Image Noise Removal Research Articles

Edge Detection of COVID-19 CT Image Based on GF_SSR, Improved Multiscale Morphology, and Adaptive Threshold

Edge detection is an effective method for image segmentation and feature extraction. Therefore, extracting weak edges with the inhomogeneous gray of Corona Virus Disease 2019 (COVID-19) CT images is extremely important. Multiscale morphology has been widely used in the edge detection of medical images due to its excellent boundary detection accuracy. In this paper, we propose a weak edge detection method based on Gaussian filtering and singlescale Retinex (GF_SSR), and improved multiscale morphology and adaptive threshold binarization (IMSM_ATB). As all the CT images have noise, we propose to remove image noise by Gaussian filtering. The edge of CT images is enhanced using the SSR algorithm. In addition, based on the extracted edge of CT images using improved Multiscale morphology, a particle swarm optimization (PSO) algorithm is introduced to binarize the image by automatically getting the optimal threshold. To evaluate our method, we use images from three datasets, namely COVID-19, Kaggle-COVID-19, and COVID-Chestxray, respectively. The average values of results are worthy of reference, with the Shannon information entropy of 1.8539, the Precision of 0.9992, the Recall of 0.8224, the F-Score of 1.9158, running time of 11.3000. Finally, three types of lesion images in the COVID-19 dataset are selected to evaluate the visual effects of the proposed algorithm. Compared with the other four algorithms, the proposed algorithm effectively detects the weak edge of the lesion and provides help for image segmentation and feature extraction.

Image Noise Removal Method Based on Thresholding and Regularization Techniques

In this article, a salt and pepper noise (SPN) removal method is proposed based on thresholding and regularization techniques. The proposed method utilizes the ability to remove noise from an image denoising model based on Total Variation (TV) regularization and characteristics of SPN. First, a technique based on the characteristic of SPN is proposed to detect noisy pixels. Second, a modified TV regularization-based method is applied to restore the above noisy pixels. In addition, numerical implementation of the model based on the Nesterov optimal method is also provided. Five test cases with various noise levels for a large natural image dataset were studied in the experiments. The peak signal-to-noise ratio and structural similarity metrics were employed to assess the image quality after denoising. The experimental results indicated that the proposed method removes SPN remarkably and outperforms state-of-the-art image denoising methods for SPN.

Framelet transform and fuzzy clustering-based intelligent technique for speckle noise removal in ultrasound images

Purpose Speckle noise removal in ultrasound images is one of the important tasks in biomedical-imaging applications. Many filtering -based despeckling methods are discussed in many existing works. Two-dimensional (2-D) transforms are also used enormously for the reduction of speckle noise in ultrasound medical images. In recent years, many soft computing-based intelligent techniques have been applied to noise removal and segmentation techniques. However, there is a requirement to improve the accuracy of despeckling using hybrid approaches. Design/methodology/approach The work focuses on double-bank anatomy with framelet transform combined with Gaussian filter (GF) and also consists of a fuzzy kind of clustering approach for despeckling ultrasound medical images. The presented transform efficiently rejects the speckle noise based on the gray scale relative thresholding where the directional filter group (DFB) preserves the edge information. Findings The proposed approach is evaluated by different performance indicators such as the mean square error (MSE), peak signal to noise ratio (PSNR) speckle suppression index (SSI), mean structural similarity and the edge preservation index (EPI) accordingly. It is found that the proposed methodology is superior in terms of all the above performance indicators. Originality/value Fuzzy kind clustering methods have been proved to be better than the conventional threshold methods for noise dismissal. The algorithm gives a reconcilable development as compared to other modern speckle reduction procedures, as it preserves the geometric features even after the noise dismissal.

Experimental evaluation of filters used for removing speckle noise and enhancing ultrasound image quality

In the modern-days diagnostics, ultrasound is considered a significant non-invasive imaging technique. However, ultrasound images are frequently contaminated by multiplicative speckle noise. Speckle noise is produced by constructive and destructive interference between ultrasound waves when the object being measured is smaller than the wavelength of the beam. The removal of speckle noise in ultrasound images is possible by using various filters. The current experimental study is aimed at finding the most suitable de-speckling filters for enhancing ultrasound images. The present study involves 102-abdomen ultrasound images degraded by speckle noise and the analysis of eight de-speckling filters (i.e., Mean, Median, Kuan, Lee, Frost, Adaptive Homomorphic, Wiener and Anisotropic Diffusion) is developed to find the optimum de-speckling filter. The results of the given filters are analyzed using the five quality metrics (i.e., PSNR, RMSE, SSI, STM, and SSIM). The metrics are further investigated by using the statistical tests (i.e., one-way ANOVA and Tukey’s post hoc test) to support the experimental evaluation. Simulation results showed that the Frost and adaptive Homomorphic filters work well for the ultrasound images degraded with higher value of speckle noise. From the proposed research, it is easy to select the optimal filter, which helps doctors to get fine details of the image.

A Novel Disease Detection and Classification Method Using Improved Fusion Random Weight Support Vector Machine

Health informatics is one of the main branch of engineering which provides a solution to a variety of problems like delayed, missed or incorrect diagnoses with the help of computational techniques. With the help of technologies such as bio-computing, health informatics, the disaster impacts on both human health and biological factors can be reduced to a large extend. Using these computational technologies, the country’s economy can also get boosted up and due to increased disease-causing pathogens, which directly impact the human health system. In this research work, a different type of sugarcane disease is detected and classified because manual identification is difficult and time-consuming. So, the farmers couldn’t find a better solution, than on the whole, they go for stubble burning, which is an alarming issue both on human and environmental wellness. The burning of bagasse causes bagassois, an interstitial lung disease that affects the tissues present in the lung through the air sacs. So, this sugarcane disease detection needs to be done early to avoid various health and environmental issues. The proposed work consists of the detection of four types of sugarcane leaf disease directly from the field. The sequence of methods is capturing images with WSN nodes, pre-processing with image enhancement and noise removal (IENR), segmentation with Fuzzy membership function and clustering (FMFC), feature extraction using Gray Level Co-occurrence Matrix Vector (GLCMV) and classification using Support Vector Machine (SVM). With the help of the effective proposed method, the highest parameters like precision, accuracy, sensitivity, and specificity for sugarcane leaf disease have been obtained. Based on the successful implementation process, the accuracy stated for the four sugarcane diseases along with the execution time is given below as Smut disease (87.12, 1.01 sec), Rust disease (90.23, 1.02 sec), Grassy Shoot disease (95.34, 1.047 sec), Red Rot disease (95.51, 1.04 sec).

Retrospective study of deep learning to reduce noise in non-contrast head CT images.

Presented herein is a novel CT denoising method uses a skip residual encoder-decoder framework with group convolutions and a novel loss function to improve the subjective and objective image quality for improved disease detection in patients with acute ischemic stroke (AIS). In this retrospective study, confirmed AIS patients with full-dose NCCT head scans were randomly selected from a stroke registry between 2016 and 2020. 325 patients (67±15 years, 176 men) were included. 18 patients each with 4-7 NCCTs performed within 5-day timeframe (83 total scans) were used for model training; 307 patients each with 1-4 NCCTs performed within 5-day timeframe (380 total scans) were used for hold-out testing. In the training group, a mean CT was created from the patient's co-registered scans for each input CT to train a rotation-reflection equivariant U-Net with skip and residual connections, as well as a group convolutional neural network (SRED-GCNN) using a custom loss function to remove image noise. Denoising performance was compared to the standard Block-matching and 3D filtering (BM3D) method and RED-CNN quantitatively and visually. Signal-to-noise ratio (SNR) and contrast-to-noise (CNR) were measured in manually drawn regions-of-interest in grey matter (GM), white matter (WM) and deep grey matter (DG). Visual comparison and impact on spatial resolution were assessed through phantom images. SRED-GCNN reduced the original CT image noise significantly better than BM3D, with SNR improvements in GM, WM, and DG by 2.47x, 2.83x, and 2.64x respectively and CNR improvements in DG/WM and GM/WM by 2.30x and 2.16x respectively. Compared to the proposed SRED-GCNN, RED-CNN reduces noise effectively though the results are visibly blurred. Scans denoised by the SRED-GCNN are shown to be visually clearer with preserved anatomy. The proposed SRED-GCNN model significantly reduces image noise and improves signal-to-noise and contrast-to-noise ratios in 380 unseen head NCCT cases.

An Improved Image Filtering Algorithm for Mixed Noise

In recent years, image filtering has been a hot research direction in the field of image processing. Experts and scholars have proposed many methods for noise removal in images, and these methods have achieved quite good denoising results. However, most methods are performed on single noise, such as Gaussian noise, salt and pepper noise, multiplicative noise, and so on. For mixed noise removal, such as salt and pepper noise + Gaussian noise, although some methods are currently available, the denoising effect is not ideal, and there are still many places worthy of improvement and promotion. To solve this problem, this paper proposes a filtering algorithm for mixed noise with salt and pepper + Gaussian noise that combines an improved median filtering algorithm, an improved wavelet threshold denoising algorithm and an improved Non-local Means (NLM) algorithm. The algorithm makes full use of the advantages of the median filter in removing salt and pepper noise and demonstrates the good performance of the wavelet threshold denoising algorithm and NLM algorithm in filtering Gaussian noise. At first, we made improvements to the three algorithms individually, and then combined them according to a certain process to obtain a new method for removing mixed noise. Specifically, we adjusted the size of window of the median filtering algorithm and improved the method of detecting noise points. We improved the threshold function of the wavelet threshold algorithm, analyzed its relevant mathematical characteristics, and finally gave an adaptive threshold. For the NLM algorithm, we improved its Euclidean distance function and the corresponding distance weight function. In order to test the denoising effect of this method, salt and pepper + Gaussian noise with different noise levels were added to the test images, and several state-of-the-art denoising algorithms were selected to compare with our algorithm, including K-Singular Value Decomposition (KSVD), Non-locally Centralized Sparse Representation (NCSR), Structured Overcomplete Sparsifying Transform Model with Block Cosparsity (OCTOBOS), Trilateral Weighted Sparse Coding (TWSC), Block Matching and 3D Filtering (BM3D), and Weighted Nuclear Norm Minimization (WNNM). Experimental results show that our proposed algorithm is about 2–7 dB higher than the above algorithms in Peak Signal-Noise Ratio (PSNR), and also has better performance in Root Mean Square Error (RMSE), Structural Similarity (SSIM), and Feature Similarity (FSIM). In general, our algorithm has better denoising performance, better restoration of image details and edge information, and stronger robustness than the above-mentioned algorithms.

A New Defogging Algorithm for Underwater Images

Abstract Images taken underwater will appear greenish or blueish due to the scattering and attenuation of light, resulting in color distortion of underwater images. This paper proposes a new underwater image defogging algorithm, which can effectively remove image noise, improve the color saturation and contrast of underwater images, and restore clear underwater images without fog. The algorithm introduces guided filtering, which increases speed and work efficiency. The linear enhancement of the saturation component can effectively enhance the color saturation of the underwater image. Compensation for local brightness can better show image details. Through experimental comparison with other algorithms, our algorithm has achieved good advantages in terms of defogging, image structural information integrity, and resistance to color attenuation.

Combined total variation of first and fractional orders for Poisson noise removal in digital images

Introduction: Many methods have been proposed to handle the image restoration problem with Poisson noise. A popular approach to Poissonian image reconstruction is the one based on Total Variation. This method can provide significantly sharp edges and visually fine images, but it results in piecewise-constant regions in the resulting images. Purpose: Developing an adaptive total variation-based model for the reconstruction of images contaminated by Poisson noise, and an algorithm for solving the optimization problem. Results: We proposed an effective way to restore images degraded by Poisson noise. Using the Bayesian framework, we proposed an adaptive model based on a combination of first-order total variation and fractional order total variation. The first-order total variation model is efficient for suppressing the noise and preserving the keen edges simultaneously. However, the first-order total variation method usually causes artifact problems in the obtained results. To avoid this drawback, we can use high-order total variation models, one of which is the fractional-order total variation-based model for image restoration. In the fractional-order total variation model, the derivatives have an order greater than or equal to one. It leads to the convenience of computation with a compact discrete form. However, methods based on the fractional-order total variation may cause image blurring. Thus, the proposed model incorporates the advantages of two total variation regularization models, having a significant effect on the edge-preserving image restoration. In order to solve the considered optimization problem, the Split Bregman method is used. Experimental results are provided, demonstrating the effectiveness of the proposed method. Practical relevance: The proposed method allows you to restore Poissonian images preserving their edges. The presented numerical simulation demonstrates the competitive performance of the model proposed for image reconstruction. Discussion: From the experimental results, we can see that the proposed algorithm is effective in suppressing noise and preserving the image edges. However, the weighted parameters in the proposed model were not automatically selected at each iteration of the proposed algorithm. This requires additional research.

Learning domain transfer for unsupervised magnetic resonance imaging restoration and edge enhancement

AbstractRecently, many effective medical image restoration methods based on deep learning have been proposed. Most of the methods are used to solve single image processing tasks, such as image noise removal, image deblurring, and image super‐resolution. However, real medical images often suffer from multiple degradation factors, such as signal interference in the process of shooting or the relative movement of patients during the process of image acquisition. The image restoration methods only considering a single image degradation factor often fail to yield satisfactory results for the restoration purpose of practical medical images. It is difficult to obtain paired medical images to incorporate real image processing tasks into the framework of supervised learning. For the restoration of real medical images with multiple degradation factors, an unsupervised learning method based on domain transfer to resolve the MRI restoration problem is proposed. Specifically, learning invariant representations from a degraded image and a transferred image via adversarial domain adaption and then extra self‐supervised modules to further improve the robustness of representations are used. In addition, the Laplacian operator is embedded in the encoder to extract additional edges, which can form additional constraints on edge recovery. Experimental results show that the proposed method is effective in both image restoration and edge preservation.

Image inpainting by low-rank tensor decomposition and multidirectional search

For a damaged image, the loss of pixel information can be roughly divided into two categories, random missing and non-random missing. The missing of an entire row or column of the image is a specific structural missing pattern that is extremely difficult to deal with. Although most of the existing methods have partially fixed this information missed problem, the diffusion-based methods tend to produce blur, the exemplar-based methods are prone to error filling, and the neural network-based methods are highly dependent on data, which cannot handle this special structural missing very well. Using the nonlocal self-similarity prior and the low-rank prior, we present multidirectional search and nonlocal low-rank tensor completion (MS-NLLRTC) algorithm based on the tensor ring (TR) decomposition and multidirectional search (MS). The MS method is a newly proposed method that can search similar patches much more diversified. Using MS method, we directly stack the similar patches into a three-dimensional similar tensor instead of pulling them into column vectors, then the similar tensor can be completed by TR decomposition. The optimization results can be obtained by leveraging the alternating direction method under the augmented Lagrangian multiplier framework. Moreover, we add a weighted nuclear norm to the tensor completion model (WNLLRTC), achieving a better inpainting performance. We also combine a noise removal method with WNLLRTC algorithm, which can handle image random missing and image noise removal simultaneously. Experimental results indicate that our proposed algorithms are competitive with some state-of-the-art inpainting algorithms in terms of both numerical evaluation and visual quality.

Noise Removal in Lung LDCT Images by Novel Discrete Wavelet-Based Denoising With Adaptive Thresholding Technique

Cancer is presently one of the prominent causes of death in the world. Early cancer detection, which can improve the prognosis and survival of cancer patients, is challenging for radiologists. Low-dose computed tomography, a commonly used imaging test for screening lung cancer, has a risk of exposure of patients to ionizing radiations. Increased radiation exposure can cause lung cancer development. However, reduced radiation dose results in noisy LDCT images. Efficient preprocessing techniques with computer-aided diagnosis tools can remove noise from LDCT images. Such tools can increase the survival of lung cancer patients by an accurate delineation of the lung nodules. This study aims to develop a framework for preprocessing LDCT images. The authors propose a noise removal technique of discrete wavelet transforms with adaptive thresholding by computing the threshold with a genetic algorithm. The performance of the proposed technique is evaluated by comparing with mean, median, and Gaussian noise filters.

Trainable fourth-order partial differential equations for image noise removal

Image processing by partial differential equations (PDEs) has been an active topic in the area of image denoising, which is an important task in computer vision. In PDE-based methods for unprocessed image process ing, the original image is considered as the initial value for the PDE and the solution of the equation is the outcome of the model. Despite the advan tages of using PDEs in image processing, designing and modeling different equations for various types of applications have always been a challenging and interesting problem. In this article, we aim to tackle this problem by introducing a fourth-order equation with flexible and trainable coefficients, and with the help of an optimal control problem, the coefficients are determined; therefore the proposed model adapts itself to each particular application. At the final stage, the image enhancement is performed on the noisy test image and the performance of our proposed method is compared to other PDE-based models.

An efficient method for scanned images by using color-correction and [formula omitted] gradient minimization

To improve the quality of scanned image captured by cameras, we propose a novel and efficient method for image processing by using color-correction and L0 gradient minimization. Our method is divided into two steps. To derive a colorimetric mapping between digital RGB signals and real image values, we use a polynomial model by considering the interrelations among the standard color spaces. A L0 gradient minimization is used to remove the image noises. Based on the half-quadratic splitting method, an iterative algorithm for our proposed method is developed. The iterative algorithm is easy to implement with the optimal complexity O(NlogN). Our method is particularly beneficial to correct image color and remove image noises. Various tests are presented to demonstrate the robustness and efficiency of our method.

An Advanced Noise Reduction and Edge Enhancement Algorithm

Complementary metal-oxide-semiconductor (CMOS) image sensors can cause noise in images collected or transmitted in unfavorable environments, especially low-illumination scenarios. Numerous approaches have been developed to solve the problem of image noise removal. However, producing natural and high-quality denoised images remains a crucial challenge. To meet this challenge, we introduce a novel approach for image denoising with the following three main contributions. First, we devise a deep image prior-based module that can produce a noise-reduced image as well as a contrast-enhanced denoised one from a noisy input image. Second, the produced images are passed through a proposed image fusion (IF) module based on Laplacian pyramid decomposition to combine them and prevent noise amplification and color shift. Finally, we introduce a progressive refinement (PR) module, which adopts the summed-area tables to take advantage of spatially correlated information for edge and image quality enhancement. Qualitative and quantitative evaluations demonstrate the efficiency, superiority, and robustness of our proposed method.

Fish Image Classification by XgBoost Based on Gist and GLCM Features

Classification of fish image is a complex issue in the field of pattern recognition. Fish classification is a complicated task. Physical shape, size, orientation etc. made it complex to classify. Selection of appropriate feature is also a great issue in image classification. Classification of fish image is very important in fishing service and agricultural field, fish industry, survey applications of fisheries and in other related area. For the assessment and counting of fishes, classification of fish image is also necessary as it can save time. This paper presents a fish image classification method with the robust Gist feature and Gray Level Co-occurrence Matrix (GLCM) feature. Noise removal and resizing of image is applied as pre-processing task. Gist and GLCM feature are combined to make a better feature matrix. Features are also tested separately. But combined feature vector performs better than individual. Classification is made on ten types of raw images of fish from two datasets -QUT and F4K dataset. The feature set is trained with different machine learning models. Among them, XgBoost performs with 90.2% and 98.08% accuracy for QUT and F4K dataset respectively.

Restoration method of ancient mural image defect information based on neighborhood filtering

The local data of ancient murals is seriously damaged, and image noise exists in the process of restoration, which affects the quality of restoration of ancient murals. Therefore, this paper studies the restoration method of ancient mural image defect information based on neighborhood filtering. On the premise of obtaining the causes of ancient mural defects, this method enhances image data based on spatial domain enhancement method, extracts pixel similar information based on neighborhood filtering, searches in the whole image, and removes image noise used to repair local areas; By extracting the line drawing features of mural, the defect part of ancient mural image can be repaired. The experimental results show that the peak signal-to-noise ratio of the repaired image is the highest and the quality of the image is better under the application of the repair method.

RSAMSR: A deep neural network based on residual self-encoding and attention mechanism for image super-resolution

This paper proposes an improved residual self-encoding and attention mechanism super-resolution (RSAMSR) network. Firstly, we construct a new structure through the multi-path convolution and design an attention mechanism module. Then the input data are divided into high and low-frequency components sent to the residual network with different depths for processing based on the spatial scaling theory. Finally, we introduce a self-encoding network to remove image noise. The model uses the L1 loss function for data training on the DIV2K data set and is compared with some state-of-the-art SR networks in four different public datasets of Set5, Set14, B100, and Urban100 under the magnification factor ×2, ×3, and ×4. Detailed experimental results show that the proposed model has fewer model parameters, the best objective criteria PSNR and SSIM, and the best subjective visual effect.

Research on Feature Enhancement for Small Object Detection

Small object detection is a challenging research direction in the field of computer vision, due to the low resolution and restricted information of small objects. At present, the general detectors only use appearance features to classify and locate objects, but they are prone to failure under the interference of background noise. On the other hand, the detector based on deep neural network has excellent performance on large scale, but it is difficult to extract enough information of small objects. This paper proposes a feature enhancement network (FENet), which contains two modules. The Residual feature enhancement (RFE) module combines residual learning and sub-pixel convolution to improve the resolution of input small objects and remove image noise. The Attention Feature Pyramid (AFP) module integrates the feature pyramid and attention mechanism, which can extract context information and filter redundant context information. At the same time, considering the imbalance of the contribution of large and small objects to the loss function during the training process, a feedback-driven function is introduced to solve the problem of uneven loss under multiple scales. Experimental results show that compared with the existing small object detection methods, our method has better performance.

Monitoring the Transformation of Arctic Landscapes: Automated Shoreline Change Detection of Lakes Using Very High Resolution Imagery

Water bodies are a highly abundant feature of Arctic permafrost ecosystems and strongly influence their hydrology, ecology and biogeochemical cycling. While very high resolution satellite images enable detailed mapping of these water bodies, the increasing availability and abundance of this imagery calls for fast, reliable and automatized monitoring. This technical work presents a largely automated and scalable workflow that removes image noise, detects water bodies, removes potential misclassifications from infrastructural features, derives lake shoreline geometries and retrieves their movement rate and direction on the basis of ortho-ready very high resolution satellite imagery from Arctic permafrost lowlands. We applied this workflow to typical Arctic lake areas on the Alaska North Slope and achieved a successful and fast detection of water bodies. We derived representative values for shoreline movement rates ranging from 0.40–0.56 m yr−1 for lake sizes of 0.10 ha–23.04 ha. The approach also gives an insight into seasonal water level changes. Based on an extensive quantification of error sources, we discuss how the results of the automated workflow can be further enhanced by incorporating additional information on weather conditions and image metadata and by improving the input database. The workflow is suitable for the seasonal to annual monitoring of lake changes on a sub-meter scale in the study areas in northern Alaska and can readily be scaled for application across larger regions within certain accuracy limitations.