Approach For Noise Removal Research Articles

A hybrid unsupervised learning approach for noise removal in particle image velocimetry

A hybrid unsupervised learning approach for noise removal in particle image velocimetry

Unsupervised Denoising in Spectral CT: Multi-Dimensional U-Net for Energy Channel Regularisation

Spectral Computed Tomography (CT) is a versatile imaging technique widely utilized in industry, medicine, and scientific research. This technique allows us to observe the energy-dependent X-ray attenuation throughout an object by using Photon Counting Detector (PCD) technology. However, a major drawback of spectral CT is the increase in noise due to a lower achievable photon count when using more energy channels. This challenge often complicates quantitative material identification, which is a major application of the technology. In this study, we investigate the Noise2Inverse image denoising approach for noise removal in spectral computed tomography. Our unsupervised deep learning-based model uses a multi-dimensional U-Net paired with a block-based training approach modified for additional energy-channel regularization. We conducted experiments using two simulated spectral CT phantoms, each with a unique shape and material composition, and a real scan of a biological sample containing a characteristic K-edge. orangeMeasuring the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) for the simulated data and the contrast-to-noise ratio (CNR) for the real-world data, our approach not only outperforms previously used methods—namely the unsupervised Low2High method and the total variation-constrained iterative reconstruction method—but also does not require complex parameter tuning.

Adaptive Bayesian speckle reduction in the 2D DOST domain using 2D MC-GARCH-M model: Preserving image edges and textural information

Image denoising and image quality enhancement are major issues in image processing. Additive and multiplicative noise removal is one of the main image enhancement approaches. In this paper, we propose a novel 2D Merged Complex Generalized Autoregressive Conditional Heteroscedasticity Mixture (MC-GARCH-M) model for 2D complex stochastic processes. This model effectively captures non-Gaussian statistics and all three types of dependencies within the processes (RRD, IID, and RID) using the proposed linear mapping transformation T. Our statistical analysis shows that the 2D MC-GARCH-M model provides the best fit to the non-Gaussian statistics of the mapped matrix of 2D DOST coefficients compared to Gaussian, Generalized Gaussian, and Stable distributions. We confirm the presence of heteroscedasticity in the mapped matrix using the Engle hypothesis test, verifying ARCH/GARCH effects. The 2D MC-GARCH-M model, with its location-dependent conditional variances, provides a flexible approach for noise removal and modeling complex stochastic processes. Experimental results on artificially speckled aerial and actual SAR images demonstrate that our method outperforms state-of-the-art approaches in terms of speckle removal and preserving the edges and textural information of the image. Key innovations include: a new statistical analysis using linear mapping T showing non-Gaussian heavy-tailed distributions; an adaptive Bayesian estimator, MCMAP, based on the heteroscedastic model for speckle noise removal; and the method's applicability to images with varying mutual information (MI) between real and imaginary parts of 2D DOST coefficients. Our method is adaptive and robust to initial parameter settings, effectively utilizing magnitude and phase information, providing an optimal closed-form solution, reducing memory and computational requirements, and demonstrating robustness to speckle power levels. While requiring more computational resources compared to thresholding methods, our approach is less demanding than other Bayesian algorithms, making it suitable for offline processing.

Hyperspectral Image Mixed Noise Removal via Double Factor Total Variation Nonlocal Low-Rank Tensor Regularization

A hyperspectral image (HSI) is often corrupted by various types of noise during image acquisition, e.g., Gaussian noise, impulse noise, stripes, deadlines, and more. Thus, as a preprocessing step, HSI denoising plays a vital role in many subsequent tasks. Recently, a variety of mixed noise removal approaches have been developed for HSI, and the methods based on spatial–spectral double factor and total variation (DFTV) regularization have achieved comparable performance. Additionally, the nonlocal low-rank tensor model (NLR) is often employed to characterize spatial nonlocal self-similarity (NSS). Generally, fully exploring prior knowledge can improve the denoising performance, but it significantly increases the computational cost when the NSS prior is employed. To solve this problem, this article proposes a novel DFTV-based NLR regularization (DFTVNLR) model for HSI mixed noise removal. The proposed model employs low-rank tensor factorization (LRTF) to characterize the spectral global low-rankness (LR), introduces 2-D and 1-D TV constraints on double-factor to characterize the spatial and spectral local smoothness (LS), respectively. Meanwhile, the NLR is applied to the spatial factor to characterize the NSS. Then, we developed an algorithm based on proximal alternating minimization (PAM) to solve the proposed model effectively. Particularly, we effectively controlled the computational cost from two aspects, namely taking small-sized double factor as regularization object and putting the time-consuming NLR model before the main loop with fewer iterations to solve it independently. Finally, considerable experiments on simulated and real noisy HSI substantiate that the proposed method is superior to the related state-of-the-art methods in balancing the denoising effect and speed.

Combined Unet and CNN image classification model for COVID disease detection using CXR/CT imaging

Accurate SARS-CoV-2 screening is made possible by automated Computer-Aided Diagnosis (CAD) which reduces the stress on healthcare systems. Since Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) is highly contagious, the transition chain can be broken through an early diagnosis by clinical knowledge and Artificial Intelligence (AI). Manual findings are time and labor-intensive. Even if Reverse Transcription-Polymerase Chain Reaction (RT-PCR) delivers quick findings, Chest X-ray (CXR) imaging is still a more trustworthy tool for disease classification and assessment. Several studies have been conducted using Deep Learning (DL) algorithms for COVID-19 detection. One of the biggest challenges in modernizing healthcare is extracting useful data from high-dimensional, heterogeneous, and complex biological data. Intending to introduce an automated COVID-19 diagnosis model, this paper develops a proficient optimization model that enhances the classification performance with better accuracy. The input images are initially pre-processed with an image filtering approach for noise removal and data augmentation to extend the dataset. Secondly, the images are segmented via U-Net and are given to classification using the Fused U-Net Convolutional Neural Network (FUCNN) model. Here, the performance of U-Net is enhanced through the modified Moth Flame Optimization (MFO) algorithm named Chaotic System-based MFO (CSMFO) by optimizing the weights of U-Net. The significance of the implemented model is confirmed over a comparative evaluation with the state-of-the-art models. Specifically, the proposed CSMFO-FUCNN attained 98.45% of accuracy, 98.63% of sensitivity, 98.98% of specificity, and 98.98% of precision.

Effective hybridization approach for noise removal in magnetic resonance imaging

Effective hybridization approach for noise removal in magnetic resonance imaging

Improving electrocardiography signal quality: introducing an efficient approach for noise removal

Improving electrocardiography signal quality: introducing an efficient approach for noise removal

A Neighborhood Impact Driven K-Medoid Clustering and Fuzzy Logic Blended Approach for High Density Impulse Noise Detection and Removal

In the field of image processing, removing impulse noise has been regarded as one of the most important tasks, primarily because of the noise pattern it presents. Existing filters used the effect of only those non-noisy pixels which were present inside the specified windows ignoring the effect of the non-noisy pixels present in the surrounding windows. So, the least distant non-noisy pixels in the present window as well as in the surrounding windows may have an influence on the present window's noisy pixels. Hence, considering the above factors, in this paper, a two-step technique named KMDCIFF (K-medoid clustering identified fuzzy filter) is proposed for removing impulse noise from digital images. In the proposed KMDCIFF algorithm, the first step is noise detection using K-medoid clustering, followed by a fuzzy logic-acquainted noise reduction strategy that utilizes the least distant local and non-local non-noisy pixels for removal operation. The detection process involves the application of K-medoid clustering on all 5×5 windows produced by centering each pixel of the considered image. In order to remove noise, a 7×7 window is constructed with each detected noisy pixel in the center. Analyzing the impact of the least distant local and non-local pixel on each noisy pixel, the same is replaced by an estimated pixel’s intensity value obtained from the most influential non-noisy pixels. KMDCIFF is evaluated using well-known metrics for diverse types of images. At a high noise density of 80%, KMDCIFF exhibited significant peak-signal-to-noise-ratios (PSNRs) of 26.97 dB and 29.67 dB and structural similarity indexes (SSIMs) of 0.8045 and 0.9288 on random and fixed valued impulse noise impacted Lena image, respectively. Comparing the results of the contemporary study to those of previous studies of a similar kind in this sector, the results are unswervingly astounding.

Phenological heterogeneities of invasive Spartina alterniflora salt marshes revealed by high-spatial-resolution satellite imagery

The rapid expansion of invasive Spartina alterniflora in China’s coastal wetlands has seriously threatened regional ecosystem health. Characterizing phenology of S. alterniflora salt marshes supports the studies on plant invasion mechanism and carbon fluxes in coastal wetlands. To date, little is known about the capacity of high-spatial-resolution imagery in revealing local scale heterogeneities and temporal variations in the phenology; in addition, the driving factors of such heterogeneities are not well understood. This study took Yellow River Estuary (YRE) as the study site where S. alterniflora area has expanded since 2008. We retrieved start of season (SOS), end of season (EOS), length of growing season (LOS), and maximum Normalized Difference Vegetation Index (NDVImax) from time series Sentinel-2 imagery (10-meter resolution) during 2017 ∼ 2019 with assist of a rule-based data noise removal approach. Results showed that phenological metrics differ with invasion years. The differences in the median NDVImax reached 0.13, in the median SOS reached 26 days, and in the median LOS reached 51 days. S. alterniflora with 5-year invasion had the highest NDVImax, and younger S. alterniflora marshes had earlier SOS and longer LOS. Both SOS and EOS showed negative relationships with NDVImax, indicating the marshes with greater green vegetation cover had earlier SOS and EOS. More spatial details can be revealed from higher-resolution PlanetScope imagery (3-meter resolution), showing the influence of tidal creeks on phenology. The spatial heterogeneity in phenology was associated with environmental factors such as tidal inundation, elevation, micro-climate, nutrients, and canopy structure. S. alterniflora showed markedly higher NDVImax and earlier EOS in 2018 compared to 2017 and 2019, associated with larger river water discharge and sediment load brought by Water Sediment Regulation Scheme, greater precipitation in the wettest season and lower preseason temperature in 2018. Large phenological variations at both spatial and temporal scales suggest that S. alterniflora marshes are sensitive to the local environment and climate change. This study has the potential to provide references for the management of invasive plants threatening coastal wetlands in the world.

Modified metaheuristics with stacked sparse denoising autoencoder model for cervical cancer classification

Cervical cancer is the most commonly diagnosed cancer among women globally, with high mortality rate. For early diagnosis, automated and accurate cervical cancer classification approaches can be developed through effective classification of Pap smear cell images. The current study introduces a novel Modified Firefly Optimization Algorithm with Deep Learning-enabled cervical cancer classification (MFFOA-DL3) model for the classification of Pap Smear Images (PSI). The proposed MFFOA-DL3 model examines the PSI for the existence of cervical cancer cells. To accomplish this, the proposed MFFOA-DL3 model primarily applies Bilateral Filtering (BF)-based noise removal approach to get rid of the noise. Then, Kapur's entropy-based image segmentation technique is applied to determine the affected regions. Moreover, EfficientNet technique is also applied to generate the feature vectors. Finally, MFFOA with Stacked Sparse Denoising Autoencoder (SSDA) model is exploited to classify the PSI. In current study, MFFOA is utilized to appropriately modify the parameters related to SSDA model. The proposed MFFOA-DL3 model was experimentally validated using benchmark dataset. The results attained from extensive comparative analysis highlighted the better performance of MFFOA-DL3 model over other recent approaches.

Internal quality assessment of mango fruit: an automated grading system with ensemble classifier

ABSTRACT In this work, a non-destructive and automated mango grading system model is developed for grading the mangoes into three categories depending on their internal features like Soluble Solid Content (SSC) as well as Total Acid Content (TAC). Initially, the prepared database is de-noised with the proposed adaptive Gaussian noise removal approach. Then, the Gray Level Co Occurrence Matrix (GLCM), Gray Level Run-Length Matrix (GLRM) features, and Near Infrared (NIR) spectroscopy features were extracted. As the curse of dimensionality persists, a patch-based Principal Component Analysis (PCA) model for dimensionality reduction is introduced. Subsequently, the dimensional reduced features are subjected to aproposed ensemble classifier that encompasses: ‘Support Vector Machine (SVM), Random Forest (RF), three Artificial Neural Network (ANN), and K-Nearest Neighbor (KNN)’. The weight of the third ANN is optimally-tuned by a novel improved meta-heuristic model depicting the Lion-Binary crossover mask base Whale Optimization (LBWO) Algorithm.

Automated Recognition of Cancer Tissues through Deep Learning Framework from the Photoacoustic Specimen

The fast advancement of biomedical research technology has expanded and enhanced the spectrum of diagnostic instruments. Various research groups have found optical imaging, ultrasonic imaging, and magnetic resonance imaging to create multifunctional devices that are critical for biomedical activities. Multispectral photoacoustic imaging that integrates the ideas of optical and ultrasonic technologies is one of the most essential instruments. At the same time, early cancer identification is becoming increasingly important in order to minimize fatality. Deep learning (DL) techniques have recently advanced to the point where they can be used to diagnose and classify cancer using biological images. This paper describes a hybrid optimization method that combines in-depth transfer learning-based cancer detection with multispectral photoacoustic imaging. The goal of the PS-ACO-RNN approach is to use ultrasound images to detect and classify the presence of cancer. Bilateral filtration (BF) is often used as a noise removal approach in image processing. In addition, lightweight LEDNet models are used to separate the biological images. A feature extractor with particle swarm with ant colony optimization (PS-ACO) paradigm can also be used. Finally, biological images assign appropriate class labels using a recurrent neural network (RNN) model. The effectiveness of the PS-ACO-RNN technique is verified using a benchmark database, and test results show that the PS-ACO-RNN approach works better than current approaches.

An Adaptive ECG Noise Removal Process Based on Empirical Mode Decomposition (EMD).

The electrocardiogram (ECG) is a generally used instrument for examining cardiac disorders. For proper interpretation of cardiac illnesses, a noise-free ECG is often preferred. ECG signals, on the other hand, are suffering from numerous noises throughout gathering and programme. This article suggests an empirical mode decomposition-based adaptive ECG noise removal technique (EMD). The benefits of the proposed methods are used to dip noise in ECG signals with the least amount of distortion. For decreasing high-frequency noises, traditional EMD-based approaches either cast off the preliminary fundamental functions or use a window-based methodology. The signal quality is then improved via an adaptive process. The simulation study uses ECG data from the universal MIT-BIH database as well as the Brno University of Technology ECG Quality Database (BUT QDB). The proposed method's efficiency is measured using three typical evaluation metrics: mean square error, output SNR change, and ratio root mean square alteration at various SNR levels (signal to noise ratio). The suggested noise removal approach is compatible with other commonly used ECG noise removal techniques. A detailed examination reveals that the proposed method could be served as an effective means of noise removal ECG signals, resulting in enhanced diagnostic functions in automated medical systems.

Nonlocal low-rank regularized two-phase approach for mixed noise removal

Removing mixed noise in images is a difficult problem which has been discussed in many recent papers. In this paper, we tackle the problem of having mixed additive Gaussian white noise and impulse noise. We propose to remove this mixed noise through a nonlocal low-rank regularized two-phase approach. In the first phase, we identify and label the pixels that are likely to be corrupted by the impulse noise. In the second phase, the image is restored through the unlabeled observed data. The restored image is achieved via solving an optimization problem whose objective function has an ℓ 1/ℓ 2 combined content-dependent fidelity term and a nonconvex nonlocal low-rank regularization term. Both terms are built on patch matrices formed from similar patches. Each patch matrix is considered to be low-rank according to the prior knowledge of images. We solve this nonconvex optimization through an iterative adaptive nuclear norm minimization algorithm and provide its convergence analysis. Our experiments show the proposed method outperforms the existing state-of-the-art algorithms in terms of three quantitative metrics, namely, the peak signal-to-noise ratio, the structural similarity and the feature similarity, and visual quality of the restored images.

Noise Cancellation in Computed Tomography Images through Adaptive Multi-Stage Noise Removal Paradigm

Image de-noising is a noise removal approach, which is utilized to remove noise from the noisy image and is utilized to protect the significant features of images namely, corners, edges, textures, and sharp structures. For medical diagnosis Computer tomography (CT) images are mainly utilized. Due to acquisition and transmission in CT imaging, the noise that appears leads to poor image quality. To overcome this problem, an efficient Noise cancellation in computed tomography images using adaptive multi-stage noise removal paradigm is proposed. The proposed approach consists of three phases namely, Optimal Discrete Wavelet Transform, first stage noise removal using Block Matching, and 3D filtering (BM3D) filter and second stage noise removal using the bilateral filter (BF). Initially, Discrete Wavelet Transform (DWT) is applied to the input image to diminish noise in CT images. In this method, co-efficient ranges are optimally selected with the help of Crow Search Optimization (CSO) algorithm. Secondly, to remove the noise present in the bands, BM3D algorithm is applied. Finally, bilateral filter is applied to the BM3D output image to further enhance the image. The performance of the proposed methodology is analyzed in terms of Peak signal-to-noise ratio (PSNR), Root Mean Square Error (RMSE), and Structural Similarity Index (SSIM). Furthermore, the multi-stage noise removal model obtained gives the best PSNR values compared to other techniques.

A new approach for Cauchy noise removal

<abstract> In this paper, a new total generalized variational (TGV) model for restoring images with Cauchy noise is proposed, which contains a non-convex fidelity term and a TGV regularization term. In order to obtain a strictly convex model, we add an appropriate proximal term to the non-convex fidelity term. We prove that the solution of the proposed model exists and is unique. Due to the convexity of the proposed model and in order to get a convergent algorithm, we employ an alternating minimization algorithm to solve the proposed model. Finally, we demonstrate the performance of our scheme by numerical examples. Numerical results demonstrate that the proposed algorithm significantly outperforms some previous methods for Cauchy noise removal. </abstract>

On Postprocessing Reduction of Phase Noise in FMCW Radars

Detection using continuous wave (CW) is inherently prone to undesired fluctuations in the phase of the transmitted (Tx) wave and hence is highly vulnerable to phase noise (PN). Along with hardware-based solutions, there are several software-based techniques to alleviate the PN in frequency-modulated CW (FMCW) detection systems. These methods generally employ a parallel transmit/receive channel, using a delay-line, to instantaneously extract the PN of the Tx wave and next, they propose a PN removal method to eliminate its impacts on the received FMCW beat signal. In this article, we introduce a general noise removal approach based on determination and resolution of the PN inverse problem. Thereafter, we propose a method to adapt this approach to the FMCW PN problem. Subsequently, a systematic comparison between the existing methods and the introduced one is made. It is pointed out that the inverse method does not rely on short-range (SR) approximations and therefore, its applicability is extendable to medium-range (MR) and long-range (LR) radars. At the end, the capability of the proposed approach compared with the existing ones-which are mainly based on SR approximations-is assessed in a field experiment.

Performance Analysis of Noise Removal Techniques For Digital Images

Noise has impairment effect on image so it destroys its information. In order to overcome this problem, it is necessary to remove noise before extracting information and image processing as one of the preprocessing steps. A brief overview of various sources and types of image noise as well as noise removal technique of digital images has been produced in this paper. The general idea of this paper is to perform segmentation of the corrupted image before using noise removal filter. Noise removal filter has been used to eliminate noise for each segment of image individually after segmentation process. Then comparative study between noise removal filtering for whole image and segmentation based method has been produced with performance analysis in terms of MSE and PSNR. In this paper, MSE and PSNR are calculated for the resultant reconstructed image compared with the original image. Six image samples are used to test the Segmentation based noise removal approach. The segmentation based technique has shown best results in terms of MSE and PSNR in comparison with traditional noise removal method based filter. Simulation result show that MSE is less and PSNR is high using segmentation based noise removal method especially for image which has more details, so it superior performance as compared to the traditional method.

Efficient Denoising by Feature Recovery from Residual Noise in Spatial Domain

The growth of image processing techniques has lead to limitless applications of imaging in various fields of medical, remote sensing. However, the unpreventable problem of noise contamination arises during the processing of images. As the noise content in an image rises, it becomes difficult to denoise an image while preserving high-frequency edge features as well as low frequency smooth features. Minimal artefacts and better preservation of geometrical details such as edges and texture reflects efficient image reconstruction. Since many State-of-the-art denoising algorithms have been reported in the literature, and there is always a compromise between noise removal and feature preservation. A novel approach for efficient noise removal along with recovery of fine features is being proposed. The idea behind denoising approach is the use of hybridization of spatial domain filters where base layer image and residual image are extracted and processed separately to mitigate the prevalence of artefacts and preserve image content. The performance of the proposed method is evaluated both quantitatively as well as qualitatively, and it is found that the proposed method could outperform existing denoising techniques.

Impulse noise removal by an adaptive trust-region method

This paper suggests a two-phase scheme for the impulse noise removal. In the first phase, an adaptive median filter (AMF) identifies noise candidates created by salt-and-pepper method. In the second phase, a new trust-region phase recovers noise pixels detected by the first phase. The trust-region phase produces a new adaptive radius strategy using the projected gradient for the cases where iterations are successful and a low-memory nonmonotone spectral projected gradient method (SPG) where iterations are unsuccessful. We solve the trust-region subproblem without bound constraints by the dogleg strategy (DG) using the structure of the compact limited memory Broyden–Fletcher–Goldfarb–Shanno technique. The solution is then projected into the boundary region. Numerical results are given to illustrate the efficiency of the new approach for the impulse noise removal.