Image Noise Removal Research Articles

Discrete Hermite Wavelet Filters with Prove Mathematical Aspects

This article describes a new image processing method in order to enhance the images under testing based on discrete Hermite wavelet filter. Discrete Hermite Wavelet Transform, which was used in image processing, including compression and noise removal was used after a number of theories proved to be mathematically ready for use in image processing. Through Discrete Hermite Wavelet Transform at different levels by finding a new filter and using it to find peak-to-noise ratio values (PSNR), compression ratio, mean square error (MSE) and bits per pixel found. Achieving a high compression ratio is acquired by using a new image decomposition algorithm. Bit reduction per pixel is obtained at the second level when increasing the level of decomposition to obtain compression ratio while PSNR is decreased with the basic wavelets, due to the features that characterize Discrete Hermite Wavelet Transform. A new filter was discovered more efficient and effective in reducing the error significantly in rebuilding, MSE and bits per pixel, the samples image is used show efficient intermittent wavelets that were built in this work. This method enabling to extract the integration matrices using Hermite wavelet operation matrix of integration that leads to improve the quality of images under testing. The obtained results for decreasing of and increasing of confirm the accuracy and effectiveness of the proposed method. These results can be used in many fields such as medicine, science treatment, compression, and noise removal images.

Restoration of Images With High-Density Impulsive Noise Based on Sparse Approximation and Ant-Colony Optimization

In this work, we propose an image denoising approach, specifically for “salt-and-pepper noise,” based on the optimized sparse approximation for restoring images contaminated by high-density impulse noise. The proposed method first uses the inverse-distance weighting-based prediction to estimate noise-recovered pixels. It then utilizes DCT-based sparse approximation to further refine the denoised results with the ant colony optimization. Experiments on an image benchmark dataset demonstrate that the proposed method yields better results compared to the state-of-the-art image noise removal methods.

Noise removal and edge detection in ultrasound images by the topological gradient method

Noise removal and edge detection in ultrasound images by the topological gradient method

Performance of image pre-processing filters for noise removal in transformer oil images at different temperatures

The important goal of this paper is to investigate the performance of the image pre-processing filters for the removal of noise in real time transformer oil images which are captured at different temperatures. An experiment conducted to acquire transformer oil images instantaneously at the temperatures of 30 °C, 60 °C, 90 °C and 120 °C. Digital images need to be corrected before it is used for a particular application since they are generally corrupted by noise during image acquisition. In this paper, the acquired images are enhanced using different preprocessing filtering techniques such as mean, median, wiener and non local means filters. The performance of these image enhancement filters are validated using image quality performance metrics such as Mean Square Error [MSE] and Peak Signal to Noise Ratio [PSNR]. Through this study, it was found that non local means filter execute most excellent results compared to other filtering techniques.

Mid Point Weighted Median Filter for Noise Removal and Smoothening of Images

In this paper, a Weighted Median Filter (WMF) mainly Mid-Point WMF (MP WMF) is used to smoothen the images or to remove the impulsive noise present in the input images. It is an improvised version of the median filter. This weighted filter uses the basic concept of the median filter with the enhancement in their mask from normalized mask to the weighted mask. In this weighted median filter, the weight-age is giving to the mid-point pixel i.e. centre pixels or its neighbouring pixels by increasing the repetition of those pixels so that the weight of those mid-point pixel and neighbour pixels get increased. It is shown that the weighted median filter performs more accurately than the normal median filter. Some relationship between MP WMF and other two Four Neighbouring (N4) and Diagonal Neighbouring (ND) Weighted Median Filter are derived. Experimental work has demonstrated that the MP WMF outperform very well than the standard median filters in terms of their noise reduction and in smoothening the image. The proposed MP WMF also provides very good robustness for impulsive noise.

Computer Aided Diagnosis System using Watershed Segmentation with Xception Based Classification Model for Lung CT Images

Early recognition and classification of pulmonary nodules by the use of computer-aided diagnosis (CAD) tools finds useful to reduce the death rate due to the illness of lung cancer. This paper devises a new CAD tool utilizing a segmentation based classification process for lung CT images. Initially, the input CT images are pre-processed by image enhancement and noise removal process. Then, watershed segmentation model is employed for the segmentation of the pre-processed images. Subsequently, the feature extraction process is carried out using Xecption model and random forest (RF) classifier is used of the identification of lung CT images as normal, benign or malignant. The use of RF model results to effective classification of the applied images. This model undergoes extensive experimentation against a benchmark lung CT image dataset and the results are investigated under several aspects. The obtained outcome pointed out the significant performance of the presented model over the compared methods.

Image Enhancement and Denoising in Extreme Low-Light Conditions

Image noise refers to the specks of false colors or artifacts that diminish the visual quality of the captured image. It has become our daily experience that with affordable smart-phone cameras we can capture high clarity photos in a brightly illuminated scene. But using the same camera in a poorly lit environment with high ISO settings results in images that are noisy with irrelevant specks of colors. Noise removal and contrast enhancement in images have been extensively studied by researchers over the past few decades. But most of these techniques fail to perform satisfactorily if the images are captured in an extremely dark environment. In recent years, computer vision researchers have started developing neural network-based algorithms to perform automated de-noising of images captured in a low-light environment. Although these methods are reasonably successful in providing the desired de-noised image, the transformation operation tends to distort the structure of the image contents to a certain extent. We propose an improved algorithm for image enhancement and de-noising using the camera’s raw image data by employing a deep U-Net generator. The network is trained in an end-to-end manner on a large training set with suitable loss functions. To preserve the image content structures at a higher resolution compared to the existing approaches, we make use of an edge loss term in addition to PSNR loss and structural similarity loss during the training phase. Qualitative and quantitative results in terms of PSNR and SSIM values emphasize the effectiveness of our approach.

Decision Tree Based Algorithm for Removal of Different Probability Salt and Pepper Noise in Images

A Decision tree based algorithm for the removal of equal and unequal probability salt and pepper noise in images is proposed. The algorithm aims to address one solution for different salt and pepper noise models. The proposed algorithm operates on an image using fixed 3*3 window. The decision tree based algorithm classifies pixel into noisy or not based on the decision and replaces it with mean of neighbours or unsymmetrical trimmed median or unsymmetrical trimmed midpoint. The algorithm exhibit excellent noise elimination capability at high noise densities in terms of quantitative and qualitative perspective. The algorithm was found to exhibit good noise removal characteristics for three noise models

PM-17 Noise removal for SEM images using a convolutional neural network

PM-17 Noise removal for SEM images using a convolutional neural network

A nonconvex and nonsmooth anisotropic total variation model for image noise and blur removal

In this paper, a nonconvex and nonsmooth anisotropic total variation model is proposed, which can provide a very sparser representation of the derivatives of the function in horizontal and vertical directions. The new model can preserve sharp edges and alleviate the staircase effect often arising in total variation (TV) based models. We use graduated nonconvexity (GNC) algorithm to solve the proposed nonconvex and nonsmooth minimization problem. Starting with a convex initialization, it uses a family of nonconvex functional to gradually approach the original nonconvex functional. For each subproblem, we use function splitting technique to separately address the nonconvex and nonsmooth properties, and use augmented Lagrangian method (ALM) to solve it. Experiments are conducted for both synthetic and real images to demonstrate the effectiveness of the proposed model. In addition, we compare it with several state-of-the-art models in denoising and deblurring applications. The numerical results show that our model has the best performance in terms of PSNR and MSSIM indexes.

Image Denoising Using Novel Social Grouping Optimization Algorithm with Transform Domain Technique

In recent days, image communication has evolved in many fields like medicine, entertainment, gaming, mail, etc. Thus, it is an immediate need to denoise the received image because noise that is added in the channel during communication alters or deteriorates information contained in the image. Any image processing techniques concerned with image denoising or image noise removal has to be started with the spatial domain and end with the transform domain. A lot of research was carried out in the spatial domain by modifying the performance of different image filters such as mean filters, median filters, Laplacian filters, etc. Recently much research was carried out in Transform techniques under the transform domain, with evolutionary computing tools (ECT). ECT has proven to be dominant when compared with traditional denoising techniques in combination with wavelets in the transform domain. In this article, the authors applied a novel ECT such as SGOA on the denoising problem for denoising monochrome as well as color images and performance for denoising was evaluated using several image quality metrics.

An Advanced ICTVSS Model for Real-Time Vehicle Traffic Applications.

From the accident news, it is found that the occurrences of traffic accidents every year and the numbers of deaths and injuries have raised continually and have become a specific issue concerned in society in Taiwan. More seriously, the number of traffic accidents is positively increased with the increasing motorized vehicles. Thus, to reduce the incidence of traffic accidents through by some advanced real-time technologies is an important and interesting work. However, some serious problems against traffic safety are facing, such as the low-quality video saved by a camera, low efficiency facilities supported, inefficient management of surveillance resources, and low definition resolution for cameras, which is resulted in a dilemma problem caused from providing evidence-based images to a local authority either for criteria for judgment or basis for improvement. As a big effort to deal with the above defects for constructing a smart city, this paper makes a main purpose to develop an advanced system of intelligent cloud-based transportation vehicle surveillance (called ICTVSS) for license plate identification. This existing identification algorithm was studied and developed from a combination of improved differential algorithm and improved active contour algorithm. Given such a combination, a novel algorithm of dynamic license identification for smart monitoring was fully realized for constructing a well-defined smart city. The experimental results showed good performance and experienced that the proposed algorithm performed well in locating multi-license plate and differential methods, removing image noise of license plate, and processing constant-inconstant light source from complex environment cases, and guaranteed effective license plate identification from the benefit of high resolutions of digital cameras.

Automated segmentation of fluid regions in optical coherence tomography B-scan images of age-related macular degeneration

Age-related macular degeneration (AMD) is a common eye disease that causes progressive vision loss in people older than 50 years. Fluid regions in retina are the most characteristic of AMD. Accurately segmenting fluid regions is crucial for the early diagnosis of AMD, and assessment of treatment efficacy. In this paper, we propose an automatic deep learning method constructed by integrating Squeeze-and-Excitation blocks with U-Net named SEUNet to segment fluid regions and classify OCT B-scan images to AMD or normal image. The proposed method comprises three stages: (1) preprocessing stage that includes image noise removal, locating the image on the area of interest, and image color-reversing; (2) fluid region segmentation stage which is based on U-Net and constructed by integrating Squeeze-and-Excitation block to segment fluid region; and (3) image classification stage that classifies image to AMD or normal image. Experimental results show that the proposed method have an average IOU coefficient of 0.9035, an average Dice coefficient of 0.9421, an average precision of 0.9446, and an average recall of 0.9464. Therefore, the proposed method can effectively segment fluid regions in OCT B-scan images.

A decision based asymmetrically trimmed modified winsorized median filter for the removal of salt and pepper noise in images and videos

A decision based asymmetrically trimmed Winsorized median for the removal of salt and pepper noise in images and videos is proposed. The proposed filter initially classifies the pixels as noisy and non noisy and later replaces the noisy pixels with asymmetrically trimmed modified winsorized median leaving the non noisy pixels unaltered. Exhaustive experiments were conducted on standard image database and the performance of the proposed filter was evaluated in terms of both quantitative and qualitatively with existing algorithm. It was found that the proposed algorithm was found to exhibit excellent noise suppression capabilities by preserving the fine information of the image even at higher noise densities. The performance of the proposed filter was found good even for videos.

Removal of noise in MRI images using a block difference‐based filtering approach

AbstractMagnetic resonance imaging (MRI) images are frequently sensitive to certain types of noises and artifacts. The denoising of MRI images is essential for improving visual quality and reliability of the quantitative analysis of diagnosis and treatment. In this article, a new block difference‐based filtering method is proposed to denoise the MRI images. First, the normal MRI image is degraded by a certain percentage of noise. The block difference between the intensity of the normal and noisy MRI is computed, and then it is compared with the intensity of the blocks of the normal MRI image. Based on the comparison, the pixel weights are updated to each block of the denoised MRI image. Observational results are brought out on the BrainWeb and BraTS datasets and evaluated by performance metrics such as peak signal‐to‐noise ratio, structural similarity index measures, universal quality index, and root mean square error. The proposed method outperforms the existing denoising filtering techniques.

Enhancing Resolution of Digital Rock Images with Super Resolution Convolutional Neural Networks

Single Image Super Resolution (SISR) techniques based on Super Resolution Convolutional Neural Networks (SRCNN) are applied to micro-computed tomography (micro-CT) images of sandstone and carbonate rocks. Digital rock imaging is limited by the capability of the scanning device resulting in a trade-off between resolution and field of view, and super resolution methods tested in this study aim to compensate for this limitation. SRCNN models SR-Resnet, Enhanced Deep SR (EDSR), and Wide-Activation Deep SR (WDSR) are used on the Digital Rock Super Resolution 1 (DRSRD1) Dataset of 4× downsampled images, comprising of 2000 high resolution (800 × 800) raw micro-CT images of Bentheimer sandstone and Estaillades carbonate. The trained models are applied to the validation and test data within the dataset and show a 3–5 dB rise (50%–70% reduction in relative error) in image quality compared to bicubic interpolation, with all tested models performing within a 0.1 dB range. Difference maps indicate that edge sharpness is completely recovered in images within the scope of the trained model, with only high frequency noise related detail loss. We find that aside from generation of high-resolution images, a beneficial side effect of super resolution methods applied to synthetically downgraded images is the removal of image noise while recovering edgewise sharpness which is important for the segmentation process. The model is also tested against low-resolution images of Bentheimer rock with image augmentation to account for natural noise and blur. The SRCNN method is shown to act as a preconditioner for image segmentation under these circumstances which naturally leads to further future development and training of models that segment an image directly. Image restoration by SRCNN on the rock images is of significantly higher quality than traditional methods and suggests SRCNN methods are a viable processing step in a digital rock workflow.

A Novel Rank Approximation Method for Mixture Noise Removal of Hyperspectral Images

Mixture noise removal is a fundamental problem in hyperspectral images’ (HSIs) processing that holds significant practical importance for subsequent applications. This problem can be recast as an approximation issue of a low-rank matrix. In this paper, a novel smooth rank approximation (SRA) model is proposed to cope with these mixture noises for HSIs. The crux idea is to devise a general smooth function under some assumptions to directly approximate the rank function, which attempts to explore a closer approximation than conventional methods. This new optimization model can be easily solved by the convex analysis tool and can remove the mixture noises of HSIs quickly and effectively. Subsequently, we give a feasible iterative algorithm, and the corresponding convergence analysis is discussed mathematically. Experimental results from the simulated data set as well as real data sets illustrate that the proposed SRA method significantly outperforms the state-of-the-art methods on HSI denoising.

A Review on CT and X-Ray Images Denoising Methods

In medical imaging systems, denoising is one of the important image processing tasks. Automatic noise removal will improve the quality of diagnosis and requires careful treatment of obtained imagery. Com-puted tomography (CT) and X-Ray imaging systems use the X radiation to capture images and they are usually corrupted by noise following a Poisson distribution. Due to the importance of Poisson noise re-moval in medical imaging, there are many state-of-the-art methods that have been studied in the image processing literature. These include methods that are based on total variation (TV) regularization, wave-lets, principal component analysis, machine learning etc. In this work, we will provide a review of the following important Poisson removal methods: the method based on the modified TV model, the adaptive TV method, the adaptive non-local total variation method, the method based on the higher-order natural image prior model, the Poisson reducing bilateral filter, the PURE-LET method, and the variance stabi-lizing transform-based methods. Our task focuses on methodology overview, accuracy, execution time and their advantage/disadvantage assessments. The goal of this paper is to provide an apt choice of denoising method that suits to CT and X-ray images. The integration of several high-quality denoising methods in image processing software for medical imaging systems will be always excellent option and help further image analysis for computer-aided diagnosis.

Removal of impulse noise in color images based on convolutional neural network

A new denoising framework based on deep convolutional neural network for suppressing impulse noise in color images is proposed in this paper. The proposed framework consists of two modules: noise detection and image reconstruction, both of which are implemented by a deep convolutional neural network. First, a noise classifier network is trained to detect random-valued impulse noise in a color image, which not only can detect the noisy color vector pixels but also can further identify the corrupted channels of each noisy color pixel. Then, a sparse clean color image is computed by replacing the values of noisy channels with 0 and keeping other noise-free channels unchanged. Finally, the sparse clean color image is fed to another denoiser network to reconstruct the denoised image. Experimental results show that the proposed denoiser outperforms other state-of-the-art methods clearly in both performance measure and visual evaluation.

An Integrated BM3D Method for Removing Mixed Noise in Remote Sensing Image

BM3D (block matching and 3D filtering) method is an effective Gaussian noise removing method, but it shows limitation when removing Gaussian and impulse mixed noise in remote sensing images. The integrated method is a more effective way to remove mixed noise. In order to make full use of the advantages of BM3D method, an improved integration method (integrated BM3D method) has been developed. And a modified method M-Liu method is raised and used for estimating the priori noise level as an input parameter for the integrated BM3D method. According to algorithm validation, this paper draws the conclusion that the integrated BM3D method, taking the removal of image noise and the retention of detail signals into account, has good denoising performance. The method can be used to provide a new method for image denoising, and it is useful for the later application of remote sensing image.