Denoising Performance Research Articles

INVESTIGATION OF DISCRETE WAVELET TRANSFORM DOMAIN OPTIMAL PARAMETRIC APPROACH FOR DENOISING OF PHONOCARDIOGRAM SIGNAL

Phonocardiogram (PCG) signals are contaminated with various noise signals, which hinders the accurate diagnostic interpretation of the signal. Discrete wavelet transform (DWT) is a well-known technique used to remove noise from PCG signals and improve signal quality. The performance of DWT-based denoising depends upon several parameters involved in the process, such as mother wavelets used for decomposition, the number of decomposition levels (DLs), thresholding technique used and the threshold estimation rule followed. In this work, an investigative study is carried out to select the optimal parameter values which give the best denoising performance. The metrics such as mean-square error (MSE), normalized-mean-square error (NMSE), root-mean-square error (RMSE), percentage root-mean-square difference (PRD) and signal-to-noise ratio (SNR) are used to evaluate the performance of the denoising in this study. The results obtained show that the fifth-order Coiflet wavelet is best suited for denoising PCG signals when applied with the soft thresholding (ST) function and rigrsure threshold selection rule. Also, the optimum number of DLs resulting in better performance is level 6. SNR value obtained from the studies shows the efficacy of the parameters selected for denoising. The denoised PCG signals provide accurate information to determine various kinds of heart valve-related disorders (HVDs).

Generative Adaptive Convolutions for Real-World Noisy Image Denoising

Recently, deep learning techniques are soaring and have shown dramatic improvements in real-world noisy image denoising. However, the statistics of real noise generally vary with different camera sensors and in-camera signal processing pipelines. This will induce problems of most deep denoisers for the overfitting or degrading performance due to the noise discrepancy between the training and test sets. To remedy this issue, we propose a novel flexible and adaptive denoising network, coined as FADNet. Our FADNet is equipped with a plane dynamic filter module, which generates weight filters with flexibility that can adapt to the specific input and thereby impedes the FADNet from overfitting to the training data. Specifically, we exploit the advantage of the spatial and channel attention, and utilize this to devise a decoupling filter generation scheme. The generated filters are conditioned on the input and collaboratively applied to the decoded features for representation capability enhancement. We additionally introduce the Fourier transform and its inverse to guide the predicted weight filters to adapt to the noisy input with respect to the image contents. Experimental results demonstrate the superior denoising performances of the proposed FADNet versus the state-of-the-art. In contrast to the existing deep denoisers, our FADNet is not only flexible and efficient, but also exhibits a compelling generalization capability, enjoying tremendous potential for practical usage.

A New Proportionate Filtered-x RLS Algorithm for Active Noise Control System.

The filtered-x recursive least square (FxRLS) algorithm is widely used in the active noise control system and has achieved great success in some complex de-noising environments, such as the cabin in vehicles and aircraft. However, its performance is sensitive to some user-defined parameters such as the forgetting factor and initial gain. Once these parameters are not selected properly, the de-noising effect of FxRLS will deteriorate. Moreover, the tracking performance of FxRLS for mutation is still restricted to a certain extent. To solve the above problems, this paper proposes a new proportional FxRLS (PFxRLS) algorithm. The forgetting factor and initial gain sensitivity are successfully reduced without introducing new turning parameters. The de-noising level and tracking performance have also been improved. Moreover, the momentum technique is introduced in PFxRLS to further improve its robustness and de-noising level. To ensure stability, its convergence condition is also discussed in this paper. The effectiveness of the proposed algorithms is illustrated by simulations and experiments with different user-defined parameters and time-varying noise environments.

Graph denoising of impulsive EEG signals and the effect of their graph representation

As the field of brain monitoring is evolving rapidly, there is an increasing demand for innovative approaches to handle relevant signals. Recently, graph signal processing, which enables the treatment of signal ensembles, emerges as a powerful alternative to a per-signal analysis. This is especially the case for electroencephalogram (EEG) signals that naturally admit graph representations, with each electrode corresponding to one graph node. These signals are often corrupted by impulsive noise best characterized by heavy-tailed statistics, thus driving conventional denoising techniques to failure. To address this problem, we propose an efficient regularized graph filtering method based on fractional lower-order moments, which better adapt to heavy-tailed statistics. An experimental evaluation on real EEG measurements, including the publicly available P300 dataset and epilepsy signals, reveals a superior denoising performance of our method when compared against well-established EEG signal denoising methods.

A photon-number-based systematic algorithm for range image recovery of GM-APD lidar under few-frames detection

The GM-APD lidar can detect the single-photon level echo signal and obtain three-dimensional range information, but the imaging results are greatly affected by noise and statistical frame number. Considering these problems, this paper proposes a photon-number systematic (PNS) algorithm under a few statistical frames in low SNR (signal-to-noise ratio). It includes three parts: (a) We realize range image recovery based on the signal photon number histogram with a match filtering algorithm by using the proposed normalized discrete waveform functions. (b) We propose a two-dimensional double-threshold approximation denoising algorithm, which is used for image-level denoising. (c) The neighborhood threshold smoothing algorithm is proposed to supplement the target missing pixels. It is verified by Monte Carlo simulation and experimental results that the proposed algorithm has a high recovery ratio, denoising, and fidelity performance under few-frames detection in different SNRs conditions. The experimental largest target recovery ratio of the proposed algorithm is about 92%, the peak signal-to-noise ratio exceeds 16.4, and the maximum average measure of structural similarity is more than 85% under 500 statistical frames. This paper provides a new processing scheme for GM-APD lidar range image recovery under few-frames detection and low SNR, it lays the foundation for real-time and all-day monitoring.

Noise reduction in speech signal of Parkinson’s Disease (PD) patients using optimal variable stage cascaded adaptive filter configuration

In hands-free communications, including mobile phones, teleconferencing, and video conferencing, the ultimate aim is to obtain a noise-free signal. The adaptive filters that utilize the LMS adaptation algorithm are the best suited for speech signal de-noising among the existing speech signal enhancement techniques. LMS adaptive filter is preferred due to its low computational complexity and robustness, but it fails to simultaneously achieve a faster convergence speed and minimum steady-state MSE. This work introduces a novel cascaded adaptive filter structure for speech signal de-noising wherein the objective is to estimate the noise-free signal with high accuracy. The proposed optimal variable stage cascaded adaptive filter model utilizes a variable stage cascaded adaptive filter structure to estimate the noise-free signal, which is then employed to recover the clean signal with high accuracy. The proposed filter model is tested for reducing the noise from a normal speech signal taken from the NOIZEUS database and an impaired speech signal of Parkinson’s Disease affected patients taken from the MDVR-KCL dataset. The signals are corrupted by various stationary and non-stationary noise signals of different input SNR levels. The noisy signal is used to test the performance of the proposed optimal filter model. The signal de-noising performance of the proposed filter is evaluated in MSE, SNR, and ANR. The results have shown that the proposed filter model provides remarkable performance and an output SNR of 10–15 dB higher than the existing cascaded filter structures. Further, the proposed filter model employs LMS adaptive algorithm, offering a cost-effective and straightforward hardware implementation of ANC with improved accuracy.

EMDS-6: Environmental Microorganism Image Dataset Sixth Version for Image Denoising, Segmentation, Feature Extraction, Classification, and Detection Method Evaluation.

Environmental microorganisms (EMs) are ubiquitous around us and have an important impact on the survival and development of human society. However, the high standards and strict requirements for the preparation of environmental microorganism (EM) data have led to the insufficient of existing related datasets, not to mention the datasets with ground truth (GT) images. This problem seriously affects the progress of related experiments. Therefore, This study develops the Environmental Microorganism Dataset Sixth Version (EMDS-6), which contains 21 types of EMs. Each type of EM contains 40 original and 40 GT images, in total 1680 EM images. In this study, in order to test the effectiveness of EMDS-6. We choose the classic algorithms of image processing methods such as image denoising, image segmentation and object detection. The experimental result shows that EMDS-6 can be used to evaluate the performance of image denoising, image segmentation, image feature extraction, image classification, and object detection methods. EMDS-6 is available at the https://figshare.com/articles/dataset/EMDS6/17125025/1.

Limited parameter denoising for low-dose X-ray computed tomography using deep reinforcement learning.

The use of deep learning has successfully solved several problems in the field of medical imaging. Deep learning has been applied to the CT denoising problem successfully. However, the use of deep learning requires large amounts of data to train deep convolutional networks (CNNs). Moreover, due to the large parameter count, such deep CNNs may cause unexpected results. In this study, we introduce a novel CT denoising framework, which has interpretable behavior and provides useful results with limited data. We employ bilateral filtering in both the projection and volume domains to remove noise. To account for nonstationary noise, we tune the σ parameters of the volume for every projection view and every volume pixel. The tuning is carried out by two deep CNNs. Due to the impracticality of labeling, the two-deep CNNs are trained via a Deep-Q reinforcement learning task. The reward for the task is generated by using a custom reward function represented by a neural network. Our experiments were carried out on abdominal scans for the Mayo Clinic the cancer imaging archive (TCIA) dataset and the American association of physicists in medicine (AAPM) Low Dose CT Grand Challenge. Our denoising framework has excellent denoising performance increasing the peak signal to noise ratio (PSNR) from 28.53 to 28.93 and increasing the structural similarity index (SSIM) from 0.8952 to 0.9204. We outperform several state-of-the-art deep CNNs, which have several orders of magnitude higher number of parameters (p-value [PSNR] = 0.000, p-value [SSIM] = 0.000). Our method does not introduce any blurring, which is introduced by mean squared error (MSE) loss-based methods, or any deep learning artifacts, which are introduced by wasserstein generative adversarial network (WGAN)-based models. Our ablation studies show that parameter tuning and using our reward network results in the best possible results. We present a novel CT denoising framework, which focuses on interpretability to deliver good denoising performance, especially with limited data. Our method outperforms state-of-the-art deep neural networks. Future work will be focused on accelerating our method and generalizing it to different geometries and bodyparts.

Speech Enhancement Using U-Net with Compressed Sensing

With the development of deep learning, speech enhancement based on deep neural networks had made a great breakthrough. The methods based on U-Net structure achieved good denoising performance. However, part of them rely on ordinary convolution operation, which may ignore the contextual information and detailed features of input speech. To solve this issue, many studies have improved model performance by adding additional network modules, such as attention mechanism, long and short-term memory (LSTM), etc. In this work, therefore, a time-domain U-Net speech enhancement model which combines lightweight Shuffle Attention mechanism and compressed sensing loss (CS loss) is proposed. The time-domain dilated residual blocks are constructed and used for down-sampling and up-sampling in this model. The Shuffle Attention is added to the final output of the encoder for focusing on features of speech and suppressing irrelevant audio information. A new loss is defined by using the measurements of clean speech and enhanced speech based on compressed sensing, it can further remove noise in noisy speech. In the experimental part, the influence of different loss functions on model performance is proved through ablation experiments, and the effectiveness of CS loss is verified. Compared with the reference models, the proposed model can obtain higher speech quality and intelligibility scores with fewer parameters. When dealing with the noise outside the dataset, the proposed model still achieves good denoising performance, which proves that the proposed model can not only achieve a good enhancement effect, but also has good generalization ability.

NHNet: A non‐local hierarchical network for image denoising

With the fast development of deep learning models, hierarchical convolutional neural networks have achieved great success in image denoising tasks. To further boost the performance of image denoising, a novel non-local hierarchical network (NHNet) is proposed. Unlike existing U-Net-based hierarchical methods, which mainly focus on downsampling operations, NHNet adopts an initial resolution path and a high resolution path. Specifically, the high-resolution features are obtained through upsampling, where the non-local mechanism is adopted to capture the self-similarity properties, which contribute to a better denoising performance. Cross connections and channel attention layers are added between the two paths to integrate features in different resolutions. Compared with other U-Net-based hierarchical networks, NHNet requires fewer parameters. Experiments show that NHNet achieves state-of-the-art performance in Gaussian denoising tasks and gets competitive results when dealing with real image denoising.

A Hybrid CNN for Image Denoising

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

Hyperspectral Image Denoising via Adversarial Learning

Due to sensor instability and atmospheric interference, hyperspectral images (HSIs) often suffer from different kinds of noise which degrade the performance of downstream tasks. Therefore, HSI denoising has become an essential part of HSI preprocessing. Traditional methods tend to tackle one specific type of noise and remove it iteratively, resulting in drawbacks including inefficiency when dealing with mixed noise. Most recently, deep neural network-based models, especially generative adversarial networks, have demonstrated promising performance in generic image denoising. However, in contrast to generic RGB images, HSIs often possess abundant spectral information; thus, it is non-trivial to design a denoising network to effectively explore both spatial and spectral characteristics simultaneously. To address the above issues, in this paper, we propose an end-to-end HSI denoising model via adversarial learning. More specifically, to capture the subtle noise distribution from both spatial and spectral dimensions, we designed a Residual Spatial-Spectral Module (RSSM) and embed it in an UNet-like structure as the generator to obtain clean images. To distinguish the real image from the generated one, we designed a discriminator based on the Multiscale Feature Fusion Module (MFFM) to further improve the quality of the denoising results. The generator was trained with joint loss functions, including reconstruction loss, structural loss and adversarial loss. Moreover, considering the lack of publicly available training data for the HSI denoising task, we collected an additional benchmark dataset denoted as the Shandong Feicheng Denoising (SFD) dataset. We evaluated five types of mixed noise across several datasets in comparative experiments, and comprehensive experimental results on both simulated and real data demonstrate that the proposed model achieves competitive results against state-of-the-art methods. For ablation studies, we investigated the structure of the generator as well as the training process with joint losses and different amounts of training data, further validating the rationality and effectiveness of the proposed method.

DSRD: deep sparse representation with learnable dictionary for remotely sensed image denoising

ABSTRACT Patch-based modelling methods (i.e. sparse coding) had proven their great ability in solving the degradation problem caused by additive white Gaussian noise (AWGN) in remotely sensing images. However, these methods usually pursue surprising performance with sacrificing computational efficiency, and the learned dictionary is universal, resulting in a weak model representation flexibility. To address these issues, this paper proposes a deep sparse representation with learnable dictionary (DSRD) scheme, where the major difference from the previous sparse coding methods is that sparse representation coefficients and dictionaries are both deeply learned, acted as two modular parts to be plugged into the unfolded sparse coding model, to speed up for a stable solution as well as yielding competitive performance. The ablation studies illustrate that our DSRD strategy is efficient for a fixed solution while a flexible and powerful capacity in producing pleasing denoising performance. Meanwhile, the comparisons of quantitatively and qualitatively experimental results further demonstrate that it is effective and can generate enjoyable denoising performance that even outperforms that produced by other state-of-the-arts.

Cross-Channel Dynamic Weighting RPCA: A De-Noising Algorithm for Multi-Channel Arterial Pulse Signal

Pulse wave analysis (PWA) has been widely used in the medical field. A novel multi-channel sensor is employed in arterial pulse acquisition and brings richer physiological information to PWA. However, the noise of this sensor is distributed in the main frequency band of the pulse signal, which seriously interferes with subsequent analyses and is difficult to eliminate by existing methods. This study proposes a cross-channel dynamic weighting robust principal component analysis algorithm. A channel-scaled factor technique is used to manipulate the weighting factors in the nuclear norm. This factor can adaptively adjust the weights among the channels according to the signal pattern of each channel, optimizing the feature extraction in multi-channel signals. A series of performance evaluations were conducted, and four well-known de-noising algorithms were used for comparison. The results reveal that the proposed algorithm achieved one of the best de-noising performances in the time and frequency domains. The mean of h1 in the amplitude relative error (ARE) was 23.4% smaller than for the WRPCA algorithm. Moreover, our algorithm could accelerate convergence and reduce the computational time complexity by approximately 34.6%. These results demonstrate the performance and efficiency of the algorithm. Meanwhile, the idea can be extended to other multi-channel physiological signal de-noising and feature extraction fields.

An Adaptive Self-Organizing Migration Algorithm for Parameter Optimization of Wavelet Transformation

Wavelet transformation is well applied in the field of image processing, and parameter optimization of wavelet transformation has always been an eternal topic on its performance improvement. In this paper, an adaptive self-organizing migration algorithm (ASOMA) is proposed to optimize the wavelet parameters to elevate the performance of wavelet denoising. Firstly, based on the original SOMA, an adaptive step size adjustment method is proposed by recording the step information of successful individuals, which improves the search ability of the SOMA. Secondly, an exploratory selection method of leader is proposed to effectively balance the exploration and exploitation of the SOMA. Finally, ASOMA is compared with the original SOMA and its variants using wavelet general threshold denoising on classical test images in denoising performance, which is evaluated by the indicators of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The experimental results demonstrate that ASOMA has better denoising performance than the wavelet general threshold, the original SOMA, and the related variants of SOMA.

Single Circuit in V1 Capable of Switching Contexts During Movement Using an Inhibitory Population as a Switch.

As animals adapt to their environments, their brains are tasked with processing stimuli in different sensory contexts. Whether these computations are context dependent or independent, they are all implemented in the same neural tissue. A crucial question is what neural architectures can respond flexibly to a range of stimulus conditions and switch between them. This is a particular case of flexible architecture that permits multiple related computations within a single circuit. Here, we address this question in the specific case of the visual system circuitry, focusing on context integration, defined as the integration of feedforward and surround information across visual space. We show that a biologically inspired microcircuit with multiple inhibitory cell types can switch between visual processing of the static context and the moving context. In our model, the VIP population acts as the switch and modulates the visual circuit through a disinhibitory motif. Moreover, the VIP population is efficient, requiring only a relatively small number of neurons to switch contexts. This circuit eliminates noise in videos by using appropriate lateral connections for contextual spatiotemporal surround modulation, having superior denoising performance compared to circuits where only one context is learned. Our findings shed light on a minimally complex architecture that is capable of switching between two naturalistic contexts using few switching units.

Ultrasound image denoising using generative adversarial networks with residual dense connectivity and weighted joint loss.

BackgroundUltrasound imaging has been recognized as a powerful tool in clinical diagnosis. Nonetheless, the presence of speckle noise degrades the signal-to-noise of ultrasound images. Various denoising algorithms cannot fully reduce speckle noise and retain image features well for ultrasound imaging. The application of deep learning in ultrasound image denoising has attracted more and more attention in recent years.MethodsIn the article, we propose a generative adversarial network with residual dense connectivity and weighted joint loss (GAN-RW) to avoid the limitations of traditional image denoising algorithms and surpass the most advanced performance of ultrasound image denoising. The denoising network is based on U-Net architecture which includes four encoder and four decoder modules. Each of the encoder and decoder modules is replaced with residual dense connectivity and BN to remove speckle noise. The discriminator network applies a series of convolutional layers to identify differences between the translated images and the desired modality. In the training processes, we introduce a joint loss function consisting of a weighted sum of the L1 loss function, binary cross-entropy with a logit loss function and perceptual loss function.ResultsWe split the experiments into two parts. First, experiments were performed on Berkeley segmentation (BSD68) datasets corrupted by a simulated speckle. Compared with the eight existing denoising algorithms, the GAN-RW achieved the most advanced despeckling performance in terms of the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and subjective visual effect. When the noise level was 15, the average value of the GAN-RW increased by approximately 3.58% and 1.23% for PSNR and SSIM, respectively. When the noise level was 25, the average value of the GAN-RW increased by approximately 3.08% and 1.84% for PSNR and SSIM, respectively. When the noise level was 50, the average value of the GAN-RW increased by approximately 1.32% and 1.98% for PSNR and SSIM, respectively. Secondly, experiments were performed on the ultrasound images of lymph nodes, the foetal head, and the brachial plexus. The proposed method shows higher subjective visual effect when verifying on the ultrasound images. In the end, through statistical analysis, the GAN-RW achieved the highest mean rank in the Friedman test.

Low illumination image enhancement based on multi-scale CycleGAN with deep residual shrinkage

Low-illumination image restoration has been widely used in many fields. Aiming at the problem of low resolution and noise amplification in low light environment, this paper applies style transfer of CycleGAN(Cycle-Consistent Generative Adversarial Networks) to low illumination image enhancement. In the design network structure, different convolution kernels are used to extract the features from three paths, and the deep residual shrinkage network is designed to suppress the noise after convolution. The color deviation of the image can be resolved by the identity loss of CycleGAN. In the discriminator, different convolution kernels are used to extract image features from two paths. Compared with the training and testing results of Deep-Retinex network, GLAD network, KinD and other network methods on LOL-dataset and Brightening dataset, CycleGAN based on multi-scale depth residuals contraction proposed in this experiment on LOL-dataset results image quality evaluation indicators PSNR = 24.62, NIQE = 4.9856, SSIM = 0.8628, PSNR = 27.85, NIQE = 4.7652, SSIM = 0.8753. From the visual effect and objective index, it is proved that CycleGAN based on multi-scale depth residual shrinkage has excellent performance in low illumination enhancement, detail recovery and denoising.

Seismic random noise suppression by using deep residual U-Net

Pre-stack seismic denoising is one of most important processing steps in seismic exploration, which can significantly enhance the signal-to-noise ratio (SNR) and resolution of real seismic data. Seismic random noise often presents some complicated characteristics (non-gaussian, non-stationary, non-linear) and may overlap with desired signals in frequency domain. Thus, we need to explore the corresponding approach to attenuate the unwanted random noise and simultaneously recover the signals. Recently, some methods based on convolutional neural network (CNN) have shown excellent performance in seismic data denoising. These CNN-based denoising methods can learn the potential features of labeled data, thereby establishing the mapping relationship between noisy seismic data and signals. However, these existing CNN-based methods only consider the single-scale potential features and neglect some useful multiscale features, leading to their performance degradation when processing some seismic data with low SNR. In view of above drawback, we propose a novel CNN by introducing the residual theory and reconstruction block into the conventional U-Net, called deep residual U-Net (DRUN). In DRUN, some residual blocks are utilized to obtain the multiscale features of noisy seismic data and the followed reconstruction block can incorporate features of different scales, thereby distinguishing signals and random noise. Both the synthetic and field seismic data are processed to verify the effectiveness of DRUN. Compared with the original U-Net, the experimental results demonstrate that the proposed DRUN has superiority in noise attenuation and signal preservation.

GPR image denoising with NSST-UNET and an improved BM3D

To suppress random noise while preserving effective information in the edge areas of ground penetrating radar (GPR) images, this paper proposes a novel denoising method by making use of a deep neural network called NSST-UNET and an improved BM3D. At first, NSST-UNET is designed with a non-subsampled shearlet transform (NSST) coding layer and a skip connection based on a multi-scale convolution module and applied to identify the edge and smooth areas of noisy GPR images. Then, the denoising is accomplished with the improved BM3D in two steps. In the first step, a larger search range for similar blocks and a soft threshold are used to denoise the edge and smooth areas, respectively. In the second step, the Wiener filter optimized by mean square error and the Wiener filter optimized by structural similarity are utilized to denoise the smooth and unsmooth areas, respectively. Finally, the excellent denoising performance of the proposed method is verified by qualitative and quantitative analysis with simulation and field exploration data.