In the field of image processing,the analysis of Synthetic Aperture Radar(SAR)images is crucial due to its broad range of applications.However,SAR images are often affected by coherent speckle noise,which significantl...In the field of image processing,the analysis of Synthetic Aperture Radar(SAR)images is crucial due to its broad range of applications.However,SAR images are often affected by coherent speckle noise,which significantly degrades image quality.Traditional denoising methods,typically based on filter techniques,often face challenges related to inefficiency and limited adaptability.To address these limitations,this study proposes a novel SAR image denoising algorithm based on an enhanced residual network architecture,with the objective of enhancing the utility of SAR imagery in complex electromagnetic environments.The proposed algorithm integrates residual network modules,which directly process the noisy input images to generate denoised outputs.This approach not only reduces computational complexity but also mitigates the difficulties associated with model training.By combining the Transformer module with the residual block,the algorithm enhances the network's ability to extract global features,offering superior feature extraction capabilities compared to CNN-based residual modules.Additionally,the algorithm employs the adaptive activation function Meta-ACON,which dynamically adjusts the activation patterns of neurons,thereby improving the network's feature extraction efficiency.The effectiveness of the proposed denoising method is empirically validated using real SAR images from the RSOD dataset.The proposed algorithm exhibits remarkable performance in terms of EPI,SSIM,and ENL,while achieving a substantial enhancement in PSNR when compared to traditional and deep learning-based algorithms.The PSNR performance is enhanced by over twofold.Moreover,the evaluation of the MSTAR SAR dataset substantiates the algorithm's robustness and applicability in SAR denoising tasks,with a PSNR of 25.2021 being attained.These findings underscore the efficacy of the proposed algorithm in mitigating speckle noise while preserving critical features in SAR imagery,thereby enhancing its quality and usability in practical scenarios.展开更多
The visual noise of each light intensity area is different when the image is drawn by Monte Carlo method.However,the existing denoising algorithms have limited denoising performance under complex lighting conditions a...The visual noise of each light intensity area is different when the image is drawn by Monte Carlo method.However,the existing denoising algorithms have limited denoising performance under complex lighting conditions and are easy to lose detailed information.So we propose a rendered image denoising method with filtering guided by lighting information.First,we design an image segmentation algorithm based on lighting information to segment the image into different illumination areas.Then,we establish the parameter prediction model guided by lighting information for filtering(PGLF)to predict the filtering parameters of different illumination areas.For different illumination areas,we use these filtering parameters to construct area filters,and the filters are guided by the lighting information to perform sub-area filtering.Finally,the filtering results are fused with auxiliary features to output denoised images for improving the overall denoising effect of the image.Under the physically based rendering tool(PBRT)scene and Tungsten dataset,the experimental results show that compared with other guided filtering denoising methods,our method improves the peak signal-to-noise ratio(PSNR)metrics by 4.2164 dB on average and the structural similarity index(SSIM)metrics by 7.8%on average.This shows that our method can better reduce the noise in complex lighting scenesand improvethe imagequality.展开更多
To enable proper diagnosis of a patient,medical images must demonstrate no presence of noise and artifacts.The major hurdle lies in acquiring these images in such a manner that extraneous variables,causing distortions...To enable proper diagnosis of a patient,medical images must demonstrate no presence of noise and artifacts.The major hurdle lies in acquiring these images in such a manner that extraneous variables,causing distortions in the form of noise and artifacts,are kept to a bare minimum.The unexpected change realized during the acquisition process specifically attacks the integrity of the image’s quality,while indirectly attacking the effectiveness of the diagnostic process.It is thus crucial that this is attended to with maximum efficiency at the level of pertinent expertise.The solution to these challenges presents a complex dilemma at the acquisition stage,where image processing techniques must be adopted.The necessity of this mandatory image pre-processing step underpins the implementation of traditional state-of-the-art methods to create functional and robust denoising or recovery devices.This article hereby provides an extensive systematic review of the above techniques,with the purpose of presenting a systematic evaluation of their effect on medical images under three different distributions of noise,i.e.,Gaussian,Poisson,and Rician.A thorough analysis of these methods is conducted using eight evaluation parameters to highlight the unique features of each method.The covered denoising methods are essential in actual clinical scenarios where the preservation of anatomical details is crucial for accurate and safe diagnosis,such as tumor detection in MRI and vascular imaging in CT.展开更多
Terahertz imaging technology has great potential applications in areas,such as remote sensing,navigation,security checks,and so on.However,terahertz images usually have the problems of heavy noises and low resolution....Terahertz imaging technology has great potential applications in areas,such as remote sensing,navigation,security checks,and so on.However,terahertz images usually have the problems of heavy noises and low resolution.Previous terahertz image denoising methods are mainly based on traditional image processing methods,which have limited denoising effects on the terahertz noise.Existing deep learning-based image denoising methods are mostly used in natural images and easily cause a large amount of detail loss when denoising terahertz images.Here,a residual-learning-based multiscale hybridconvolution residual network(MHRNet)is proposed for terahertz image denoising,which can remove noises while preserving detail features in terahertz images.Specifically,a multiscale hybrid-convolution residual block(MHRB)is designed to extract rich detail features and local prediction residual noise from terahertz images.Specifically,MHRB is a residual structure composed of a multiscale dilated convolution block,a bottleneck layer,and a multiscale convolution block.MHRNet uses the MHRB and global residual learning to achieve terahertz image denoising.Ablation studies are performed to validate the effectiveness of MHRB.A series of experiments are conducted on the public terahertz image datasets.The experimental results demonstrate that MHRNet has an excellent denoising effect on synthetic and real noisy terahertz images.Compared with existing methods,MHRNet achieves comprehensive competitive results.展开更多
In recent years, deep convolutional neural networks have shown superior performance in image denoising. However, deep network structures often come with a large number of model parameters, leading to high training cos...In recent years, deep convolutional neural networks have shown superior performance in image denoising. However, deep network structures often come with a large number of model parameters, leading to high training costs and long inference times, limiting their practical application in denoising tasks. This paper proposes a new dual convolutional denoising network with skip connections(DECDNet), which achieves an ideal balance between denoising effect and network complexity. The proposed DECDNet consists of a noise estimation network, a multi-scale feature extraction network, a dual convolutional neural network, and dual attention mechanisms. The noise estimation network is used to estimate the noise level map, and the multi-scale feature extraction network is combined to improve the model's flexibility in obtaining image features. The dual convolutional neural network branch design includes convolution and dilated convolution interactive connections, with the lower branch consisting of dilated convolution layers, and both branches using skip connections. Experiments show that compared with other models, the proposed DECDNet achieves superior PSNR and SSIM values at all compared noise levels, especially at higher noise levels, showing robustness to images with higher noise levels. It also demonstrates better visual effects, maintaining a balance between denoising and detail preservation.展开更多
In the field of image denoising, deep learning technology holds a dominance. However, the current network model tends to lose fine-grained information with the depth of the network. To address this issue, this paper p...In the field of image denoising, deep learning technology holds a dominance. However, the current network model tends to lose fine-grained information with the depth of the network. To address this issue, this paper proposes a Multi-scale Attention Dilated Residual Image Denoising Network(MADRNet) based on skip connection, which consists of Dense Interval Transmission Block(DTB), Sparse Residual Block(SRB), Dilated Residual Attention Reconstruction Block(DRAB) and Noise Extraction Block(NEB). The DTB enhances the classical dense layer by reducing information redundancy and extracting more accurate feature information. Meanwhile, SRB improves feature information exchange and model generalization through the use of sparse mechanism and skip connection strategy with different expansion factors. The NEB is primarily responsible for extracting and estimating noise. Its output, together with that of the sparse residual module, acts on the DRAB to effectively prevent loss of shallow feature information and improve denoising effect. Furthermore, the DRAB integrates an dilated residual block into an attention mechanism to extract hidden noise information while using residual learning technology to reconstruct clear images. We respectively examined the performance of MADRNet in gray image denoising, color image denoising and real image denoising. The experiment results demonstrate that proposed network outperforms some excellent image denoising network in terms of peak signal-to-noise ratio, structural similarity index measurement and denoising time. The proposed network effectively addresses issues associated with the loss of detail information.展开更多
Nano-computed tomography(Nano-CT)is an emerging,high-resolution imaging technique.However,due to their low-light properties,tabletop Nano-CT has to be scanned under long exposure conditions,which the scanning process ...Nano-computed tomography(Nano-CT)is an emerging,high-resolution imaging technique.However,due to their low-light properties,tabletop Nano-CT has to be scanned under long exposure conditions,which the scanning process is time-consuming.For 3D reconstruction data,this paper proposed a lightweight 3D noise reduction method for desktop-level Nano-CT called AAD-ResNet(Axial Attention DeNoise ResNet).The network is framed by theU-net structure.The encoder and decoder are incorporated with the proposed 3D axial attention mechanism and residual dense block.Each layer of the residual dense block can directly access the features of the previous layer,which reduces the redundancy of parameters and improves the efficiency of network training.The 3D axial attention mechanism enhances the correlation between 3D information in the training process and captures the long-distance dependence.It can improve the noise reduction effect and avoid the loss of image structure details.Experimental results show that the network can effectively improve the image quality of a 0.1-s exposure scan to a level close to a 3-s exposure,significantly shortening the sample scanning time.展开更多
In this work,we propose a second-order model for image denoising by employing a novel potential function recently developed in Zhu(J Sci Comput 88:46,2021)for the design of a regularization term.Due to this new second...In this work,we propose a second-order model for image denoising by employing a novel potential function recently developed in Zhu(J Sci Comput 88:46,2021)for the design of a regularization term.Due to this new second-order derivative based regularizer,the model is able to alleviate the staircase effect and preserve image contrast.The augmented Lagrangian method(ALM)is utilized to minimize the associated functional and convergence analysis is established for the proposed algorithm.Numerical experiments are presented to demonstrate the features of the proposed model.展开更多
The rail surface status image is affected by the noise in the shooting environment and contains a large amount of interference information, which increases the difficulty of rail surface status identification. In orde...The rail surface status image is affected by the noise in the shooting environment and contains a large amount of interference information, which increases the difficulty of rail surface status identification. In order to solve this problem, a preprocessing method for the rail surface state image is proposed. The preprocessing process mainly includes image graying, image denoising, image geometric correction, image extraction, data amplification, and finally building the rail surface image database. The experimental results show that this method can efficiently complete image processing, facilitate feature extraction of rail surface status images, and improve rail surface status recognition accuracy.展开更多
In order to effectively restore color noisy images with the mixture of Gaussian noise and impulse noise,a new algorithm is proposed using the quaternion-based holistic processing idea for color images.First,a color im...In order to effectively restore color noisy images with the mixture of Gaussian noise and impulse noise,a new algorithm is proposed using the quaternion-based holistic processing idea for color images.First,a color image is represented by a pure quaternion matrix.Secondly,according to the different characteristics of the Gaussian noise and the impulse noise,an algorithm based on quaternion directional vector order statistics is used to detect the impulse noise. Finally,the quaternion optimal weights non-local means filter （QOWNLMF）for Gaussian noise removal is improved for the mixed noise removal.The detected impulse noise pixels are not considered in the calculation of weights.Experimental results on five standard images demonstrate that the proposed algorithm performs better than the commonly used robust outlyingness ratio-nonlocal means （ROR-NLM）algorithm and the optimal weights mixed filter （OWMF）.展开更多
In order to decrease the sensitivity of the constant scale parameter, adaptively optimize the scale parameter in the iteration regularization model （IRM） and attain a desirable level of applicability for image denoi...In order to decrease the sensitivity of the constant scale parameter, adaptively optimize the scale parameter in the iteration regularization model （IRM） and attain a desirable level of applicability for image denoising, a novel IRM with the adaptive scale parameter is proposed. First, the classic regularization item is modified and the equation of the adaptive scale parameter is deduced. Then, the initial value of the varying scale parameter is obtained by the trend of the number of iterations and the scale parameter sequence vectors. Finally, the novel iterative regularization method is used for image denoising. Numerical experiments show that compared with the IRM with the constant scale parameter, the proposed method with the varying scale parameter can not only reduce the number of iterations when the scale parameter becomes smaller, but also efficiently remove noise when the scale parameter becomes bigger and well preserve the details of images.展开更多
Aim To fuse the fluorescence image and transmission image of a cell into a single image containing more information than any of the individual image. Methods Image fusion technology was applied to biological cell imag...Aim To fuse the fluorescence image and transmission image of a cell into a single image containing more information than any of the individual image. Methods Image fusion technology was applied to biological cell imaging processing. It could match the images and improve the confidence and spatial resolution of the images. Using two algorithms, double thresholds algorithm and denoising algorithm based on wavelet transform,the fluorescence image and transmission image of a Cell were merged into a composite image. Results and Conclusion The position of fluorescence and the structure of cell can be displyed in the composite image. The signal-to-noise ratio of the exultant image is improved to a large extent. The algorithms are not only useful to investigate the fluorescence and transmission images, but also suitable to observing two or more fluoascent label proes in a single cell.展开更多
In order to overcome the phenomenon of image blur and edge loss in the process of collecting and transmitting medical image,a denoising method of medical image based on discrete wavelet transform(DWT)and modified medi...In order to overcome the phenomenon of image blur and edge loss in the process of collecting and transmitting medical image,a denoising method of medical image based on discrete wavelet transform(DWT)and modified median filter for medical image coupling denoising is proposed.The method is composed of four modules:image acquisition,image storage,image processing and image reconstruction.Image acquisition gets the medical image that contains Gaussian noise and impulse noise.Image storage includes the preservation of data and parameters of the original image and processed image.In the third module,the medical image is decomposed as four sub bands(LL,HL,LH,HH)by wavelet decomposition,where LL is low frequency,LH,HL,HH are respective for horizontal,vertical and in the diagonal line high frequency component.Using improved wavelet threshold to process high frequency coefficients and retain low frequency coefficients,the modified median filtering is performed on three high frequency sub bands after wavelet threshold processing.The last module is image reconstruction,which means getting the image after denoising by wavelet reconstruction.The advantage of this method is combining the advantages of median filter and wavelet to make the denoising effect better,not a simple combination of the two previous methods.With DWT and improved median filter coefficients coupling denoising,it is highly practical for high-precision medical images containing complex noises.The experimental results of proposed algorithm are compared with the results of median filter,wavelet transform,contourlet and DT-CWT,etc.According to visual evaluation index PSNR and SNR and Canny edge detection,in low noise images,PSNR and SNR increase by 10%–15%;in high noise images,PSNR and SNR increase by 2%–6%.The experimental results of the proposed algorithm achieved better acceptable results compared with other methods,which provides an important method for the diagnosis of medical condition.展开更多
Rather than attempting to separate signal from noise in the spatial domain, it is often advantageous to work in a transform domain. Building on previous work, a novel denoising method based on local adaptive least squ...Rather than attempting to separate signal from noise in the spatial domain, it is often advantageous to work in a transform domain. Building on previous work, a novel denoising method based on local adaptive least squares support vector regression is proposed. Investigation on real images contaminated by Gaussian noise has demonstrated that the proposed method can achieve an acceptable trade off between the noise removal and smoothing of the edges and details.展开更多
Classic non-local means (CNLM) algorithm uses the inherent self-similarity in images for noise removal. The denoised pixel value is estimated through the weighted average of all the pixels in its non-local neighborhoo...Classic non-local means (CNLM) algorithm uses the inherent self-similarity in images for noise removal. The denoised pixel value is estimated through the weighted average of all the pixels in its non-local neighborhood. In the CNLM algorithm, the differences between the pixel value and the distance of the pixel to the center are both taken into consideration to calculate the weighting coefficients. However, the Gaussian kernel cannot reflect the information of edge and structure due to its isotropy, and it has poor performance in flat regions. In this paper, an improved non-local means algorithm based on local edge direction is presented for image denoising. In edge and structure regions, the steering kernel regression (SKR) coefficients are used to calculate the weights, and in flat regions the average kernel is used. Experiments show that the proposed algorithm can effectively protect edge and structure while removing noises better when compared with the CNLM algorithm.展开更多
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 cle...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.展开更多
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 ...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.展开更多
An adaptive image denosing technique was proposed to achieve the tradeoff between details retain and noises removal. In order to achieve this objective, the contourlet transform was introduced and a new threshold meth...An adaptive image denosing technique was proposed to achieve the tradeoff between details retain and noises removal. In order to achieve this objective, the contourlet transform was introduced and a new threshold method, namely CWinShrink, is presented. It shrinks the contourlet coefficients with adaptive shrinkage factors. The shrinkage factors were calculated with reference to the sum of squares of the contourlet coefficients within the neighborhood window. This approach achieves enhanced results for images those are corrupted with additive Gaussian noise. In numerical comparisons with various methods, for a set of noisy images （the PSNR range fi＇om 10.86dB to 26.91dB） , the presented method outperforms VisuShrink and Wiener filter in terms of the PSNR. Experiments also show that this method not only keeps the details of image but also yields denoised images with better visual quality.展开更多
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 dicti...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.展开更多
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 co...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.展开更多
文摘In the field of image processing,the analysis of Synthetic Aperture Radar(SAR)images is crucial due to its broad range of applications.However,SAR images are often affected by coherent speckle noise,which significantly degrades image quality.Traditional denoising methods,typically based on filter techniques,often face challenges related to inefficiency and limited adaptability.To address these limitations,this study proposes a novel SAR image denoising algorithm based on an enhanced residual network architecture,with the objective of enhancing the utility of SAR imagery in complex electromagnetic environments.The proposed algorithm integrates residual network modules,which directly process the noisy input images to generate denoised outputs.This approach not only reduces computational complexity but also mitigates the difficulties associated with model training.By combining the Transformer module with the residual block,the algorithm enhances the network's ability to extract global features,offering superior feature extraction capabilities compared to CNN-based residual modules.Additionally,the algorithm employs the adaptive activation function Meta-ACON,which dynamically adjusts the activation patterns of neurons,thereby improving the network's feature extraction efficiency.The effectiveness of the proposed denoising method is empirically validated using real SAR images from the RSOD dataset.The proposed algorithm exhibits remarkable performance in terms of EPI,SSIM,and ENL,while achieving a substantial enhancement in PSNR when compared to traditional and deep learning-based algorithms.The PSNR performance is enhanced by over twofold.Moreover,the evaluation of the MSTAR SAR dataset substantiates the algorithm's robustness and applicability in SAR denoising tasks,with a PSNR of 25.2021 being attained.These findings underscore the efficacy of the proposed algorithm in mitigating speckle noise while preserving critical features in SAR imagery,thereby enhancing its quality and usability in practical scenarios.
基金supported by the National Natural Science(No.U19A2063)the Jilin Provincial Development Program of Science and Technology (No.20230201080GX)the Jilin Province Education Department Scientific Research Project (No.JJKH20230851KJ)。
文摘The visual noise of each light intensity area is different when the image is drawn by Monte Carlo method.However,the existing denoising algorithms have limited denoising performance under complex lighting conditions and are easy to lose detailed information.So we propose a rendered image denoising method with filtering guided by lighting information.First,we design an image segmentation algorithm based on lighting information to segment the image into different illumination areas.Then,we establish the parameter prediction model guided by lighting information for filtering(PGLF)to predict the filtering parameters of different illumination areas.For different illumination areas,we use these filtering parameters to construct area filters,and the filters are guided by the lighting information to perform sub-area filtering.Finally,the filtering results are fused with auxiliary features to output denoised images for improving the overall denoising effect of the image.Under the physically based rendering tool(PBRT)scene and Tungsten dataset,the experimental results show that compared with other guided filtering denoising methods,our method improves the peak signal-to-noise ratio(PSNR)metrics by 4.2164 dB on average and the structural similarity index(SSIM)metrics by 7.8%on average.This shows that our method can better reduce the noise in complex lighting scenesand improvethe imagequality.
文摘To enable proper diagnosis of a patient,medical images must demonstrate no presence of noise and artifacts.The major hurdle lies in acquiring these images in such a manner that extraneous variables,causing distortions in the form of noise and artifacts,are kept to a bare minimum.The unexpected change realized during the acquisition process specifically attacks the integrity of the image’s quality,while indirectly attacking the effectiveness of the diagnostic process.It is thus crucial that this is attended to with maximum efficiency at the level of pertinent expertise.The solution to these challenges presents a complex dilemma at the acquisition stage,where image processing techniques must be adopted.The necessity of this mandatory image pre-processing step underpins the implementation of traditional state-of-the-art methods to create functional and robust denoising or recovery devices.This article hereby provides an extensive systematic review of the above techniques,with the purpose of presenting a systematic evaluation of their effect on medical images under three different distributions of noise,i.e.,Gaussian,Poisson,and Rician.A thorough analysis of these methods is conducted using eight evaluation parameters to highlight the unique features of each method.The covered denoising methods are essential in actual clinical scenarios where the preservation of anatomical details is crucial for accurate and safe diagnosis,such as tumor detection in MRI and vascular imaging in CT.
基金National Natural Science Foundation of China,Grant/Award Number:62173098,62104047Guangdong Provincial Key Laboratory of Cyber-Physical System,Grant/Award Number:2020B1212060069。
文摘Terahertz imaging technology has great potential applications in areas,such as remote sensing,navigation,security checks,and so on.However,terahertz images usually have the problems of heavy noises and low resolution.Previous terahertz image denoising methods are mainly based on traditional image processing methods,which have limited denoising effects on the terahertz noise.Existing deep learning-based image denoising methods are mostly used in natural images and easily cause a large amount of detail loss when denoising terahertz images.Here,a residual-learning-based multiscale hybridconvolution residual network(MHRNet)is proposed for terahertz image denoising,which can remove noises while preserving detail features in terahertz images.Specifically,a multiscale hybrid-convolution residual block(MHRB)is designed to extract rich detail features and local prediction residual noise from terahertz images.Specifically,MHRB is a residual structure composed of a multiscale dilated convolution block,a bottleneck layer,and a multiscale convolution block.MHRNet uses the MHRB and global residual learning to achieve terahertz image denoising.Ablation studies are performed to validate the effectiveness of MHRB.A series of experiments are conducted on the public terahertz image datasets.The experimental results demonstrate that MHRNet has an excellent denoising effect on synthetic and real noisy terahertz images.Compared with existing methods,MHRNet achieves comprehensive competitive results.
基金funded by National Nature Science Foundation of China,grant number 61302188。
文摘In recent years, deep convolutional neural networks have shown superior performance in image denoising. However, deep network structures often come with a large number of model parameters, leading to high training costs and long inference times, limiting their practical application in denoising tasks. This paper proposes a new dual convolutional denoising network with skip connections(DECDNet), which achieves an ideal balance between denoising effect and network complexity. The proposed DECDNet consists of a noise estimation network, a multi-scale feature extraction network, a dual convolutional neural network, and dual attention mechanisms. The noise estimation network is used to estimate the noise level map, and the multi-scale feature extraction network is combined to improve the model's flexibility in obtaining image features. The dual convolutional neural network branch design includes convolution and dilated convolution interactive connections, with the lower branch consisting of dilated convolution layers, and both branches using skip connections. Experiments show that compared with other models, the proposed DECDNet achieves superior PSNR and SSIM values at all compared noise levels, especially at higher noise levels, showing robustness to images with higher noise levels. It also demonstrates better visual effects, maintaining a balance between denoising and detail preservation.
基金funded by National Nature Science Foundation of China,grant number 61302188。
文摘In the field of image denoising, deep learning technology holds a dominance. However, the current network model tends to lose fine-grained information with the depth of the network. To address this issue, this paper proposes a Multi-scale Attention Dilated Residual Image Denoising Network(MADRNet) based on skip connection, which consists of Dense Interval Transmission Block(DTB), Sparse Residual Block(SRB), Dilated Residual Attention Reconstruction Block(DRAB) and Noise Extraction Block(NEB). The DTB enhances the classical dense layer by reducing information redundancy and extracting more accurate feature information. Meanwhile, SRB improves feature information exchange and model generalization through the use of sparse mechanism and skip connection strategy with different expansion factors. The NEB is primarily responsible for extracting and estimating noise. Its output, together with that of the sparse residual module, acts on the DRAB to effectively prevent loss of shallow feature information and improve denoising effect. Furthermore, the DRAB integrates an dilated residual block into an attention mechanism to extract hidden noise information while using residual learning technology to reconstruct clear images. We respectively examined the performance of MADRNet in gray image denoising, color image denoising and real image denoising. The experiment results demonstrate that proposed network outperforms some excellent image denoising network in terms of peak signal-to-noise ratio, structural similarity index measurement and denoising time. The proposed network effectively addresses issues associated with the loss of detail information.
基金supported by the National Natural Science Foundation of China(62201618).
文摘Nano-computed tomography(Nano-CT)is an emerging,high-resolution imaging technique.However,due to their low-light properties,tabletop Nano-CT has to be scanned under long exposure conditions,which the scanning process is time-consuming.For 3D reconstruction data,this paper proposed a lightweight 3D noise reduction method for desktop-level Nano-CT called AAD-ResNet(Axial Attention DeNoise ResNet).The network is framed by theU-net structure.The encoder and decoder are incorporated with the proposed 3D axial attention mechanism and residual dense block.Each layer of the residual dense block can directly access the features of the previous layer,which reduces the redundancy of parameters and improves the efficiency of network training.The 3D axial attention mechanism enhances the correlation between 3D information in the training process and captures the long-distance dependence.It can improve the noise reduction effect and avoid the loss of image structure details.Experimental results show that the network can effectively improve the image quality of a 0.1-s exposure scan to a level close to a 3-s exposure,significantly shortening the sample scanning time.
文摘In this work,we propose a second-order model for image denoising by employing a novel potential function recently developed in Zhu(J Sci Comput 88:46,2021)for the design of a regularization term.Due to this new second-order derivative based regularizer,the model is able to alleviate the staircase effect and preserve image contrast.The augmented Lagrangian method(ALM)is utilized to minimize the associated functional and convergence analysis is established for the proposed algorithm.Numerical experiments are presented to demonstrate the features of the proposed model.
文摘The rail surface status image is affected by the noise in the shooting environment and contains a large amount of interference information, which increases the difficulty of rail surface status identification. In order to solve this problem, a preprocessing method for the rail surface state image is proposed. The preprocessing process mainly includes image graying, image denoising, image geometric correction, image extraction, data amplification, and finally building the rail surface image database. The experimental results show that this method can efficiently complete image processing, facilitate feature extraction of rail surface status images, and improve rail surface status recognition accuracy.
基金The National Natural Science Foundation of China(No.61572258,61173141,61271312,61232016,61272421)the Natural Science Foundation of Jiangsu Province(No.BK2012858,BK20151530)+1 种基金the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(No.13KJB520015)Open Fund of Jiangsu Engineering Center of Network Monitoring(No.KJR1404)
文摘In order to effectively restore color noisy images with the mixture of Gaussian noise and impulse noise,a new algorithm is proposed using the quaternion-based holistic processing idea for color images.First,a color image is represented by a pure quaternion matrix.Secondly,according to the different characteristics of the Gaussian noise and the impulse noise,an algorithm based on quaternion directional vector order statistics is used to detect the impulse noise. Finally,the quaternion optimal weights non-local means filter （QOWNLMF）for Gaussian noise removal is improved for the mixed noise removal.The detected impulse noise pixels are not considered in the calculation of weights.Experimental results on five standard images demonstrate that the proposed algorithm performs better than the commonly used robust outlyingness ratio-nonlocal means （ROR-NLM）algorithm and the optimal weights mixed filter （OWMF）.
基金The National Natural Science Foundation of China(No.60702069)the Research Project of Department of Education of Zhe-jiang Province (No.20060601)+1 种基金the Natural Science Foundation of Zhe-jiang Province (No.Y1080851)Shanghai International Cooperation onRegion of France (No.06SR07109)
文摘In order to decrease the sensitivity of the constant scale parameter, adaptively optimize the scale parameter in the iteration regularization model （IRM） and attain a desirable level of applicability for image denoising, a novel IRM with the adaptive scale parameter is proposed. First, the classic regularization item is modified and the equation of the adaptive scale parameter is deduced. Then, the initial value of the varying scale parameter is obtained by the trend of the number of iterations and the scale parameter sequence vectors. Finally, the novel iterative regularization method is used for image denoising. Numerical experiments show that compared with the IRM with the constant scale parameter, the proposed method with the varying scale parameter can not only reduce the number of iterations when the scale parameter becomes smaller, but also efficiently remove noise when the scale parameter becomes bigger and well preserve the details of images.
文摘Aim To fuse the fluorescence image and transmission image of a cell into a single image containing more information than any of the individual image. Methods Image fusion technology was applied to biological cell imaging processing. It could match the images and improve the confidence and spatial resolution of the images. Using two algorithms, double thresholds algorithm and denoising algorithm based on wavelet transform,the fluorescence image and transmission image of a Cell were merged into a composite image. Results and Conclusion The position of fluorescence and the structure of cell can be displyed in the composite image. The signal-to-noise ratio of the exultant image is improved to a large extent. The algorithms are not only useful to investigate the fluorescence and transmission images, but also suitable to observing two or more fluoascent label proes in a single cell.
基金Project(2016JJ4074)supported by the Natural Science Foundation of Hunan Province,ChinaProject(14C0920)supported by the Hunan Provincial Education Department,ChinaProject(61771191)supported by the National Natural Science Foundation of China
文摘In order to overcome the phenomenon of image blur and edge loss in the process of collecting and transmitting medical image,a denoising method of medical image based on discrete wavelet transform(DWT)and modified median filter for medical image coupling denoising is proposed.The method is composed of four modules:image acquisition,image storage,image processing and image reconstruction.Image acquisition gets the medical image that contains Gaussian noise and impulse noise.Image storage includes the preservation of data and parameters of the original image and processed image.In the third module,the medical image is decomposed as four sub bands(LL,HL,LH,HH)by wavelet decomposition,where LL is low frequency,LH,HL,HH are respective for horizontal,vertical and in the diagonal line high frequency component.Using improved wavelet threshold to process high frequency coefficients and retain low frequency coefficients,the modified median filtering is performed on three high frequency sub bands after wavelet threshold processing.The last module is image reconstruction,which means getting the image after denoising by wavelet reconstruction.The advantage of this method is combining the advantages of median filter and wavelet to make the denoising effect better,not a simple combination of the two previous methods.With DWT and improved median filter coefficients coupling denoising,it is highly practical for high-precision medical images containing complex noises.The experimental results of proposed algorithm are compared with the results of median filter,wavelet transform,contourlet and DT-CWT,etc.According to visual evaluation index PSNR and SNR and Canny edge detection,in low noise images,PSNR and SNR increase by 10%–15%;in high noise images,PSNR and SNR increase by 2%–6%.The experimental results of the proposed algorithm achieved better acceptable results compared with other methods,which provides an important method for the diagnosis of medical condition.
基金Supported by the Foundation of Hubei Provincial Department of Education(No.2003EB0018).
文摘Rather than attempting to separate signal from noise in the spatial domain, it is often advantageous to work in a transform domain. Building on previous work, a novel denoising method based on local adaptive least squares support vector regression is proposed. Investigation on real images contaminated by Gaussian noise has demonstrated that the proposed method can achieve an acceptable trade off between the noise removal and smoothing of the edges and details.
基金National Key Research and Development Program of China(No.2016YFC0101601)Fund for Shanxi“1331 Project”Key Innovative Research Team+1 种基金Shanxi Province Science Foundation for Youths(No.201601D021080)Universities Science and Technology Innovation Project of Shanxi Province(No.2017107)
文摘Classic non-local means (CNLM) algorithm uses the inherent self-similarity in images for noise removal. The denoised pixel value is estimated through the weighted average of all the pixels in its non-local neighborhood. In the CNLM algorithm, the differences between the pixel value and the distance of the pixel to the center are both taken into consideration to calculate the weighting coefficients. However, the Gaussian kernel cannot reflect the information of edge and structure due to its isotropy, and it has poor performance in flat regions. In this paper, an improved non-local means algorithm based on local edge direction is presented for image denoising. In edge and structure regions, the steering kernel regression (SKR) coefficients are used to calculate the weights, and in flat regions the average kernel is used. Experiments show that the proposed algorithm can effectively protect edge and structure while removing noises better when compared with the CNLM algorithm.
基金This work is supported by National Natural Science Foundation of China[61673108,41706103]The initials of authors who received these grants are LZ and YZ,respectively.It is also supported by Natural Science Foundation of Jiangsu Province,China[BK20170306]The initials of author who received this grant are YZ.
文摘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.
基金the Scientific Research Project of Zhejiang Education Department of China (No. Y20108569)the Soft Science Project of Ningbo of China (No. 2011A1058)the Soft Science of Zhejiang Association for Science and Technology of China (No. KX12E-10)
文摘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.
基金Sponsored by Key Lab of Optoelectronic Technology &System,Department of Education, China(Grant No.200373 -1 -2).
文摘An adaptive image denosing technique was proposed to achieve the tradeoff between details retain and noises removal. In order to achieve this objective, the contourlet transform was introduced and a new threshold method, namely CWinShrink, is presented. It shrinks the contourlet coefficients with adaptive shrinkage factors. The shrinkage factors were calculated with reference to the sum of squares of the contourlet coefficients within the neighborhood window. This approach achieves enhanced results for images those are corrupted with additive Gaussian noise. In numerical comparisons with various methods, for a set of noisy images （the PSNR range fi＇om 10.86dB to 26.91dB） , the presented method outperforms VisuShrink and Wiener filter in terms of the PSNR. Experiments also show that this method not only keeps the details of image but also yields denoised images with better visual quality.
基金supported by the National Natural Science Foundation of China(61573219,61402203,61401209,61701192,61671274)the Opening Fund of Shandong Provincial Key Laboratory of Network Based Intelligent Computing+2 种基金the Fostering Project of Dominant DisciplineTalent Team of Shandong Province Higher Education InstitutionsFostering Project of Dominant Discipline and Talent Team of SDUFE
文摘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.
基金supported by National Natural Science Foundation ofChina (61672279)Project of “Six Talents Peak” in Jiangsu (2012-WLW-023)OpenFoundation of State Key Laboratory of Hydrology-Water Resources and HydraulicEngineering, Nanjing Hydraulic Research Institute, China (2016491411).
文摘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.
