features.FB is used to obtain more accurate information via refining obtained feature from the RVB.A single convolution collaborates a residual learning operation to construct a clean image.These key components make the HDCNN have good performance in image denoising.Experiment shows that the proposed HDCNN enjoys good denoising effect in public data sets.

TV/L2-based image denoisingalgorithm with automaticparameter selection

In order to improve the adaptiveness of TV/L2-based image denoising algorithm in different signal-to-noise ratio(SNR)environments,an iterative denoising method with automatic parameter selection is proposed.Based upon the close connection between optimization function of denoising problem and regularization parameter,an updating model is built to select the regularized parameter.Both the parameter and the objective function are dynamically updated in alternating minimization iterations,consequently,it can make the algorithm work in different SNR environments.Meanwhile,a strategy for choosing the initial regularization parameter is presented.Considering Morozov discrepancy principle,a convex function with respect to the regularization parameter is modeled.Via the optimization method,it is easy and fast to find the convergence value of parameter,which is suitable for the iterative image denoising algorithm.Comparing with several state-of-the-art algorithms,many experiments confirm that the denoising algorithm with the proposed parameter selection is highly effective to evaluate peak signal-to-noise ratio(PSNR)and structural similarity(SSIM),especially in low SNR environment.

Guided Intra-Patch Smoothing Graph Filtering for Single-Image Denoising

Graph filtering is an important part of graph signal processing and a useful tool for image denoising.Existing graph filtering methods,such as adaptive weighted graph filtering(AWGF),focus on coefficient shrinkage strategies in a graph-frequency domain.However,they seldom consider the image attributes in their graph-filtering procedure.Consequently,the denoising performance of graph filtering is barely comparable with that of other state-of-the-art denoising methods.To fully exploit the image attributes,we propose a guided intra-patch smoothing AWGF(AWGF-GPS)method for single-image denoising.Unlike AWGF,which employs graph topology on patches,AWGF-GPS learns the topology of superpixels by introducing the pixel smoothing attribute of a patch.This operation forces the restored pixels to smoothly evolve in local areas,where both intra-and inter-patch relationships of the image are utilized during patch restoration.Meanwhile,a guided-patch regularizer is incorporated into AWGF-GPS.The guided patch is obtained in advance using a maximum-a-posteriori probability estimator.Because the guided patch is considered as a sketch of a denoised patch,AWGF-GPS can effectively supervise patch restoration during graph filtering to increase the reliability of the denoised patch.Experiments demonstrate that the AWGF-GPS method suitably rebuilds denoising images.It outperforms most state-of-the-art single-image denoising methods and is competitive with certain deep-learning methods.In particular,it has the advantage of managing images with significant noise.

Image Denoising with Adaptive Weighted Graph Filtering

Graph filtering,which is founded on the theory of graph signal processing,is proved as a useful tool for image denoising.Most graph filtering methods focus on learning an ideal lowpass filter to remove noise,where clean images are restored from noisy ones by retaining the image components in low graph frequency bands.However,this lowpass filter has limited ability to separate the low-frequency noise from clean images such that it makes the denoising procedure less effective.To address this issue,we propose an adaptive weighted graph filtering(AWGF)method to replace the design of traditional ideal lowpass filter.In detail,we reassess the existing low-rank denoising method with adaptive regularizer learning(ARLLR)from the view of graph filtering.A shrinkage approach subsequently is presented on the graph frequency domain,where the components of noisy image are adaptively decreased in each band by calculating their component significances.As a result,it makes the proposed graph filtering more explainable and suitable for denoising.Meanwhile,we demonstrate a graph filter under the constraint of subspace representation is employed in the ARLLR method.Therefore,ARLLR can be treated as a special form of graph filtering.It not only enriches the theory of graph filtering,but also builds a bridge from the low-rank methods to the graph filtering methods.In the experiments,we perform the AWGF method with a graph filter generated by the classical graph Laplacian matrix.The results show our method can achieve a comparable denoising performance with several state-of-the-art denoising methods.

An FPGA Design for Real-Time Image Denoising

The increasing use of images in miscellaneous applications such as medical image analysis and visual quality inspection has led to growing interest in image processing.However,images are often contaminated with noise which may corrupt any of the following image processing steps.Therefore,noise filtering is often a necessary preprocessing step for the most image processing applications.Thus,in this paper an optimized field-programmable gate array(FPGA)design is proposed to implement the adaptive vector directional distance filter(AVDDF)in hardware/software(HW/SW)codesign context for removing noise from the images in real-time.For that,the high-level synthesis(HLS)flow is used through the Xilinx Vivado HLS tool to reduce the design complexity of the HW part.The SW part is developed based on C/C++programming language and executed on an advanced reduced instruction set computer(RISC)machines(ARM)Cortex-A53 processor.The communication between the SW and HW parts is achieved using the advanced extensible Interface stream(AXI-stream)interface to increase the data bandwidth.The experiment results on the Xilinx ZCU102 FPGA board show an improvement in processing time of the AVDDF filter by 98%for the HW/SW implementation relative to the SW implementation.This result is given for the same quality of image between the HW/SW and SW implementations in terms of the normalized color difference(NCD)and the peak signal to noise ratio(PSNR).

GAUSSIAN PRINCIPLE COMPONENTS FOR NONLOCAL MEANS IMAGE DENOISING

NonLocal Means(NLM),taking fully advantage of image redundancy,has been proved to be very effective in noise removal.However,high computational load limits its wide application.Based on Principle Component Analysis(PCA),Principle Neighborhood Dictionary(PND) was proposed to reduce the computational load of NLM.Nevertheless,as the principle components in PND method are computed directly from noisy image neighborhoods,they are prone to be inaccurate due to the presence of noise.In this paper,an improved scheme for image denoising is proposed.This scheme is based on PND and uses preprocessing via Gaussian filter to eliminate the influence of noise.PCA is then used to project those filtered image neighborhood vectors onto a lower-dimensional space.With the preproc-essing process,the principle components computed are more accurate resulting in an improved de-noising performance.A comparison with some NLM based and state-of-art denoising methods shows that the proposed method performs well in terms of Peak Signal to Noise Ratio(PSNR) as well as image visual fidelity.The experimental results demonstrate that our method outperforms existing methods both subjectively and objectively.

Low-Dose CT Image Denoising Based on Improved WGAN-gp

In order to improve the quality of low-dose computational tomography (CT)images, the paper proposes an improved image denoising approach based on WGAN-gpwith Wasserstein distance. For improving the training and the convergence efficiency, thegiven method introduces the gradient penalty term to WGAN network. The novelperceptual loss is introduced to make the texture information of the low-dose imagessensitive to the diagnostician eye. The experimental results show that compared with thestate-of-art methods, the time complexity is reduced, and the visual quality of low-doseCT images is significantly improved.

Image Denoising Based on the Asymmetric Gaussian Mixture Model

In recent years,image restoration has become a huge subject,and finite hybrid model has been widely used in image denoising because of its easy modeling and strong explanatory results.The gaussian mixture model is the most common one.The existing image denoising methods usually assume that each component of the natural image is subject to the gaussian mixture model(GMM).However,this approach is not entirely reasonable.It is well known that most natural images are complex and their distribution is not entirely gaussian.As a result,there are still many problems that GMM cannot solve.This paper tries to improve the finite mixture model and introduces the asymmetric gaussian mixture model into it.Since the asymmetric gaussian mixture model can simulate the asymmetric distribution on the basis of the gaussian mixture model,it is more consistent with the natural image data,so the denoising effect of the natural complex image is better.We carried out image denoising experiments under different noise scales and types,and found that the asymmetric gaussian mixture model has better denoising effect and performance.

Image Denoising with GAN Based Model

Image denoising is often used as a preprocessing step in computer vision tasks,which can help improve the accuracy of image processing models.Due to the imperfection of imaging systems,transmission media and recording equipment,digital images are often contaminated with various noises during their formation,which troubles the visual effects and even hinders people’s normal recognition.The pollution of noise directly affects the processing of image edge detection,feature extraction,pattern recognition,etc.,making it difficult for people to break through the bottleneck by modifying the model.Many traditional filtering methods have shown poor performance since they do not have optimal expression and adaptation for specific images.Meanwhile,deep learning technology opens up new possibilities for image denoising.In this paper,we propose a novel neural network which is based on generative adversarial networks for image denoising.Inspired by U-net,our method employs a novel symmetrical encoder-decoder based generator network.The encoder adopts convolutional neural networks to extract features,while the decoder outputs the noise in the images by deconvolutional neural networks.Specially,shortcuts are added between designated layers,which can preserve image texture details and prevent gradient explosions.Besides,in order to improve the training stability of the model,we add Wasserstein distance in loss function as an optimization.We use the peak signal-to-noise ratio(PSNR)to evaluate our model and we can prove the effectiveness of it with experimental results.When compared to the state-of-the-art approaches,our method presents competitive performance.

A New Image Denoising Method with Gan Models

In order to obtain clear images and solve the problems of low image quality caused by noise disturbance,a lot of researches have been done on image denoising techniques.In the theoretical system of algorithms studied so far,many algorithms can effectively remove noise in low-dimensional images,but at the same time,the results are slightly inferior when processing high-dimensional images.This paper proposes a q-GAN,which uses multi-scale in generating networks.The convolution kernel extracts image features and transforms the denoising problem into the feature domain.In the feature domain,a residual structure is used to denoise,and the noise distribution is removed from the feature distribution.There are residual noise features in the obtained denoising features,which are removed by subsequent feature filtering of the network structure,and finally a denoised image is generated by fusing the noiseless features.

Metaheuristic Based Noise Identification and Image Denoising Using Adaptive Block Selection Based Filtering

Image denoising has become one of the major forms of image enhancement methods that form the basis of image processing. Due to the inconsistencies in the machinery producing these signals, medical images tend to require these techniques. In real time, images do not contain a single noise, and instead they contain multiple types of noise distributions in several indistinct regions. This paper presents an image denoising method that uses Metaheuristics to perform noise identification. Adaptive block selection is used to identify and correct the noise contained in these blocks. Though the system uses a block selection scheme, modifications are performed on pixel- to-pixel basis and not on the entire blocks;hence the image accuracy is preserved. PSO is used to identify the noise distribution, and appropriate noise correction techniques are applied to denoise the images. Experiments were conducted using salt and pepper noise, Gaussian noise and a combination of both the noise in the same image. It was observed that the proposed method performed effectively on noise levels up-to 0.5 and was able to produce results with PSNR values ranging from 20 to 30 in most of the cases. Excellent reduction rates were observed on salt and pepper noise and moderate reduction rates were observed on Gaussian noise. Experimental results show that our proposed system has a wide range of applicability in any domain specific image denoising scenario, such as medical imaging, mammogram etc.

Deep unfolding multi-scale regularizer network for image denoising

Existing deep unfolding methods unroll an optimization algorithm with a fixed number of steps,and utilize convolutional neural networks(CNNs)to learn data-driven priors.However,their performance is limited for two main reasons.Firstly,priors learned in deep feature space need to be converted to the image space at each iteration step,which limits the depth of CNNs and prevents CNNs from exploiting contextual information.Secondly,existing methods only learn deep priors at the single full-resolution scale,so ignore the benefits of multi-scale context in dealing with high level noise.To address these issues,we explicitly consider the image denoising process in the deep feature space and propose the deep unfolding multi-scale regularizer network(DUMRN)for image denoising.The core of DUMRN is the feature-based denoising module(FDM)that directly removes noise in the deep feature space.In each FDM,we construct a multi-scale regularizer block to learn deep prior information from multi-resolution features.We build the DUMRN by stacking a sequence of FDMs and train it in an end-to-end manner.Experimental results on synthetic and real-world benchmarks demonstrate that DUMRN performs favorably compared to state-of-theart methods.

An Image Denoising Model via the Reconciliation of the Sparsity and Low-Rankness of the Dictionary Domain Coefficients

Sparse coding has achieved great success in various image restoration tasks.However,if the sparse representation coefficients of the structure(low-frequency information)and texture(high-frequency information)components of the image are under the same penalty constraint,the restoration effect may not be ideal.In this paper,an image denoising model combining mixed norm and weighted nuclear norm as regularization terms is proposed.The proposed model simultaneously exploits the group sparsity of the high frequency and lowrankness of the low frequency in dictionary-domain.The mixed norm is used to constrain the high frequency part and the weighted nuclear norm is used to constrain the low frequency part.In order to make the proposed model easy to solve under the framework of alternative direction multiplier method(ADMM),iterative shrinkage threshold method and weighted nuclear norm minimization method are used to solve the two sub-problems.The validity of the model is verified experimentally through comparison with some state-of-the-art methods.

Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis

While recent years have witnessed a dramatic upsurge of exploiting deep neural networks toward solving image denoising,existing methods mostly rely on simple noise assumptions,such as additive white Gaussian noise(AWGN),JPEG compression noise and camera sensor noise,and a general-purpose blind denoising method for real images remains unsolved.In this paper,we attempt to solve this problem from the perspective of network architecture design and training data synthesis.Specifically,for the network architecture design,we propose a swin-conv block to incorporate the local modeling ability of residual convolutional layer and non-local modeling ability of swin transformer block,and then plug it as the main building block into the widely-used image-to-image translation UNet architecture.For the training data synthesis,we design a practical noise degradation model which takes into consideration different kinds of noise(including Gaussian,Poisson,speckle,JPEG compression,and processed camera sensor noises)and resizing,and also involves a random shuffle strategy and a double degradation strategy.Extensive experiments on AGWN removal and real image denoising demonstrate that the new network architecture design achieves state-of-the-art performance and the new degradation model can help to significantly improve the practicability.We believe our work can provide useful insights into current denoising research.The source code is available at https://github.com/cszn/SCUNet.

Group Sparsity Residual Constraint Image Denoising Model with l_(1)/l_(2)Regularization

Group sparse residual constraint with non-local priors(GSRC)has achieved great success in image restoration producing stateof-the-art performance.In the GSRC model,the l_(1)norm minimization is employed to reduce the group sparse residual.In recent years,nonconvex regularization terms have been widely used in image denoising problems,which have achieved better results in denoising than convex regularization terms.In this paper,we use the ratio of the l_(1)and l_(2)norm instead of the l_(1)norm to propose a new image denoising model,i.e.,a group sparse residual constraint model with l_(1)/l_(2)minimization(GSRC-l_(1)/l_(2)).Due to the computational difficulties arisen from the non-convexity and non-linearity,we focus on a constrained optimization problem that can be solved by alternative direction method of multipliers(ADMM).Experimental results of image denoising show that the pro-posed model outperforms several state-of-the-art image denoising methods both visually and quantitatively.