Random-valued Impulse Noise Research Articles

Switching non-local median filter

This paper describes a novel image filtering method for removal of random-valued impulse noise superimposed on grayscale images. Generally, it is well known that switching-type median filters are effective for impulse noise removal. In this paper, we propose a more sophisticated switching-type impulse noise removal method in terms of detail-preserving performance. Specifically, the noise detector of the proposed method finds out noise-corrupted pixels by focusing attention on the difference between the value of a pixel of interest (POI) and the median of its neighboring pixel values, and on the POI’s isolation tendency from the surrounding pixels. Furthermore, the removal of the detected noise is performed by the newly proposed median filter based on non-local processing, which has superior detail-preservation capability compared to the conventional median filter. The effectiveness and the validity of the proposed method are verified by some experiments using natural grayscale images.

A novel adaptive tolerance filter for random valued impulse noise suppression in digital grey and color images

During acquisition, transmission, storage and retrieval, quite often digital images become noised and mask the important details of an image and also present themselves with an ugly look. Such images if not processed properly, become useless for subsequent image processing operations like segmentation, classification etc. Hence the quality improvement (through denoising) of such noisy images becomes an important operation in the field of image processing. This paper proposes a two stage detection-estimation based filtering system to suppress random valued impulse noise from digital grey and color images based on neighborhood statistics of pixels of the working window under consideration. An adaptive working window and the adaptive tolerance computed from the pixels belonging to the current filtering window facilitates an appropriate detection of noisy pixels in the first phase, followed by the simple and computationally efficient restoration strategy in the second stage. The Simulation results prove that the proposed scheme exhibits much superior performance in comparison with other state of art image filtering methods in suppressing the random valued impulse noise from the digital grey and color images.

Efficient digital image denoising for gray scale images

We propose an algorithm for image de-noising which uses a trimmed global mean filter with rank order absolute differences to remove random-valued impulse noise, stripes, scratches and blotches. It is a two stage algorithm, in the first stage the corrupted candidate is detected using rank ordered absolute differences (ROAD). In the second stage, the corrupted pixels are replaced by the median of the uncorrupted pixels in the selected window. Trimmed global mean filter is used if the selected window contains all the pixels as noisy candidate. We used a fixed window size in both detection and filtering stages. The visual and quantitative results show that proposed filter outperforms the existing filters in restoring image which is corrupted by random valued impulse noise. The proposed algorithm also provides good results over the impulse noise image corrupted by artificially introduced scratches, blotches, and stripes without causing blurring.

Low-rank prior in single patches for nonpointwise impulse noise removal.

This paper introduces a low-rank prior in small oriented noise-free image patches. Considering an oriented patch as a matrix, a low-rank matrix approximation is enough to preserve the texture details in the optimally oriented patch. Based on this prior, we propose a single-patch method within a generalized joint low-rank and sparse matrix recovery framework to simultaneously detect and remove nonpointwise random-valued impulse noise (e.g., very small blobs). A weighting matrix is incorporated in the framework to encode an initial estimate of the spatial noise distribution. An accelerated proximal gradient method is adapted to estimate the optimal noise-free image patches. Experiments show the effectiveness of our framework in detecting and removing nonpointwise random-valued impulse noise.

English

Nowadays a good low complexity denoising technique is necessary as pre-processing operation in many real-time practical applications. Images get corrupted with impulse noise due to the process of image transmission and image acquisition. In the process of impulse noise filtering it is necessary to preserve edges and details of the image. Also to avoid image smoothing, only corrupted pixel must be filtered. Comprehensive survey of various denoising techniques has been focused in this paper. This paper illustrates the survey of different low complexity methods such as Median, Adaptive Center Weighted Median (ACWM), Adaptive Median Filter (AMF) and high complexity methods such as Alpha-trimmed Mean Based Method (ATMBM), Differential Rank Impulse Detector (DRID) and Rank Ordered Relative Difference (RORD).The most effective technique to remove random valued impulse noise without losing useful information with pleasing denoised image is by decision-tree based impulse detector and direction oriented edge preserving image filter. This design requires low computational cost, few memory buffers, no iterations and most suited to be applied to many real-time applications. Also this design can be efficiently designed with FPGA.

Image Transmission over Multipath Fading Channel and Image Denoising using Directional Weighted Median Filter

noise is often introduced into images during transmission contaminating the images due to channel errors. Based on the noise values, impulse noise can be classified as Fixed Valued Impulsive Noise or Salt and Pepper Noise(SPN) and Random Valued Impulsive Noise(RVIN). In this paper, an inpainting algorithm is presented based on Directional Weighted Median(DWM) Filter to denoise both the noises caused due to image transmission over multipath fading channel. The algorithm diffuses median value of pixels from the exterior area into the inner area and thus preserves the edges and fine details. The random valued impulsive noise and salt and pepper noise due to wireless channel modeled are simulated using MATLAB channel objects. The detection algorithm combined with the image correction based on DWMF shows better performance in terms of Peak Signal-to- Noise Ratio(PSNR) and Mean Absolute Error(MAE).

基于分层滤波技术的冲击噪声检测与去除算法

本文提出了一种基于分层滤波技术的图像随机值冲击噪声检测和去除算法。为了解决经典自适应中心加权中值滤波技术在较高噪声比率下漏检严重的问题，我们采取逐级设置由高到低的噪声值判决门限来层层筛选噪声，利用不同高度的门限甄别出不同信赖度的冲击噪点，同时更新已检测出的噪声点值。每一层均得到一幅中间去噪图像，并继续进行噪声点的判决，最终得到完整的噪声点空间以及终极去噪图像。通过对多幅不同噪声比率的噪声图进行图像恢复的仿真实验验证后，得出结论：本文所提算法无论在低噪声比率还是高噪声比率的情况下均能有效地检测出图像中的随机值冲击噪声，漏检和误检像素数相对较低，同时获得了较好的图像去噪效果，极大地扩展了原算法的应用范围。 In this paper, an algorithm about random-valued impulse noise detection and removal based on the hierarchical filter technology is proposed. In order to solve the problem of severe miss detection of classical adaptive center-weighted median filter in the situation of high noise ratios, we set the noise judgment thresholds from high values to low values to select noisy pixels hierarchically. The impulse noise with different reliable degrees is selected through different thresholds and at the same time the detected pixel values are updated. The interim denoised image is generated in each denoising layer and the noise detection continues in the next denoising layer. Lastly, we get all the locations of noisy pixels and the final denoised image is obtained. Extensive experimental results for different noisy images with different noise ratios show that our proposed algorithm can obtain the good performance of random-valued impulse noise detection in the situations of not only low noise ratios but also high noise ratios. The miss and false noise detection ratios are both low relatively. At the same time, the good denoised images can be obtained. Our algorithm expands the application range of the classical adaptive center-weighted median filter.

Denoising of colour images using window contrast enhancement and vector alignment

In this paper a two stage filtering scheme for removal of random valued impulse noise from colour images is presented. The first stage consisting of an impulse detector employs iterative contrast enhancement in the filtering window. The performance of the impulse detector is further improved by exploiting the inherent correlation among three colour components. The second stage restores the noisy pixel by optimally aligning the pixel vector such that the brightness and the colour of the restored pixel are close to the original pixel. As the proposed method also includes the noise free component in the process of restoration of noisy components, unlike other component-wise filtering approaches where restoration of noisy components is done independently, colour artefacts in the present scheme are avoided. A significantly improved performance of the proposed detection and filtering approach is demonstrated through several experiments.

Random-valued impulse noise removal using adaptive dual threshold median filter

Noise detection and its removal is very important in the image processing. Detection of noise is very crucial and significant in random valued impulse noise because it does not hamper the image pixels uniformly. This paper presents a novel and unique concept of adaptive dual threshold for the detection of random valued impulse noise along with simple median filter at noise removal stage. Simulation results shows that an efficient noise detection leads to a superior quality of de-noised image as compared to existing adaptive threshold based image de-noising techniques. Proposed threshold computation is based on averaging of pixel values of window which enhances the PSNR of our system as compared to existing median filter based image de-noising methods.

Removal of random-valued impulse noise by local statistics

In this paper, a new method for the identification and removal of random-valued impulse noise (RVIN) from images is proposed. We propose to identify the central pixel of the current sliding window as a noisy or noise free pixel based on the similar local statistics of the current window. Our proposed RVIN identifier works in an iterative way. Pixel identified as a noisy pixel is replaced by proposed minimum difference similar value in an optimal directions. The performance of the proposed method is evaluated on different test images and compared with state-of-the-art methods. Experimental results show that the proposed method cannot only identify the impulse noise efficiently, but can also preserve the detailed information of an image.

A Local Similarity Pattern for Removal of Random Valued Impulse Noise

This letter presents a new filtering scheme based on local similarity pattern within the local window for removing random valued impulse noise. A pixel to be considered as an original pixel, it should have ample numbers of similar neighboring pixels in a local window. The neighbors are divided into 2 subtypes: smooth similar neighbors and edge similar neighbors according to the different criterion. Extensive simulations show that the proposed filter provides better performance than many of the existing filters. In particular, the thresholds are adaptive to diverse image types at different noise rate and the computational complexity is very low.

FPGA IMPLEMENTATION AND ANALYSIS OF IMPULSE NOISE REDUCTION IN IMAGES

The images are affected by random valued impulse noises during the image capturing and processing stages. In this study, an efficient, high performance and low hardware utilized impulse noise reduction algorithm is presented. This methodology determines the optimum direction pixels through the estimation of standard deviation. The edges in the images are preserved during the process of impulse noise detection and removal stage. The hardware architecture for this design is proposed and its performance is analyzed with different FPGA Processors in terms of slices, LUTs and power consumption. The proposed hardware architecture consumes 1728 gates and power consumption of 159.95 mW. The main motivation behind this research is to design low power impulse noise detection architecture and its real time implementations.

Improved Median Filter using ROAD for Removal of Impulse Noise

paper represents a new algorithm which uses a trimmed global mean filter with ROAD to remove random impulse noise. A two step algorithm is implemented in which the first step ensure detection of corrupted pixels in the degraded image and the second step replaces the degraded image with either the median of uncorrupted pixels in the selected window and if the selected window contains noisy pixels only than trimmed global mean filter is used. To avoid computational delay and to ensure a light algorithm, the selected window is fixed (3x3) in both the detection and the filtering stage. This algorithm outperforms many filters in restoring image corrupted by random value impulse noise. KeywordsROLD, Impulse Noise, Denoise

Switching degenerate diffusion PDE filter based on impulselike probability for universal impulse noise removal

In this paper, a switching degenerate diffusion partial differential equation filter (SDDPDE) is developed by introducing the switching operators for reducing all kinds of impulse noise, and especially for images having a mixture of salt-and-pepper impulse noise and random-valued impulse noise which is a shortage for most of the existing filtering models. Our SDDPDE consists of the coarse and fine filtering stages. In the coarse filtering stages, the switching operator depends on a simple noise detector. In the fine filtering stages, we introduce the notion of impulselike probability, and the switching operator depends on both a simple noise detector and impulselike probability. Our SDDPDE will denoise noise pixels detected by the coarse detector while further modify the so-called noise-free pixels according to impulselike probability. The main advantages of our SDDPDE over published approaches are its simplicity and universality. In addition, we demonstrate the performance of our SDDPDE via application to three standard test images, corrupted by salt-and-pepper impulse noise, random-valued impulse noise and mixed impulse noise with high-noise levels, and the comparison with the other well-known filters. Experimental results show that our SDDPDE achieves high peak signal-to-noise ratio and better visual effect.

Color differences based fuzzy filter for extremely corrupted color images

In this paper, a color difference based fuzzy filter is presented for fix and random-valued impulse noise. Noise detection scheme of two stages was applied to detect noise efficiently whereas for noise removal an improved Histogram based Fuzzy Color Filter (HFC) is presented. Pixels detected as noisy by the noise detection scheme are deliberated as candidate for the removal of noise. Candidate noisy pixels are then processed using a modified Histogram based Fuzzy Color Filter to estimate their non-noisy values. The idea of using multiple fuzzy membership functions is presented, so that best suitable membership function for local image statistics can be used automatically. In the proposed technique we have used three different types of fuzzy membership functions (bell-shaped, trapezoidal-shaped, and triangular-shaped) and their fuzzy number construction algorithms are proposed. Experimentation is also performed with three, five, and seven membership functions. Type and number of suitable fuzzy membership functions are then identified to remove noise. Comparison with the existing filtering techniques is established on the basis of objective quantitative measures including structural similarity index measure (SSIM) and peak-signal-to-noise-ratio (PSNR). Simulations show that this filter is superior to that of the existing state-of-the-art filtering techniques in removing fix and random-valued impulse noise whereas retaining the details of the image contents.

Impulse Noise Removal using Optimal Direction Method with Fuzzy based Median Filter

Impulse noise is a spark that affects the contents of digital images. The proposed method detects the random valued impulse noise efficiently. Then the detected noisy pixels are restored by the median of neighbouring noise-free pixels. In a detection window of this proposed method, four directions are considered. From that, optimal direction is obtained by standard deviation. Threshold value is calculated by finding normalised distance between original pixel and other pixels in the optimal direction. The threshold value is used as a measure to detect whether the tested pixel is noisy or noise-free pixel. More edge pixels can be detected if the accurate or optimal direction of the edge is determined. The noisy pixel that has small deviations with the pixels in the optimal direction is seems like the original pixel. Here, in detection and in filtering, the window size is adaptive which depends on noise density in the detection window frame. The optimum threshold limit is fixed as 0.8 by using normalised distance between the central pixel and pixels in the optimum direction in first iteration. In second iteration, the threshold value should be kept very close to the value zero to remove the undetected noisy pixel and that was found as 0.4. In second iteration the noisy pixels will be mostly eliminated. It is found that the proposed method gives better results when compared to adaptive median filter, progressive switching median filter, in terms of PSNR and MSE values and output images are compared using MATLAB. General Terms Noise Removal, optimal direction

A Modified Iterative Alternating Direction Minimization Algorithm for Impulse Noise Removal in Images

Images are often corrupted by impulse noise. In this paper, an alternating direction minimization with continuation algorithm is modified and iteratively used to remove the impulse noise in images by exploring its self-similarity. A patch-based nonlocal operator and sparse representation are married in thel1-l1optimization model to be solved. Simulation results demonstrate that the proposed algorithm outperforms typical denoising methods in terms of preserving edges and textures for both salt-and-pepper noise and random-valued impulse noise. It can be also applied to suppress impulse noise-like artifacts in real mural images.

Image Restoration with Mixed or Unknown Noises

This paper proposes a simple model for image restoration with mixed or unknown noises. It can handle image restoration without assuming any prior knowledge of the noise distribution. It is particularly useful for solving real-life image restoration problems, since under various constraints, images are always degraded with mixed noise and it is impossible to determine what type of noise is involved. The proposed model can remove mixed-type noises as well as unknown noises and at the same time also works comparably well against the model whose data fitting term is designed for a specific given noise type. While most of the existing methods for image restoration are designed specifically for a given type of noise, ours appears to be the first universal model for handling image restoration with various mixed noises and unknown noises. Extensive simulations on synthetic data show that our method is effective and robust in restoring images contaminated by additive Gaussian noise, Poisson noise, random-valued impulse noise, multiplicative Gamma noise, and mixtures of these noises. Numerical results on real data show that it can remove noises without any prior knowledge of the noise distribution.

Histogram-Based Gaussian Noise Removal

In modern science and technology, as the digital image processing gets more and more importance, the process of image quality enhancement and image restoration becomes a matter of concern for the researchers. In an image, denoising complexity increases from salt and pepper impulse noise to random-valued impulse noise, through to Gaussian noise. As salt and pepper noise occupies either high (255) or low (0) values and also as it is not distributed uniformly, hence, with the help of correct neighbouring pixels and known value of noise, the corrupted pixels can be easily restored. In random-valued noise, the value of noise is unknown, but we can take advantage of the non-uniform noise distribution, and using non-corrupted neighbouring pixels values, we can restore the corrupted pixels. However, as Gaussian noise is a uniform noise, hence, not only the value of noise is unknown, but also it is not possible to get non-corrupted neighbouring pixels. In Gaussian noise, restoring pixels using the corrupted neighbouring pixels is a highly tedious job. In this paper, an efficient algorithm for the removal of Gaussian noise is proposed. Experimental results show that proposed algorithm produces good results up to 50% of noise level, the value normally real-time images were corrupted.

Removing random-valued impulse noise in images using a neural network detector

This paper proposes a new method using an artificial neural network to remove random-valued impulse noise (RVIN) in images. The inputs of the neural model used to detect the RVIN are formed using basic and related gradient values. The detection of the noisy pixels is realized in 3 phases using the proposed neural detector. In order to obtain a more robust detector, 2 different networks, which are trained with an artificial training image corrupted with high and low clutter densities, are used. The extensive simulation results show that the proposed method is significantly better than the compared filters in terms of its image restoration and noise detection performance.