Search

In this paper, we propose the incorporation of noisy image patches and the impulse response of a low-pass filter (LPF) in a convolutional neural network (CNN) to denoise Poisson--Gaussian noise in low-dose computed tomography (LDCT) images. The approach is referred to as fast and flexible denoising CNN (FFDNet)-impulse response (FFDNet-IR) in this paper. The power spectrum sparsity LPF (SLPF) allows low-frequency components to pass through while suppressing higher frequency components by the sparsity approach of the power spectrum, and it is employed to determine the impulse response of LPF. Three well-known types of LPF, namely, Direct LPF, Gaussian LPF, and Butterworth LPF, are also considered to obtain the impulse response of LPF. In the FFDNet-IR, both the noisy image patches and the IR of the LPF are sequentially inputted into the FFDNet to eliminate the Poisson--Gaussian noise. This approach enhances the denoising performance in LDCT images compared with the conventional FFDNet in the evaluation metrics of the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM). Moreover, the FFDNet-IR trained with the Poisson--Gaussian noise model demonstrates the generalization ability and effectively eliminates only Poisson or Gaussian noise. The experiments indicate that the FFDNet-IR more effectively suppresses the noise artifacts and preserves image details compared with the baseline FFDNet, as well as traditional methods such as block-matching and 3D filtering (BM3D) and nonlocal mean (NLM) for LDCT image denoising. [ABSTRACT FROM AUTHOR]

A gear box fault diagnosis method based on improved time series gray image and deep learning is put forward in order to solve the problems such as complex actual working environment of gear box, inadequate performance of extracting features by traditional methods and gray image extraction features. After the vibration signal is decomposed into several intrinsic mode components (IMFs) by EEMD, the IMFs are divided into high-frequency and low-frequency components by cumulative mean criterion, in which the high-frequency components are denoised by wavelet threshold. The high frequency IMFs and low frequency IMFs after noise reduction are reconstructed, and the reconstructed signal is coded by gray image method. Two-dimensional improved time series gray image is sent to convolution neural network for training, so as to exert the advantages of convolution network in feature extraction of pictures and display the results by confusion matrix. Finally, the model results and different gray scale images are compared with traditional diagnosis methods. The results show that compared with common gray image and global denoising gray image, the method proposed in this paper improves the accuracy of gear box fault diagnosis by 4 and 1.8 percentage points respectively, and the convergence speed is significantly faster. Compared with BP neural network and ELM diagnosis method, the method proposed in this paper significantly improves the accuracy of gear box fault diagnosis. [ABSTRACT FROM AUTHOR]

In wireless communication, the channel function estimated commonly has errors due to the influence of noise, so traditional channel estimation methods cannot accurately estimate the real channel function. Aiming at this problem, we propose a channel estimation method that combines sounding reference signal (SRS) remapping with the deep-learning network BRD_ESRNet. BRD_ESRNet consists of image denoising using a deep convolutional neural network with batch renormalization (BRDNet) and an expanded superresolution convolutional neural network (ESRCNN). At the transmitter side, we first map the SRS into four-box structures, and then, the four-box structures are scattered distribution throughout the time-frequency resource block. At the receiver side, we first perform the modified least squares (LS) estimation based on the four-box structure and place the result into the top-left resource unit of the four box. Then, we perform linear interpolation for the whole resource block. Finally, we equate the estimated channel matrix to a low-resolution image containing noise and input it to BRD_ESRNet. Thus, we obtain data with high resolution and achieve the purpose of reducing the estimation error of the channel function. The experimental results show that the proposed method in this paper has a significant improvement in performance compared to the methods of Soltani et al. and Nithya et al. In this paper, the methods of Soltani et al. and Nithya et al. are referred to as methods 1 and 2, respectively. [ABSTRACT FROM AUTHOR]

This paper discusses the challenges of the hyperparameter tuning in deep learning models and proposes a green approach to the neural architecture search process that minimizes its environmental impact. The traditional approach of neural architecture search involves sweeping the entire space of possible architectures, which is computationally expensive and time-consuming. Recently, to address this issue, performance predictors have been proposed to estimate the performance of different architectures, thereby reducing the search space and speeding up the exploration process. The proposed approach aims to develop a performance predictor by training only a small percentage of the possible hyperparameter configurations. The suggested predictor can be queried to find the best configurations without training them on the dataset. Numerical examples of image denoising and classification enable us to evaluate the performance of the proposed approach in terms of performance and time complexity. [ABSTRACT FROM AUTHOR]

This paper realizes infrared image denoising, recognition, and semantic segmentation for complex electrical equipment and proposes a thermal fault diagnosis method that incorporates temperature differences. We introduce a deformable convolution module into the Denoising Convolutional Neural Network (DeDn-CNN) and propose an image denoising algorithm based on this improved network. By replacing Gaussian wrap-around filtering with anisotropic diffusion filtering, we suggest an image enhancement algorithm that employs Weighted Guided Filtering (WGF) with an enhanced Single-Scale Retinex (Ani-SSR) technique to prevent strong edge halos. Furthermore, we propose a refined detection algorithm for electrical equipment that builds upon an improved RetinaNet. This algorithm incorporates a rotating rectangular frame and an attention module, addressing the challenge of precise detection in scenarios where electrical equipment is densely arranged or tilted. We also introduce a thermal fault diagnosis approach that combines temperature differences with DeeplabV3 + semantic segmentation. The improved RetinaNet's recognition results are fed into the DeeplabV3 + model to further segment structures prone to thermal faults. The accuracy of component recognition in this paper achieved 87.23%, 86.54%, and 90.91%, with respective false alarm rates of 7.50%, 8.20%, and 7.89%. We propose a comprehensive method spanning from preprocessing through target recognition to thermal fault diagnosis for infrared images of complex electrical equipment, providing practical insights and robust solutions for future automation of electrical equipment inspections. [ABSTRACT FROM AUTHOR]

In order to suppress noise and artifacts in low-dose computed tomography (LDCT), various deep learning techniques, especially encoder-decoder networks, have been introduced to improve the quality of LDCT images. However, in the encoder-decoder convolutional neural network, fixed-size convolution kernel, continuous down-sampling operation, and the mean square error (MSE) objective function are used, which cause problems such as low utilization of image information, image information loss, and over-smoothing of denoised image. To improve the quality of reconstructed CT images, in this paper, a LDCT image denoising network based on residual multi-scale feature extraction and hybrid loss function is proposed. On the one hand, the multi-scale feature extraction module is designed and introduced into the residual connection to improve the utilization of image feature information; on the other hand, zero padding is used to solve the information loss problem caused by continuous down-sampling operations, and batch normalization (BN) layer is used to alleviate the over-fitting problem caused by network deepening. In addition, a hybrid loss function consisting of MSE loss, structural similarity (SSIM) loss, and perceptual loss is introduced to generate denoised images with high relevance to human perception. Experimental results show that the proposed algorithm can not only improve the quality of denoised images, but also greatly improve the computational speed compared with the state of the art algorithms. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have demonstrated significant potential in enhancing image denoising performance. However, most denoising methods fuse different levels of features through long and short skip connections, easily generating a lot of redundant information, thereby weakening the complementarity of different levels of features, resulting in the loss of image details. In this paper, we propose a multi-scale detail–noise complementary learning (MDNCL) network for additive white Gaussian noise removal and real-world noise removal. The MDNCL network comprises two branches, namely the Detail Feature Learning Branch (DLB) and the Noise Learning Branch (NLB). Specifically, a loss function is applied to guide the complementary learning of image detail features and noisy mappings in these two branches. This learning approach effectively balances noise reduction and detail restoration, especially when dealing with high ratios of noise. To enhance the complementarity of features between different network layers and avoid redundant information, we designed a Feature Subtraction Unit (FSU) to capture the differences in features across the DLB network layers. Our extensive experimental evaluations demonstrate that the MDNCL approach achieves impressive denoising performance and outperforms other popular denoising methods. [ABSTRACT FROM AUTHOR]

The outcome of the denoising network suffers from over-smoothing effect, due to this, the texture content of the object will be lost. Lack of accurate texture properties in the image may lead to inefficient object segmentation and classification. This paper proposes an edge-preserving thresholding approach and applies it to the output of the denoised network. The thresholding approach relies on the distance and weight factors, which move the noisy components toward the mean of the subspace. This proposal is meant to treat over and under-smoothed components, where the smoothing decrement or increment is controlled by the threshold calculated with the average mean of the components in the respective subspace. The approach is compared with state-of-the-art methods in terms of image quality, and it is observed that this approach increases the quality proportionately. The result depicts that there is a significant improvement in PSNR of about 0.7~ 1 dB with the proposed integrated mechanism when compared against the conventional CNN-based image denoiser. Moreover, the edge details are better preserved with the proposed integrated mechanism. [ABSTRACT FROM AUTHOR]

In this paper, we propose the sequential input of a noisy image patch and the impulse response of a low-pass filter (LPF) in the training of the conventional fast and flexible solution for CNN-based image denoising (FFDNet) architecture, which enhances denoising performance and edge preservation and achieves high perceptual quality. The proposed method consists of two steps. In the first step, the power spectrum sparsity is utilized to determine the impulse response of LPF and the resulting impulse response is added to the noisy image patch in a sequential form to estimate the low- and high-frequency components of the input image. In this step, the use of three different types of LPF is also considered. In the second step, the FFDNet architecture, a deep-learning-based image denoiser, is employed. The proposed method achieves satisfactory denoising performance for grayscale and color datasets on synthetic additive white Gaussian noise (AWGN) in terms of the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), feature similarity index (FSIM), and learned perceptual image patch similarity (LPIPS) compared with the original FFDNet. The performances on realistic noise and for chest X-ray images are also investigated. [ABSTRACT FROM AUTHOR]

Image denoising and super-resolution play vital roles in imaging systems, greatly reducing the preprocessing cost of many AI techniques for object detection, segmentation, and tracking. Various advancements have been accomplished in this field, but progress is still needed. In this paper, we have proposed a novel technique named the Enhanced Learning Enriched Features (ELEF) mechanism using a deep convolutional neural network, which makes significant improvements to existing techniques. ELEF consists of two major processes: (1) Denoising, which removes the noise from images; and (2) Super-resolution, which improves the clarity and details of images. Features are learned through deep CNN and not through traditional algorithms so that we can better refine and enhance images. To effectively capture features, the network architecture adopted Dual Attention Units (DUs), which align with the Multi-Scale Residual Block (MSRB) for robust feature extraction, working sidewise with the feature-matching Selective Kernel Extraction (SKF). In addition, resolution mismatching cases are processed in detail to produce high-quality images. The effectiveness of the ELEF model is highlighted by the performance metrics, achieving a Peak Signal-to-Noise Ratio (PSNR) of 42.99 and a Structural Similarity Index (SSIM) of 0.9889, which indicates the ability to carry out the desired high-quality image restoration and enhancement. [ABSTRACT FROM AUTHOR]

During underwater image processing, image quality is affected by the absorption and scattering of light in water, thus causing problems such as blurring and noise. As a result, poor image quality is unavoidable. To achieve overall satisfying research results, underwater image denoising is vital. This paper presents an underwater image denoising method, named HHDNet, designed to address noise issues arising from environmental interference and technical limitations during underwater robot photography. The method leverages a dual-branch network architecture to handle both high and low frequencies, incorporating a hybrid attention module specifically designed for the removal of high-frequency abrupt noise in underwater images. Input images are decomposed into high-frequency and low-frequency components using a Gaussian kernel. For the high-frequency part, a Global Context Extractor (GCE) module with a hybrid attention mechanism focuses on removing high-frequency abrupt signals by capturing local details and global dependencies simultaneously. For the low-frequency part, efficient residual convolutional units are used in consideration of less noise information. Experimental results demonstrate that HHDNet effectively achieves underwater image denoising tasks, surpassing other existing methods not only in denoising effectiveness but also in maintaining computational efficiency, and thus HHDNet provides more flexibility in underwater image noise removal. [ABSTRACT FROM AUTHOR]

To address the problems of noise interference and image blurring in hyperspectral imaging (HSI), this paper proposes a denoising method for HSI based on deep learning and a total variation (TV) prior. The method minimizes the first-order moment distance between the deep prior of a Fast and Flexible Denoising Convolutional Neural Network (FFDNet) and the Enhanced 3D TV (E3DTV) prior, obtaining dual priors that complement and reinforce each other's advantages. Specifically, the original HSI is initially processed with a random binary sparse observation matrix to achieve a sparse representation. Subsequently, the plug-and-play (PnP) algorithm is employed within the framework of generalized alternating projection (GAP) to denoise the sparsely represented HSI. Experimental results demonstrate that, compared to existing methods, this method shows significant advantages in both quantitative and qualitative assessments, effectively enhancing the quality of HSIs. [ABSTRACT FROM AUTHOR]

Deep learning has gained significant interest in image denoising, but there are notable distinctions in the types of deep learning methods used. Discriminative learning is suitable for handling Gaussian noise, while optimization models are effective in estimating real noise. However, there is limited research that summarizes the different deep learning techniques for image denoising. This paper conducts a comprehensive review of techniques and methods used for image denoising and identifying challenges associated with existing approaches. In this paper, a comparative study of deep techniques is offered in image denoising. The study conducted a comprehensive review of 68 papers on image denoising published between 2018 and 2023, providing a detailed analysis of the field's progress and methodologies over a period of 5 years. Through its literature review, the paper provides a comprehensive summary of image denoising in deep learning, including machine learning methods for image denoising, CNNs for image denoising, additive white noisy-image denoising, real noisy image denoising, blind denoising, hybrid noisy images, state- of-the-art methods for image denoising with deep learning, salt and pepper noise, non-linear filters for digital color images. The main objective of this paper is to provide a comprehensive overview of various approaches used for image denoising, each of which has been explored and developed based on individual research studies. The paper aims to discuss these approaches in a systematic and organized manner, comparing their strengths and weaknesses to provide insights for future research in the field. [ABSTRACT FROM AUTHOR]

Image denoising is a fundamental problem in computer vision (CV). Vision Transformer (ViT) is an improvement in CV after convolutional neural networks (CNNs). Recently, it has been demonstrated that the RepVGG network of the structural re-parameterization performs well in image tasks. Experiments indicate that the ViT-based uniformer transformer network has successfully balanced local and global information. As image denoising tasks require more local and global information about the image, a novel image denoising model named structural Re-parameterization Uniformer Transformer-UNet (Rep-UUNet) is proposed in this paper. The model is structural and re-parameterized the structure of the Uniformer Transformer network and uses the UNet skip connections to reconstruct the output image. To complete image downstream tasks, the RepVGG model which utilizes the image local information is used. Indicators such as PSNR, SSIM and others are used to assess the performance of image denoising. Experimental results demonstrate that our Rep-UUNet network model outperforms other five models. [ABSTRACT FROM AUTHOR]

Preprocessing plays a key role in Raman spectral analysis. However, classical preprocessing algorithms often have issues with reducing Raman peak intensities and changing the peak shape when processing spectra. This paper introduces a unified solution for preprocessing based on a convolutional autoencoder to enhance Raman spectroscopy data. One is a denoising algorithm that uses a convolutional denoising autoencoder (CDAE model), and the other is a baseline correction algorithm based on a convolutional autoencoder (CAE+ model). The CDAE model incorporates two additional convolutional layers in its bottleneck layer for enhanced noise reduction. The CAE+ model not only adds convolutional layers at the bottleneck but also includes a comparison function after the decoding for effective baseline correction. The proposed models were validated using both simulated spectra and experimental spectra measured with a Raman spectrometer system. Comparing their performance with that of traditional signal processing techniques, the results of the CDAE-CAE+ model show improvements in noise reduction and Raman peak preservation. [ABSTRACT FROM AUTHOR]

Image-denoising techniques are widely used to defend against Adversarial Examples (AEs). However, denoising alone cannot completely eliminate adversarial perturbations. The remaining perturbations tend to amplify as they propagate through deeper layers of the network, leading to misclassifications. Moreover, image denoising compromises the classification accuracy of original examples. To address these challenges in AE defense through image denoising, this paper proposes a novel AE detection technique. The proposed technique combines multiple traditional image-denoising algorithms and Convolutional Neural Network (CNN) network structures. The used detector model integrates the classification results of different models as the input to the detector and calculates the final output of the detector based on a machine-learning voting algorithm. By analyzing the discrepancy between predictions made by the model on original examples and denoised examples, AEs are detected effectively. This technique reduces computational overhead without modifying the model structure or parameters, effectively avoiding the error amplification caused by denoising. The proposed approach demonstrates excellent detection performance against mainstream AE attacks. Experimental results show outstanding detection performance in well-known AE attacks, including Fast Gradient Sign Method (FGSM), Basic Iteration Method (BIM), DeepFool, and Carlini &Wagner (C&W), achieving a 94% success rate in FGSM detection, while only reducing the accuracy of clean examples by 4%. [ABSTRACT FROM AUTHOR]

Remote sensing image denoising is of great significance for the subsequent use and research of images. Gaussian noise and salt-and-pepper noise are prevalent noises in images. Contemporary denoising algorithms often exhibit limitations when addressing such mixed noise scenarios, manifesting in suboptimal denoising outcomes and the potential blurring of image edges subsequent to the denoising process. To address the above problems, a second-order removal method for mixed noise in remote sensing images was proposed. In the first stage of the method, dilated convolution was introduced into the DnCNN (denoising convolutional neural network) network framework to increase the receptive field of the network, so that more feature information could be extracted from remote sensing images. Meanwhile, a DropoutLayer was introduced after the deep convolution layer to build the noise reduction model to prevent the network from overfitting and to simplify the training difficulty, and then the model was used to perform the preliminary noise reduction on the images. To further improve the image quality of the preliminary denoising results, effectively remove the salt-and-pepper noise in the mixed noise, and preserve more image edge details and texture features, the proposed method employed a second stage on the basis of adaptive median filtering. In this second stage, the median value in the original filter window median was replaced by the nearest neighbor pixel weighted median, so that the preliminary noise reduction result was subjected to secondary processing, and the final denoising result of the mixed noise of the remote sensing image was obtained. In order to verify the feasibility and effectiveness of the algorithm, the remote sensing image denoising experiments and denoised image edge detection experiments were carried out in this paper. When the experimental results are analyzed through subjective visual assessment, images denoised using the proposed method exhibit clearer and more natural details, and they effectively retain edge and texture features. In terms of objective evaluation, the performance of different denoising algorithms is compared using metrics such as mean square error (MSE), peak signal-to-noise ratio (PSNR), and mean structural similarity index (MSSIM). The experimental outcomes indicate that the proposed method for denoising mixed noise in remote sensing images outperforms traditional denoising techniques, achieving a clearer image restoration effect. [ABSTRACT FROM AUTHOR]

Wetland experimental images are often affected by factors such as waves, weather conditions, and lighting, resulting in severe noise in the images. In order to improve the quality and accuracy of wetland experimental images, this paper proposes a wetland experimental image denoising method based on the fast finite shearlet transform (FFST) and a deep convolutional neural network model. The FFST is used to decompose the wetland experimental images, which can capture the features of different frequencies and directions in the images. The network model has a deep network structure and powerful feature extraction capabilities. By training the model, it can learn the relevant features in the wetland experimental images, thereby achieving denoising effects. The experimental results show that, compared to traditional denoising methods, the proposed method in this paper can effectively remove noise from wetland experimental images while preserving the details and textures of the images. This is of great significance for improving the quality and accuracy of wetland experimental images. [ABSTRACT FROM AUTHOR]

Under‐display camera (UDC) allows viewers to interact with the camera and watch the display at the same time. This paper introduces the UDC for Mini‐LED/Micro‐LED displays embedding the camera by drilling a pinhole between LED dies. Based on such an application, the main issues of UDC images are low‐light and noise. We propose a CNN‐based image restoration approach to enhance brightness and remove noise. Moreover, the input of the proposed neural network uses three consecutive frames to reduce the temporal flickering of videos. The processing speed on GPU can reach 1080p@30fps, which is feasible for real‐time streaming applications. [ABSTRACT FROM AUTHOR]

Background: Image denoising technology removes noise from the corrupted image by utilizing different features between image and noise. Convolutional neural network (CNN)-based algorithms have been the concern of the recent progress on diverse image restoration problems and become an efficient solution in image denoising. Objective: Although a quite number of existing CNN-based image denoising methods perform well on the simplified additive white Gaussian noise (AWGN) model, their performance often degrades severely on the real-world noisy images which are corrupted by more complicated noise. Methods: In this paper, we utilized the multi-task learning (MTL) framework to integrate multiple loss functions for collaborative training of CNN. This approach aims to improve the denoising performance of CNNs on real-world images with non-Gaussian noise. Simultaneously, to automatically optimize the weights of individual sub-tasks within the MTL framework, we incorporated a self-learning weight layer into the CNN. Results: Extensive experiments demonstrate that our approach effectively enhances the denoising performance of CNN-based image denoising algorithms on real-world images. It reduces excessive image smoothing, improves quantitative metrics, and enhances visual quality in the restored images. Conclusion: Our method shows the effectiveness of the improved performance of denoising CNNS for real-world image denoising processing. [ABSTRACT FROM AUTHOR]

A problem of image denoising, when images are corrupted by a non-stationary noise, is considered in this paper. Since, in practice, no a priori information on noise is available, noise statistics should be pre-estimated prior to image denoising. In this paper, deep convolutional neural network (CNN) based method for estimation of a map of local, patch-wise, standard deviations of noise (so-called sigma-map) is proposed. It achieves the state-of-the-art performance in accuracy of estimation of sigma-map for the case of non-stationary noise, as well as estimation of a noise variance for the case of an additive white Gaussian noise. Extensive experiments on image denoising using estimated sigma-maps demonstrate that our method outperforms recent CNN-based blind image denoising methods by up to 6 dB in PSNR, as well as other state-of-the-art methods based on sigma-map estimation by up to 0.5 dB, providing, at the same time, better usage flexibility. A comparison with the ideal case, when denoising is applied using ground-truth sigma-map, shows that a difference of corresponding PSNR values for the most of noise levels is within 0.1-0.2 dB, and does not exceed 0.6 dB. [ABSTRACT FROM AUTHOR]

The image denoising model based on convolutional neural network (CNN) can achieve a good denoising effect. However, its robustness is poor, and it is not suitable for direct noise removal tasks. Differently, the image denoising method based on the diffusion equation is more stable and has theoretical guarantees. In order to give full play to the advantages of CNN and diffusion equation in image denoising, this paper proposes a speckle noise denoising model via a combination of the two tools. Firstly, based on the mathematical model of speckle noise, a class of neural network speckle noise removal model which mixes residual learning and structure learning is proposed using image decomposition theory. Then, in order to solve the hyperparameter problem that the model depends on noise variance, a noise variance estimation algorithm based on a nonlinear diffusion equation is proposed. Finally, a speckle noise denoising model based on diffusion equation and CNN is obtained. Numerical simulation experiments verify the accuracy of the variance estimation algorithm and also the denoising effect and practical application value of the proposed method. [ABSTRACT FROM AUTHOR]

Recently, convolutional neural networks (CNNs) have been widely used in image denoising, and their performance has been enhanced through residual learning. However, previous research mostly focused on optimizing the network architecture of CNNs, ignoring the limitations of the commonly used residual learning. This paper identifies two of its limitations, which are the neglect of image information and the lack of effective consideration of image self-similarity. To solve these limitations, this paper proposes a compositional denoising network (CDN), which contains two sub-paths, the image information path (IIP) and the noise estimation path (NEP), respectively. IIP is trained via an image-to-image method to extract image information. For NEP, it utilizes image self-similarity from the perspective of training. This similarity-based training method constrains NEP to output similar estimated noise distributions for different image patches with a specific kind of noise. Finally, image information and noise distribution information are comprehensively considered for image denoising. Experimental results indicate that CDN outperforms other CNN-based methods in both synthetic and real-world image denoising, achieving state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Most studies on convolutional Neural Network (CNN) based image processing have proposed networks that can be optimized for a single level. Here, the term "level" refers to the specific objective defined for each task, such as the degree of noise in denoising tasks. Hence, they underperform on other levels and must be retrained to deliver optimal performance. Using multiple models to cover multiple levels involves very high computational costs. To solve these problems, recent approaches train the networks on two different levels and propose their own modulation methods to enable the arbitrary intermediate levels. However, many of them 1) have difficulty adapting from one level to the other, 2) suffer from unintended artifacts in the intermediate levels, or 3) require large memory and computational cost. In this paper, we propose a novel framework using Filter Transition Network (FTN), which is a non-linear module that easily adapts to new levels, is regularized to prevent undesirable side-effects, and extremely lightweight being a data-independent module. Additionally, for stable learning of FTN, we newly propose a method to initialize nonlinear CNNs with identity mappings. Extensive results for various image processing tasks indicate that the performance of FTN is stable regarding adaptation and modulation and is comparable to that of the other heavy frameworks. [ABSTRACT FROM AUTHOR]

High-dimensional deep features extracted by convolutional neural networks have nonlocal self-similarity. However, incorporating this nonlocal prior of deep features into deep network architectures with an interpretable variational framework is rarely explored. In this paper, we propose a learnable nonlocal self-similarity deep feature network for image denoising. Our method is motivated by the fact that the high-dimensional deep features obey a mixture probability distribution based on the Parzen--Rosenblatt window method. Then a regularizer with learnable nonlocal weights is proposed by considering the dual representation of the log-probability prior of the deep features. Specifically, the nonlocal weights are introduced as dual variables that can be learned by unrolling the associated numerical scheme. This leads to nonlocal modules (NLMs) in newly designed networks. Our method provides a statistical and variational interpretation for the nonlocal self-attention mechanism widely used in various networks. By adopting nonoverlapping window and region decomposition techniques, we can significantly reduce the computational complexity of nonlocal self-similarity, thus enabling parallel computation of the NLM. The solution to the proposed variational problem can be formulated as a learnable nonlocal self-similarity network for image denoising. This work offers a novel approach for constructing network structures that consider self-similarity and nonlocality. The improvements achieved by this method are predictable and partially controllable. Compared with several closely related denoising methods, the experimental results show the effectiveness of the proposed method in image denoising. [ABSTRACT FROM AUTHOR]

Remote sensing (RS) scene classification has always attracted much attention as an elemental and hot topic in the RS community. In recent years, many methods using convolutional neural networks (CNNs) and other advanced machine-learning techniques have been proposed. Their performance is excellent; however, they are disabled when there are noisy labels (i.e., RS scenes with incorrect labels), which is inevitable and common in practice. To address this problem, some specific RS classification models have been developed. Although feasible, their behavior is still limited by the complex contents of RS scenes, excessive noise filtering schemes, and intricate noise-tolerant learning strategies. To further enhance the RS classification results under the noisy scenario and overcome the above limitations, in this paper we propose a multiscale information exploration network (MIEN) and a progressive learning algorithm (PLA). MIEN involves two identical sub-networks whose goals are completing the classification and recognizing possible noisy RS scenes. In addition, we develop a transformer-assistive multiscale fusion module (TAMSFM) to enhance MIEN's behavior in exploring the local, global, and multiscale contents within RS scenes. PLA encompasses a dual-view negative-learning (DNL) stage, an adaptively positive-learning (APL) stage, and an exhaustive soft-label-learning (ESL) stage. Their aim is to learn the relationships between RS scenes and irrelevant semantics, model the links between clean RS scenes and their labels, and generate reliable pseudo-labels. This way, MIEN can be thoroughly trained under the noisy scenario. We simulate noisy scenarios and conduct extensive experiments using three public RS scene data sets. The positive experimental results demonstrate that our MIEN and PLA can fully understand RS scenes and resist the negative influence of noisy samples. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN) has shown its superpower in image denoising in recent years. However, most CNN models suffer from a large number of model parameters and the effect of image denoising still needs to be improved. To cope with these issues, we propose a recursive lightweight CNN approach that can make the noisy images purer and purer, namely PPNets, in this paper. The PPNets mainly consist of four parts: separable convolution–batch normalization–ReLU (SCBR) blocks to extract coarse features, bottlenecks with skip connection to integrate coarse features and refined features to enhance expression ability of model, noise proposal network with an attention mechanism to predict noise level and recursive strategies to stack the denoising model to make the noisy images purer and purer. Since SCBR uses depthwise convolution and pointwise convolution to replace traditional convolution operations, the proposed PPNets have fewer weight parameters. We conduct extensive experiments on two gray image datasets and three color image datasets. The experimental results demonstrate that the PPNets are significantly superior to the traditional models in denoising effectiveness. At the same time, the PPNets outperform the compared state-of-the-art CNN models in terms of both denoising effectiveness and the number of model parameters. [ABSTRACT FROM AUTHOR]

The main objective of this paper is to improve the efficiency and accuracy of convolutional neural network models for image classification and denoising tasks. The focus of the study is on enhancing the activation layer of these models, which is a critical component that determines the output of each neuron in the network. To achieve this goal, we propose a novel activation function based on Chebyshev polynomials, which is both data-driven and self-learnable. In addition to proposing the LIP model, the authors investigate its performance in approximating various nonlinearities and determine its Lipschitz bound. The study then evaluates the performance of the proposed activation function by conducting experiments on multiple datasets using different convolutional neural network models. The results show that the proposed activation function outperforms other activation layers and significantly enhances the accuracy of image classification and denoising tasks. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNN) have attracted considerable interest in image denoising because of their excellent learning capacity. However, most of the existing methods cannot fully extract and utilize the fine features during denoising, resulting in insufficient detailed information extracted and limited model expression ability, especially in complex denoising tasks. Inspired by the above challenges, in this paper, a feature-enhanced multi-scale residual network (FEMRNet) is proposed, mainly including an enhanced feature extraction block (EFEB), a multi-scale residual backbone (MSRB), a detail information recovery block (DIRB) and a merge reconstruction block (MRB). Specifically, the EFEB can increase the receptive field through dilated convolution with different expansion factors, and multi-scale convolution can further enhance the feature. The MSRB integrates global and local feature information through residual denoising blocks and skip connections to enhance the inferencing ability of denoising models. The DIRB is used to finely extract the information in the image, and combine the timing information by convGRU to restore the image details. Finally, MRB is designed to construct a clean image by subtracting the fused noise mapping obtained from MSRB and DIRB with a given noisy image. Additionally, extensive experiments are implemented on commonly-used denoising benchmarks. Comparison experiments with state-of-the-art methods and ablation experiments show that our method achieves promising performance in denoising tasks. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have demonstrated impressive results in additive white Gaussian noise removal due to their strong fitting ability. However, their performance in mixed noise removal remains unsatisfactory, primarily due to their limited receptive field that focuses only on the local features of images and disregards global information. To ameliorate this issue, recent state‐of‐the‐art approaches employ attention mechanism (AM) to capture the global information. However, most AM based methods still suffer from low computational efficiency. In this paper, a novel model named simple dual attention mechanism UNet (SDAUNet) for mixed noise removal is proposed. In SDAUNet, the UNet architecture is used to gradually acquire multi‐scale image features and provide a more comprehensive and accurate representation of the image features than other CNNs. A simple dual attention convolutional block is presented to acquire the global image features that can successfully capture image details with a low burden. The experimental results demonstrate that the SDAUNet model can achieve better measurement metrics and visual performance than other state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

BACKGROUND: Low dose computed tomography (LDCT) uses lower radiation dose, but the reconstructed images contain higher noise that can have negative impact in disease diagnosis. Although deep learning with the edge extraction operators reserves edge information well, only applying the edge extraction operators to input LDCT images does not yield overall satisfactory results. OBJECTIVE: To improve LDCT images quality, this study proposes and tests a dual edge extraction multi-scale attention mechanism convolution neural network (DEMACNN) based on a compound loss. METHODS: The network uses edge extraction operators to extract edge information from both the input images and the feature maps in the network, improving the utilization of the edge operators and retaining the images edge information. The feature enhancement block is constructed by fusing the attention mechanism and multi-scale module, enhancing effective information, while suppressing useless information. The residual learning method is used to learn the network, improving the performance of the network, and solving the problem of gradient disappearance. Except for the network structure, a compound loss function, which consists of the MSE loss, the proposed joint total variation loss, and the edge loss, is proposed to enhance the denoising ability of the network and reserve the edge of images. RESULTS: Compared with other advanced methods (REDCNN, CT-former and EDCNN), the proposed new network achieves the best PSNR and SSIM values in LDCT images of the abdomen, which are 33.3486 and 0.9104, respectively. In addition, the new network also performs well on head and chest image data. CONCLUSION: The experimental results demonstrate that the proposed new network structure and denoising algorithm not only effectively removes the noise in LDCT images, but also protects the edges and details of the images well. [ABSTRACT FROM AUTHOR]

Denoising computed tomography (CT) medical images is crucial in preserving information and restoring images contaminated with noise. Standard filters have extensively been used for noise removal and fine details' preservation. During the transmission of medical images, noise degrades the visibility of anatomical structures and subtle abnormalities, making it difficult for radiologists to accurately diagnose and interpret medical conditions. In recent studies, an optimum denoising filter using the wavelet threshold and deep-CNN was used to eliminate Gaussian noise in CT images using the image quality index (IQI) and peak signal-to-noise ratio (PSNR). Although the results were better than those with traditional techniques, the performance resulted in a loss of clarity and fine details' preservation that rendered the CT images unsuitable. To address these challenges, this paper focuses on eliminating noise in CT scan images corrupted with additive Gaussian blur noise (AGBN) using an ensemble approach that integrates anisotropic Gaussian filter (AGF) and wavelet transform with a deep learning denoising convolutional neural network (DnCNN). First, the noisy image is denoised by AGF and Haar wavelet transform as preprocessing operations to eliminate AGBN. The DnCNN is then combined with AGF and wavelet for post-processing operation to eliminate the rest of the noises. Specifically, we used AGF due to its adaptability to edge orientation and directional information, which prevents blurring along edges for non-uniform noise distribution. Denoised images are evaluated using PSNR, mean squared error (MSE), and the structural similarity index measure (SSIM). Results revealed that the average PSNR value of the proposed ensemble approach is 28.28, and the average computational time is 0.01666 s. The implication is that the MSE between the original and reconstructed images is very low, implying that the image is restored correctly. Since the SSIM values are between 0 and 1.0, 1.0 perfectly matches the reconstructed image with the original image. In addition, the SSIM values at 1.0 or near 1.0 implicitly reveal a remarkable structural similarity between the denoised CT image and the original image. Compared to other techniques, the proposed ensemble approach has demonstrated exceptional performance in maintaining the quality of the image and fine details' preservation. [ABSTRACT FROM AUTHOR]

The prevalent convolutional neural network (CNN)-based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy. However, these methods may ignore the underlying distribution of clean images, inducing distortions or artifacts in denoising results. This paper proposes a new perspective to treat image denoising as a distribution learning and disentangling task. Since the noisy image distribution can be viewed as a joint distribution of clean images and noise, the denoised images can be obtained via manipulating the latent representations to the clean counterpart. This paper also provides a distribution-learning-based denoising framework. Following this framework, we present an invertible denoising network, FDN, without any assumptions on either clean or noise distributions, as well as a distribution disentanglement method. FDN learns the distribution of noisy images, which is different from the previous CNN-based discriminative mapping. Experimental results demonstrate FDN's capacity to remove synthetic additive white Gaussian noise (AWGN) on both category-specific and remote sensing images. Furthermore, the performance of FDN surpasses that of previously published methods in real image denoising with fewer parameters and faster speed. [ABSTRACT FROM AUTHOR]

Considering the potential risk of X-ray to patients, denoising of low-dose X-ray medical images is imperative. Inspired by deep learning, a convolutional autoencoder method for X-ray breast image denoising is proposed in this paper. First, image symmetry and flip are used to increase the number of images in the public dataset; second, the number of samples is increased further by image cropping segmentation, adding simulated noise, and producing the dataset. Finally, a convolutional autoencoder neural network model is constructed, and clean and noisy images are fed into it to complete the training. The results show that this method effectively removes noise while retaining image details in X-ray breast images, yielding higher peak signal-to-noise ratio and structural similarity index values than classical and novel denoising methods. [ABSTRACT FROM AUTHOR]

Banana is a significant crop, and three banana leaf diseases, including Sigatoka, Cordana and Pestalotiopsis, have the potential to have a serious impact on banana production. Existing studies are insufficient to provide a reliable method for accurately identifying banana leaf diseases. Therefore, this paper proposes a novel method to identify banana leaf diseases. First, a new algorithm called K-scale VisuShrink algorithm (KVA) is proposed to denoise banana leaf images. The proposed algorithm introduces a new decomposition scale K based on the semi-soft and middle course thresholds, the ideal threshold solution is obtained and substituted with the newly established threshold function to obtain a less noisy banana leaf image. Then, this paper proposes a novel network for image identification called Ghost ResNeSt-Attention RReLU-Swish Net (GR-ARNet) based on Resnet50. In this, the Ghost Module is implemented to improve the network's effectiveness in extracting deep feature information on banana leaf diseases and the identification speed; the ResNeSt Module adjusts the weight of each channel, increasing the ability of banana disease feature extraction and effectively reducing the error rate of similar disease identification; the model's computational speed is increased using the hybrid activation function of RReLU and Swish. Our model achieves an average accuracy of 96.98% and a precision of 89.31% applied to 13,021 images, demonstrating that the proposed method can effectively identify banana leaf diseases.

In digital image processing, filtering noise is an important step for reconstructing a high-quality image for further processing such as object segmentation, object detection, and object recognition. Various image-denoising approaches, including median, Gaussian, and bilateral filters, are available in the literature. Since convolutional neural networks (CNN) are able to directly learn complex patterns and features from data, they have become a popular choice for image-denoising tasks. As a result of their ability to learn and adapt to various denoising scenarios, CNNs are powerful tools for image denoising. Some deep learning techniques such as CNN incorporate denoising strategies directly into the CNN model layers. A primary limitation of these methods is their necessity to resize images to a consistent size. This resizing can result in a loss of vital image details, which might compromise CNN's effectiveness. Because of this issue, we utilize a traditional denoising method as a preliminary step for noise reduction before applying CNN. To our knowledge, a comparative performance study of CNN using traditional and embedded denoising against a baseline approach (without denoising) is yet to be performed. To analyze the impact of denoising on the CNN performance, in this paper, firstly, we filter the noise from the images using traditional means of denoising method before their use in the CNN model. Secondly, we embed a denoising layer in the CNN model. To validate the performance of image denoising, we performed extensive experiments for both traffic sign and object recognition datasets. To decide whether denoising will be adopted and to decide on the type of filter to be used, we also present an approach exploiting the peak-signal-to-noise-ratio (PSNRs) distribution of images. Both CNN accuracy and PSNRs distribution are used to evaluate the effectiveness of the denoising approaches. As expected, the results vary with the type of filter, impact, and dataset used in both traditional and embedded denoising approaches. However, traditional denoising shows better accuracy, while embedded denoising shows lower computational time for most of the cases. Overall, this comparative study gives insights into whether denoising will be adopted in various CNN-based image analyses, including autonomous driving, animal detection, and facial recognition. [ABSTRACT FROM AUTHOR]

How to remove various kinds of noises of hyperspectral images (HSIs) simultaneously is an important issue that we face, which will directly affect the subsequent application of HSIs. Many HSI denoising techniques have been proposed for this purpose and deep convolutional neural network (CNN) is the most effective approach in recent years. However, existing HSI denoising methods are usually unsatisfactory in removing mixed noises and preserving more details. In this paper, we propose a novel noise intensity estimation guided progressive network (NIEG-PNet) to address these problems. To be specific, we design three core modules to improve the HSI denoising accuracy. First, we propose a noise intensity estimation module (NIEM) to capture multiscale noises and structural characteristics of HSI, which can also be a noise prior to guide the network learning. Second, we propose a recurrent feedback grouped denoising module (RFGDM) to fully capture the spectral correlation. Moreover, we design a dual self-attention module including a position self-attention module and a channel self-attention module to exploit the local and global spatial and spectral correlations and alleviate the problem of small available training HSIs. Last, we propose a global spatial-spectral consistency module (GSSCM), which designs a new parallel structure to combine the two-dimensional and the three-dimensional convolutions more effectively. Moreover, it can explore the relationship between the spectral and the horizontal or vertical direction of the spaces. The experimental results on both synthetic and real-data experiments show the superiority of the proposed NIEG-PNet compared to other traditional and advanced HSI denoising methods. [ABSTRACT FROM AUTHOR]

Deep convolution neural networks have proven their powerful ability in comparing many tasks of computer vision due to their strong data learning capacity. In this paper, we propose a novel end-to-end denoising network, termed Fourier embedded U-shaped network (FEUSNet). By analyzing the amplitude spectrum and phase spectrum of Fourier coefficients, we find that low-frequency features of an image are in the former while noise features are in the latter. To make full use of this characteristic, Fourier features are learned and are concatenated as a prior module that is embedded into a U-shaped network to reduce noise while preserving multi-scale fine details. In the experiments, we first present ablation studies on the Fourier coefficients' learning networks and loss function. Then, we compare the proposed FEUSNet with the state-of-the-art denoising methods in quantization and qualification. The experimental results show that our FEUSNet performs well in noise suppression and preserves multi-scale enjoyable structures, even outperforming advanced denoising approaches. [ABSTRACT FROM AUTHOR]

In this paper, we present a new method for multitask learning applied to ultrasound beamforming. Beamforming is a critical component in the ultrasound image formation pipeline. Ultrasound images are constructed using sensor readings from multiple transducer elements, with each element typically capturing multiple acquisitions per frame. Hence, the beamformer is crucial for framerate performance and overall image quality. Furthermore, post-processing, such as image denoising, is usually applied to the beamformed image to achieve high clarity for diagnosis. This work shows a fully convolutional neural network that can learn different tasks by applying a new weight normalization scheme. We adapt our model to both high frame rate requirements by fitting weight normalization parameters for the sub-sampling task and image denoising by optimizing the normalization parameters for the speckle reduction task. Our model outperforms single-angle delay and sum on pixel-level measures for speckle noise reduction, subsampling, and single-angle reconstruction. [ABSTRACT FROM AUTHOR]

Background: Convolutional neural networks (CNNs) have shown promising results in image denoising tasks. While most existing CNN‐based methods depend on supervised learning by directly mapping noisy inputs to clean targets, high‐quality references are often unavailable for interventional radiology such as cone‐beam computed tomography (CBCT). Purpose: In this paper, we propose a novel self‐supervised learning method that reduces noise in projections acquired by ordinary CBCT scans. Methods: With a network that partially blinds input, we are able to train the denoising model by mapping the partially blinded projections to the original projections. Additionally, we incorporate noise‐to‐noise learning into the self‐supervised learning by mapping the adjacent projections to the original projections. With standard image reconstruction methods such as FDK‐type algorithms, we can reconstruct high‐quality CBCT images from the projections denoised by our projection‐domain denoising method. Results: In the head phantom study, we measure peak signal‐to‐noise ratio (PSNR) and structural similarity index measure (SSIM) values of the proposed method along with the other denoising methods and uncorrected low‐dose CBCT data for a quantitative comparison both in projection and image domains. The PSNR and SSIM values of our self‐supervised denoising approach are 27.08 and 0.839, whereas those of uncorrected CBCT images are 15.68 and 0.103, respectively. In the retrospective study, we assess the quality of interventional patient CBCT images to evaluate the projection‐domain and image‐domain denoising methods. Both qualitative and quantitative results indicate that our approach can effectively produce high‐quality CBCT images with low‐dose projections in the absence of duplicate clean or noisy references. Conclusions: Our self‐supervised learning strategy is capable of restoring anatomical information while efficiently removing noise in CBCT projection data. [ABSTRACT FROM AUTHOR]

In the field of image denoising, convolutional neural networks (CNNs) have become increasingly popular due to their ability to learn effective feature representations from large amounts of data. In the field of image denoising, CNNs are widely used to improve performance. However, increasing network depth can weaken the influence of shallow layers on deep layers, especially for complex denoising tasks such as real denoising and blind denoising, where conventional networks fail to achieve high-quality results. To address this issue, this paper proposes a hybrid dilated convolution-based denoising network (AMDNet) that incorporates attention mechanisms. In specific, AMDNet consists of four modules: the sparse module (SM), the feature fusion module (FFM), the attention guidance module (AGM), and the image residual module (IRM). The SM employs hybrid dilated convolution to extract local features, while the FFM is used to integrate global and local features. The AGM accurately extracts noise information hidden in complex backgrounds. Finally, the IRM reconstructs images in a residual manner to obtain high-quality results after denoising. AMDNet has the following features: (1) The sparse mechanism in hybrid dilated convolution enables better extraction of local features, enhancing the network's ability to capture noise information. (2) The feature fusion module, through long-range connections, fully integrates global and local features, improving the performance of the model; (3) the attention module is ingeniously designed to precisely extract features in complex backgrounds. The experimental results demonstrate that AMDNet achieves outstanding performance on three tasks (Gaussian noise, real noise, and blind denoising). [ABSTRACT FROM AUTHOR]

Image denoising is an important consideration for improving the accuracy of acquired data. Given the morphological nature of astrophotography, with sparse star data overlaid on dim underlying background nebulae and galaxies, denoising is complicated to implement. New methods using convolutional neural networks and transformer networks show promise in general denoising applications. This paper explores the use of five recent denoising networks on astrophotography image data and demonstrates the feasibility as well as optimisations and pitfalls in the use of these networks. The paper confirms that image denoising in astrophotography using such networks is accurate and that a complete knowledge of ground truth might not be necessary for the accurate training of them. [ABSTRACT FROM AUTHOR]

Abnormal target detection in hyperspectral remote sensing image is one of the hotspots in image research. The image noise generated in the detection process will lead to the decline of the quality of hyperspectral remote sensing image. In view of this, this paper proposes an abnormal target detection method of hyperspectral remote sensing image based on the convolution neural network. Firstly, the deep residual learning network model has been used to remove the noise in hyperspectral remote sensing image. Secondly, the spatial and spectral features of hyperspectral remote sensing images were used to optimize the clustering dictionary, and then the image segmentation containing target information is completed. Finally, the image was input into the deep convolution neural network with a dual classifier, and the network detects the abnormal target in the image. The test results of this algorithm show that the structural similarity of the denoised image is higher than 0.86, which shows that this method has good noise reduction performance, image details will not damage, segmentation effect is good, and it can obtain high-definition target image information and accurately detect abnormal targets in the image. [ABSTRACT FROM AUTHOR]

A method is proposed in this paper for life detection and non-contact respiratory rate measurement in cluttered environments. Only an RGB video of the detection area is required. In the method, spatial filtering is firstly applied to each frame of the video for image denoising. Gray level compensation follows to compensate for the change of gray level caused by the environment light. Thirdly, the gray levels of each pixel over time are filtered separately by a low-pass filter. At last, the human is located and the respiratory rate is measured. Tests on a self-made dataset show that an accuracy of 76.7% is achieved by the proposed method, which is better than that of the Convolutional Neural Networks (30%) and the histogram of oriented gradients (3.3%). [ABSTRACT FROM AUTHOR]

Nowadays, urbanization has become a trend, and the realization of urbanization cannot be separated from the implementation of various projects. In the process of project implementation, the most critical issue is safety, so it is extremely necessary to monitor the project safety. Traditional manual monitoring cannot meet the development of today's project, and the design of an automatic monitoring system for project safety has become a hot spot. In this paper, based on image processing and monitoring technology, and engineering safety monitoring and control system based on image quality analysis is studied, which can detect the engineering safety in real-time. Firstly, the image acquisition equipment is used to collect engineering images, and image processing is carried out to improve the image quality. Secondly, the convolutional neural network is used to realize image security analysis and detect the unsafe risk in engineering. Finally, combined with network technology, the automatic monitoring and control system of engineering safety based on image quality analysis is realized. Through simulation analysis, it is found that image processing can effectively remove noise and other interference and improve image quality. And the convolutional neural network can effectively detect the safety problems in the project, which shows that the design and implementation of the project safety monitoring and control system, it can achieve real-time safety monitoring in the implementation of the project, and has a good application effect in the project safety monitoring. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) provide impressive empirical success in various tasks; however, their inner workings generally lack interpretability. In this paper, we interpret shallow CNNs that we have trained for the task of positive sparse signal denoising. We identify and analyze common structures among the trained CNNs. We show that the learned CNN denoisers can be interpreted as a nonlinear locally-adaptive thresholding procedure, which is an empirical approximation of the minimum mean square error estimator. Based on our interpretation, we train constrained CNN denoisers and demonstrate no loss in performance despite having fewer trainable parameters. The interpreted CNN denoiser is an instance of a multivariate spline regression model, and a generalization of classical proximal thresholding operators. [ABSTRACT FROM AUTHOR]

The training and updating of the supervised deep learning model are both dependent on labelled data. Unfortunately, the data‐labelling process is usually expensive and time consuming, which makes obtaining labelled data a huge challenge, especially in the field of geophysics. Because of the above‐mentioned factors, some seismic data denoising methods based on supervised deep learning use synthetic seismic data for network training. Since synthetic seismic data are more or less different from real seismic data, the denoising results may have some amount of residual noise and some false signals when dealing with real seismic data. In response to the above problems, this paper introduces an unpaired domain‐to‐domain translation method based on the framework of two‐way generative adversarial networks, which does not need to use labelled data for training, and effectively solves the problem of lacking labelled data in the seismic data denoising tasks. We use an unpaired mixed training set containing synthetic seismic data and real seismic data to train the network, which effectively improves the denoising ability of the network for the real seismic data. The experimental results show that compared with the state‐of‐the‐art denoising methods such as denoising convolutional neural network, the proposed method can suppress the random noise and ground roll more thoroughly, and the denoising results basically would have no false signals. [ABSTRACT FROM AUTHOR]

In this paper, we address the image denoising problem in presence of speckle degradation typically arising in ultra-sound images. Variational methods and Convolutional Neural Networks (CNNs) are considered well-established methods for specific noise types, such as Gaussian and Poisson noise. Nonetheless, the advances achieved by these two classes of strategies are limited when tackling the de-speckle problem. In fact, variational methods for speckle removal typically amounts to solve a non-convex functional with the related issues from the convergence viewpoint; on the other hand, the lack of large datasets of noise-free ultra-sound images has not allowed the extension of the state-of-the-art CNN denoiser methods to the case of speckle degradation. Here, we aim at combining the classical variational methods with the predictive properties of CNNs by considering a weighted total variation regularized model; the local weights are obtained as the output of a statistically inspired neural network that is trained on a small and composite dataset of natural and synthetic images. The resulting non-convex variational model, which is minimized by means of the Alternating Direction Method of Multipliers (ADMM) is proven to converge to a stationary point. Numerical tests show the effectiveness of our approach for the denoising of natural and satellite images. • An hybrid strategy for the despeckling problem combining convolutional neural networks and variational methods is proposed. • The proposed neural architecture is statistically-inspired and not requires the training on a large data-set of images. • A proof of convergence to a stationary point for the alternating direction method is given. [ABSTRACT FROM AUTHOR]

Noise is a consistent problem for x-ray transmission images of High-Energy-Density (HED) experiments because it can significantly affect the accuracy of inferring quantitative physical properties from these images. We consider experiments that use x-ray area backlighting to image a thin layer of opaque material within a physics package to observe its hydrodynamic evolution. The spatial variance of the x-ray transmission across the system due to changing opacity serves as an analog for measuring density in this evolving layer. The noise in these images adds nonphysical variations in measured intensity, which can significantly reduce the accuracy of our inferred densities, particularly at small spatial scales. Denoising these images is thus necessary to improve our quantitative analysis, but any denoising method also affects the underlying information in the image. In this paper, we present a method for denoising HED x-ray images via a deep convolutional neural network model with a modified DenseNet architecture. In our denoising framework, we estimate the noise present in the real (data) images of interest and apply the inferred noise distribution to a set of natural images. These synthetic noisy images are then used to train a neural network model to recognize and remove noise of that character. We show that our trained denoiser network significantly reduces the noise in our experimental images while retaining important physical features. [ABSTRACT FROM AUTHOR]

Visual information is extremely important in today's world. Visual information transmitted in the form of digital images has become a critical mode of communication. As a result, digital image processing plays a critical role in advancing the image-related applications. Especially, in the medical field, the image processing stage is one of the important stages that need great accuracy to diagnose and determine the type of the disease. Its objective is to overcome the noise problems in medical images and preserve information and edges in images. Medical images can be enhanced by removing noise through the use of traditional and Deep Learning (DL) methods. DL methods depending on Convolutional Neural Networks (CNNs) have achieved great results in the processing stage for noise reduction in medical images. The DL is a promising and effective solution for estimating real noise and extracting representative features from images. This paper presents a review of image denoising methods for medical images, considering noise sources, and types of noise. The concepts of noise reduction (denoising) for various methods are presented. In addition, a comparative study is presented to clarify the advantages and disadvantages of each method. Finally, some possible trends for future work are introduced. [ABSTRACT FROM AUTHOR]