Pixel Noise Research Articles

Recursive reservoir concatenation for salt-and-pepper denoising

We propose a recursive reservoir concatenation architecture in reservoir computing for salt-and-pepper noise removal. The recursive algorithm consists of two components. One is the initial network training for the recursion. Since the standard reservoir computing does not appreciate images as input data, we designed a nonlinear image-specific forward operator that can extract image features from noisy input images, which are to be mapped into a reservoir for training. The other is the recursive reservoir concatenation to further improve the reconstruction quality. Training errors decrease as more reservoirs are concatenated due to the hierarchical structure of the recursive reservoir concatenation. The proposed method outperformed most analytic or machine-learning based denoising models for salt-and-pepper noise with a training cost much lower than other neural network-based models. Reconstruction is completely parallel, in that noise in different pixels can be removed in parallel.

Global Semantic Localization from Abstract Ellipse-Ellipsoid Model and Object-Level Instance Topology

Robust and highly accurate localization using a camera is a challenging task when appearance varies significantly. In indoor environments, changes in illumination and object occlusion can have a significant impact on visual localization. In this paper, we propose a visual localization method based on an ellipse-ellipsoid model, combined with object-level instance topology and alignment. First, we develop a CNN-based (Convolutional Neural Network) ellipse prediction network, DEllipse-Net, which integrates depth information with RGB data to estimate the projection of ellipsoids onto images. Second, we model environments using 3D (Three-dimensional) ellipsoids, instance topology, and ellipsoid descriptors. Finally, the detected ellipses are aligned with the ellipsoids in the environment through semantic object association, and 6-DoF (Degree of Freedom) pose estimation is performed using the ellipse-ellipsoid model. In the bounding box noise experiment, DEllipse-Net demonstrates higher robustness compared to other methods, achieving the highest prediction accuracy for 11 out of 23 objects in ellipse prediction. In the localization test with 15 pixels of noise, we achieve ATE (Absolute Translation Error) and ARE (Absolute Rotation Error) of 0.077 m and 2.70∘ in the fr2_desk sequence. Additionally, DEllipse-Net is lightweight and highly portable, with a model size of only 18.6 MB, and a single model can handle all objects. In the object-level instance topology and alignment experiment, our topology and alignment methods significantly enhance the global localization accuracy of the ellipse-ellipsoid model. In experiments involving lighting changes and occlusions, our method achieves more robust global localization compared to the classical bag-of-words based localization method and other ellipse-ellipsoid localization methods.

Object-oriented U-GCN for open-pit mining extraction from high spatial resolution remote-sensing images of complex scenes

ABSTRACT Precise extraction of open-pit mines is crucial for resource management and ecological and environmental dynamic monitoring. Current methods for extracting open-pit mines encounter challenges such as low accuracy and difficulty detecting complex scenes of open-pit mining. To address these issues, this paper proposes an object-oriented intelligent extraction method for complex mining scenes using Gaofen-2(GF-2) high-resolution remote-sensing images, which expresses the pixel-level features at the object level and utilizes the unique feature propagation and aggregation capabilities of the graph structure for the extraction of the mines. First, an object-oriented feature expression strategy is introduced to express multi-level pixel-level features as object-level features by constructing objects with appropriate multi-resolution segmentation parameters. This approach effectively reduces the impact of isolated pixel noise and outliers on classification results. Second, this paper proposes a U-GCN-based open-pit mining extraction method that combines the powerful multi-level feature extraction capabilities of U-GCN to propagate and aggregate information in a graph structure, effectively modelling spatial relationships between different objects. This method achieves high-precision extraction of open-pit mining areas. In experiments conducted on two study areas of varying scales, the F1 scores for open-pit mine extraction reached 93.32% and 83.06%. Comparative experiments demonstrate that the proposed object-oriented U-GCN method performs superiorly in terms of accuracy, stability and robustness across mining scenes with different levels of complexity. The proposed open-pit mine extraction method offers new insights and methodologies for current extraction practices.

Optimization of the Pixel Design for Large Gamma Cameras Based on Silicon Photomultipliers.

Most single-photon emission computed tomography (SPECT) scanners employ a gamma camera with a large scintillator crystal and 50-100 large photomultiplier tubes (PMTs). In the past, we proposed that the weight, size and cost of a scanner could be reduced by replacing the PMTs with large-area silicon photomultiplier (SiPM) pixels in which commercial SiPMs are summed to reduce the number of readout channels. We studied the feasibility of that solution with a small homemade camera, but the question on how it could be implemented in a large camera remained open. In this work, we try to answer this question by performing Geant4 simulations of a full-body SPECT camera. We studied how the pixel size, shape and noise could affect its energy and spatial resolution. Our results suggest that it would be possible to obtain an intrinsic spatial resolution of a few mm FWHM and an energy resolution at 140 keV close to 10%, even if using pixels more than 20 times larger than standard commercial SiPMs of 6 × 6 mm2. We have also found that if SiPMs are distributed following a honeycomb structure, the spatial resolution is significantly better than if using square pixels distributed in a square grid.

Deep Neural Remote Sensing and Sentinel-2 Satellite Image Processing of Kirkuk City, Iraq for Sustainable Prospective

Sentinel-2 satellites, equipped with board-mounted multi-spectral payloads provide images of the Earth in the wavelengths of the electromagnetic spectrum. These sensors can be used on Earth's surface to observe it with a very high spatial resolution, and there is a wide range of near-infrared and non-infrared spectral bands. These spectral ranges allow for a wide array of purposes, like assessing vegetation health land use and land cover changes, coastal and inland water quality assessment, and making disaster maps. In this case study, we mapped and analyzed different types of Sentinel-2 images that imaged Kirkuk city landscape in Iraq. The methodology is based on Artificial Intelligence AI analyzing patterns of Sentinel hub data and Geographic Information Systems (GIS)-based mapping. Furthermore, Minimum Noise Fraction (MNF) and Pixel Purity Index (PPI) were applied on each image to enhance the spectral unmixing accuracy which provides higher precise endmember spectra. Besides a deep neural remote sensing have been used for 10m resolution Sentinel-2 image segmentation of Kikuk. This produces such a result where features are exactly distinguished and identified. This is, performed by automatically detecting and classifying features on the image to provide better identification and estimation. Analyzing received data through Sentinel-2 provides us with the basis to identify such patterns, trends, and insights as key facts supporting urban planning, environmental sustainability and so much more. Received: 25 March 2024 | Revised: 31 May 2024 | Accepted: 23 August 2024 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement Data are available from the corresponding author upon reasonable request. Author Contribution Statement Huda Jamal Jumaah: Conceptualization, Methodology, Formal analysis, Resources, Data curation, Writing - original draft, Writing - review & editing, Visualization, Supervision, Project administration. Aydin Adnan Rashid: Software. Serri Abdul Razzaq Saleh: Validation. Sarah Jamal Jumaah: Investigation.

An improved pixel circuit with low noise event rate and enhanced bright‐light sensitivity for dynamic vision sensor

AbstractDynamic vision sensor (DVS) imaging quality is significantly affected by pixel noise and temporal contrast (TC), which is inversely proportional to sensitivity. To reduce the noise event rate and improve sensitivity in bright‐light conditions in the DVS pixel circuit, this paper proposes improvements to the conventional DVS pixel circuit. The proposed DVS pixel circuit adopts stacked medium‐threshold transistors instead of a single high‐threshold transistor in the photoreceptor and introduces a threshold switching circuit. Compared with the conventional DVS pixel circuit, this design increases event threshold normalized by root mean square (RMS) noise voltage, reducing the dim‐light noise bandwidth. Additionally, it achieves higher sensitivity in bright‐light conditions compared with dim‐light conditions. The proposed DVS pixel circuit is implemented in a 110‐nm complementary metal‐oxide semiconductor (CMOS) process. Post‐simulation results show that, for photocurrents between 5 fA and 100 pA, the proposed DVS pixel circuit achieves a 35 Hz peak event rate at 15% TC, which is reduced to 3.1% of the conventional structure. For photocurrents exceeding 30 pA, the proposed structure can switch TC from 15% to 5%, maintaining a noise event rate below 0.1 Hz.

Adaptive median filter salt and pepper noise suppression approach for common path coherent dispersion spectrometer

The Common-path Coherent-dispersion Spectrometer (CODES), an exoplanet detection instrument, executes high-precision Radial Velocity (RV) inversions by recording the phase shifts of interference fringes. Salt-and-pepper noise caused by factors such as improper operation of the CCD probe/analog-to-digital converter and strong dark currents may interfere with the phase information of the fringe. This lowers the quality of the interfering fringe image and significantly interferes with the RV’s inversion. In this study, an adaptive median filtering algorithm (CODESmF) based on submaximum and subminimum values is designed to eliminate the interference fringe image's salt-and-pepper noise as well as to reduce RV error. This allows the interference fringe image's phase information to be retained more completely. The algorithm consists of two major modules. Pixel Sub-extreme-based Filtered Noise Monitoring Module: discriminates signal pixels and noise pixels based on the submaximum and subminimum values of the pixels in the filtering window. Adaptive Median Filter Noise Suppression Module: the signal pixel is kept at the original value output, the noise pixel serves as the filtering window's center pixel, and the adaptive median filtering procedure is repeated numerous times with various filtering window sizes. According to the experimental findings, the CODESmF outperforms comparable algorithms and works better at recovering interference fringes. More than 90% of the phase/RV error caused by salt-and-pepper noise is typically eliminated by the CODESmF algorithm, and in certain circumstances, it can even remove roughly 98% of the phase error.

Pt4: Phantom-4D, an open-source software tool for creating time-evolving 3D phantoms

pt4, an open-source software tool to describe time-evolving phantoms is presented. pt4 allows users to create detailed time-evolving phantoms for testing novel 4D-CT reconstruction algorithms. Ground-truth volumes and simulated X-ray projections can be produced at arbitrary time-points during time-evolution and with customisable pixel dimensions, noise models, and X-ray source trajectories. Phantoms are built up from 3D primitives whose parameters and attenuation can be made arbitrary functions of time. This feature permits both complex continuous and discontinuous time-evolution necessary for thorough testing of 4D-CT reconstruction algorithms. Various phantoms built using pt4 are also presented to demonstrate the versatility of pt4 phantom description. pt4 is written in C++ and is highly parallelised leading to a performant implementation which is feasible to use for up to thousand-of-voxel volume pixel dimensions.

Forecast Cosmological Constraints with the 1D Wavelet Scattering Transform and the Lyman-α Forest.

We make forecasts for the constraining power of the 1D wavelet scattering transform when used with a Lyman-α forest cosmology survey. Using mock simulations and a Fisher matrix, we show that there is considerable cosmological information in the scattering transform coefficients not captured by the flux power spectrum. We estimate mock covariance matrices assuming uncorrelated Gaussian pixel noise for each quasar at a level drawn from a simple log-normal model. The extra information comes from a smaller estimated covariance in the first-order wavelet power and from second-order wavelet coefficients that probe non-Gaussian information in the forest. Forecast constraints on cosmological parameters from the wavelet scattering transform are more than an order of magnitude tighter than for the power spectrum, shrinking a 4D parameter space by a factor of 10^{6}. Should these improvements be realized with the Dark Energy Spectroscopic Instrument, inflationary running would be constrained to test common inflationary models predicting α_{s}=-6×10^{-4} and neutrino mass constraints would be improved enough for a 5-σ detection of the minimal neutrino mass.

A Data-driven Approach for Mitigating Dark Current Noise and Bad Pixels in Complementary Metal Oxide Semiconductor Cameras for Space-based Telescopes

In recent years, there has been a gradual increase in the performance of complementary metal oxide semiconductor (CMOS) cameras. These cameras have gained popularity as a viable alternative to charge-coupled device cameras in a wide range of applications. One particular application is the CMOS camera installed in small space telescopes. However, the limited power and spatial resources available on satellites present challenges in maintaining ideal observation conditions, including temperature and radiation environment. Consequently, images captured by CMOS cameras are susceptible to issues such as dark current noise and defective pixels. In this paper, we introduce a data-driven framework for mitigating dark current noise and bad pixels for CMOS cameras. Our approach involves two key steps: pixel clustering and function fitting. During the pixel clustering step, we identify and group pixels exhibiting similar dark current noise properties. Subsequently, in the function fitting step, we formulate functions that capture the relationship between dark current and temperature, as dictated by the Arrhenius law. Our framework leverages ground-based test data to establish distinct temperature–dark current relations for pixels within different clusters. The cluster results could then be utilized to estimate the dark current noise level and detect bad pixels from real observational data. To assess the effectiveness of our approach, we have conducted tests using real observation data obtained from the Yangwang-1 satellite, equipped with a near-ultraviolet telescope and an optical telescope. The results show a considerable improvement in the detection efficiency of space-based telescopes.

Nondestructive freshness evaluation of mackerel fish using Vis/NIR hyperspectral imaging and multivariate analysis

Nondestructive freshness evaluation models for chub mackerel (Scomber japonicus) fillets were developed using visible/near-infrared (Vis/NIR) hyperspectral imaging and multivariate regression analysis. Total 96 mackerel samples were investigated during 6 days of storage under five different conditions for measurement of pH, total volatile basic nitrogen (TVB-N), and K values along with acquisition of hyperspectral images. With partial least squares regression (PLSR) and support vector regression (SVR) along with wavelength selection method using Variables Importance in Projection (VIP) scores, performances of PLSR, VIP-PLSR, SVR, and VIP-SVR models were evaluated and compared. The VIP-PLSR models showed the best performance for predicting the freshness indicators, with R2 values of 0.86, 0.86, and 0.91 for pH, TVB-N, and K values, respectively. Furthermore, it was shown that the identification and removal of noise pixels from the hyperspectral data based on correlation analysis was effective in improving the regression results.

Enhancement of Small Ship Detection Using Polarimetric Combination from Sentinel−1 Imagery

Speckle noise and the spatial resolution of the Sentinel−1 Synthetic Aperture Radar (SAR) image can cause significant difficulties in the detection of small objects, such as small ships. Therefore, in this study, the Polarimetric Combination-based Ship Detection (PCSD) approach is proposed for enhancing small ship detection performance, which combines three different characteristics of polarization: newVH, enhanced VH, and enhanced VV. Employing the Radar Cross Section (RCS) value in three stages, the newVH was utilized to detect Automatic Identification System (AIS) -ships and small ships. In the first step, the adaptive threshold (AT) method was applied to newVH with a high RCS condition (>−10.36 (dB)) for detecting AIS-ships. Secondly, the first small ship target was detected with the maximum suppression of false alarms by using the AT with a middle RCS condition (>−16.98 (dB)). In the third step, a candidate group was identified by applying a condition to the RCS values (>−23.01 (dB)), where both small ships and speckle noise were present simultaneously. Subsequently, the enhanced VH and VV polarizations were employed, and an optimized threshold value was selected for each polarization to detect the second small ship while eliminating noise pixels. Finally, the results were evaluated using the AIS and small fishing vessel tracking system (V-Pass) based on the detected ship positions and ship lengths. The average matching results from 26 scenes in 2022 indicated a matching rate of over 86.67% for AIS-ships. Regarding small ships, the detection performance of PCSD was 42.27%, which was over twice as accurate as the previous Constant False Alarm Rate (CFAR) ship detection model. As a result, PCSD enhanced the detection rate of small ships while maintaining the capacity for detecting AIS-equipped ships.

Improved signature recognition system based on statistical features and fuzzy logic

Signature recognition system knows significant attention due to its undeniable importance. For this purpose, a wide-ranged techniques including both statistical and structural approaches, have been introduced. They are both subfields of machine learning that focus on identifying patterns in data.Statistical methodologies are extensively used within diverse domains, providing accurate features and deep understanding of data characteristics. In the proposed system, a statistical framework is adopted, which encompasses three crucial phases: preprocessing, feature extraction, and classification.In the initial stage, a variety of image preprocessing algorithms are employed to segregate signature pixels from background and noise pixels. The second phase consists of extracting the discriminant information based on statistical characteristics, this includes calculating white-black transitions horizontally, vertically, as well as diagonally and antidiagonally. The resulting features are employed as input for the fuzzy min-max classifier (FMMC), which involves iteratively creating hyperboxes. Each iteration comprises three phases: expansion, overlap, and contraction. The primary advantage of applying FMMC lies in its proficiency to handle noisy data and data with overlapping distributions, factors commonly observed in signature images.The proposed method is evaluated with various systems utilizing histogram of oriented gradient, profile projection, convolutional neural network, and Loci as feature extraction techniques, as well as K-nearest neighbors and multilayer perceptron as classification methods. The experimental findings confirm the effectiveness of the proposed framework, demonstrating its ability to achieve a notable accuracy of 99.16 %, along with remarkable average precision, recall, and F1-score values of 99.17 %, 99.24 %, and 99.16 % respectively.

Test measurements of an ASIC for X-ray material discrimination by using on-chip time domain integration and a CdTe sensor

Using time-domain integration (TDI) and a two-dimensional sensor is beneficial for X-ray imaging of moving objects. Applying on-chip instead off-chip TDI decreases the required data throughput between an ASIC and the backend several times [1]. This, in turn, allows us to significantly simplify the ASIC itself as well as the backend.We present the results of test measurements of an ASIC dedicated for X-ray material discrimination by using on-chip TDI and a CdTe sensor.The main part of the ASIC is an 192 × 64 pixel matrix. The pixel size is 100 μm × 100 μm, so the chip size is approximately 6.7 mm × 2 cm. The chip is manufactured in a 130 nm CMOS technology with 8 metal layers. A single pixel analog front-end consists of a charge-sensitive amplifier, a shaper, and three discriminators followed by counters. The test was conducted with a 0.75 mm thick CdTe sensor.First, we show the results of the discriminator offset correction followed by the evaluation of the pixel analog front-end gain and noise conducted with single energy radiation. Next, the results of moving objects imaging are obtained by using an industrial X-ray machine for food inspection (continuous energy spectrum). This is carried out to present an example of the image and evaluate the image signal to noise ratio for different energy discriminator thresholds, sensor bias voltages, detector module temperatures and object speeds.

Euclid: Improving the efficiency of weak lensing shear bias calibration

To obtain an accurate cosmological inference from upcoming weak lensing surveys such as the one conducted by Euclid, the shear measurement requires calibration using galaxy image simulations. As it typically requires millions of simulated galaxy images and consequently a substantial computational effort, seeking methods to speed the calibration up is valuable. We study the efficiency of different noise cancellation methods that aim at reducing the simulation volume required to reach a given precision in the shear measurement. The more efficient a method is, the faster we can estimate the relevant biases up to a required precision level. Explicitly, we compared fit methods with different noise cancellations and a method based on responses. We used GalSim to simulate galaxies both on a grid and at random positions in larger scenes. Placing the galaxies at random positions requires their detection, which we performed with SExtractor. On the grid, we neglected the detection step and, therefore, the potential detection bias arising from it. The shear of the simulated images was measured with the fast moment-based method KSB, for which we note deviations from purely linear shear measurement biases. For the estimation of uncertainties, we used bootstrapping as an empirical method. We extended the response-based approach to work on a wider range of shears and provide accurate estimates of selection biases. We find that each method we studied on top of shape noise cancellation can further increase the efficiency of calibration simulations. The improvement depends on the considered shear amplitude range and the type of simulations (grid-based or random positions). The response method on a grid for small shears provides the biggest improvement. Here the runtime for the estimation of multiplicative biases can be lowered by a factor of 145 compared to the benchmark simulations without any cancellation. In the more realistic case of randomly positioned galaxies, we still find an improvement factor of 70 for small shears using the response method. Alternatively, the runtime can be lowered by a factor of 7 already using pixel noise cancellation on top of shape noise cancellation. Furthermore, we demonstrate that the efficiency of shape noise cancellation can be enhanced in the presence of blending if entire scenes are rotated instead of individual galaxies.

Unbiased centroiding of point targets close to the Cramer Rao limit.

Systematic errors affecting center-of-gravity (CoG) measurements may occur from coarse sampling of the point-spread-function (PSF) or from signal truncation at the boundaries of the region-of-interest (ROI). For small ROI and PSF widths, these effects are shown to become dominant, but this can be mitigated by introducing novel unbiased estimators that are largely free of systematic error and perform particularly well for low photon numbers. Analytical expressions for the estimator variances, comprising contributions from photon shot noise, random pixel noise, and residual systematic error, are derived and verified by Monte Carlo simulations. The accuracy and computational speed of the unbiased estimators are compared to those of other common estimators, including iteratively weighted CoG, thresholded CoG, iterative least squares fitting, and two-dimensional Gaussian regression. Each estimator is optimized with respect to ROI size and PSF radius and its error compared to the theoretical limit defined by the Cramer Rao lower bound (CRLB). The unbiased estimator with full systematic error correction operating on a small ROI [3×3] emerges as one of the most accurate estimators while requiring significantly less computing effort than alternative algorithms.

Evaluation of afforestations for avalanche protection with orthoimages using the random forest algorithm

Afforestations provide cost-effective and environmentally friendly protection against natural hazards, compared to technical measures. In Austria, more than 3000 afforestation sites for hazard protection covering 9000 ha have been established between 1906 and 2017, mainly for snow avalanche protection. The actual protective effect depends on avalanche predisposing factors and land cover, i.e. whether forest is present. In this study, predisposing factors and land cover classes were identified and analysed in selected afforestation sites. The protective effect of forest was attributed to the presence of forest cover and tree species. Using RGB images with a ground resolution of 20 × 20 cm, nine land cover categories have been distinguished by means of supervised classification with the random forest algorithm. Those land cover categories were classified with an overall accuracy of 0.87–0.98 and Kappa-values, ranging between 0.81 and 0.93. Images were filtered using a 3 pixel by 3 pixel majority filter, which assigns each cell in the output grid the most commonly occurring value in a moving window centred on each grid cell. This filter further increased the overall accuracy by removing noise pixels while preserving the fine elements of the classified grid. Our results indicate a protective effect for about half of the analysed afforestation sites. The dominance of the land use class “Meadow” at most sites with little avalanche protection effect suggests grazing as a limiting factor. The spatial information provided with the described method allows to identify critical areas in terms of avalanche protection even years after the initial afforestation.

Enhanced Global Image Segmentation: Addressing Pixel Inhomogeneity and Noise with Average Convolution and Entropy-Based Local Factor

Enhanced Global Image Segmentation: Addressing Pixel Inhomogeneity and Noise with Average Convolution and Entropy-Based Local Factor

Two‐step morphology‐based denoising and non‐local means smoothing improves micro‐computed tomography digital rock images

AbstractDigital rock physics is a workflow that relies on imaging techniques to quickly and cost‐effectively estimate the petrophysical properties of small core samples taken from reservoirs. By using digital representations of rock samples as input, physics‐based simulators can estimate properties such as porosity and permeability. The accuracy of these estimates depends on the quality of the digital volumes generated from micro‐computed tomography scans. To enhance the accuracy, denoising is necessary to reduce image noise caused by various experimental factors like electronic noise and bad pixels. This study introduces a novel two‐step denoising pipeline that combines adaptive morphological filtering with non‐local means smoothing, ensuring both noise reduction and preservation of edges. The effectiveness of the proposed pipeline is assessed through qualitative evaluation using optimal segmentation results and quantitative evaluation using a non‐reference metric and equivalent number of looks. Comparing the results of the two‐step approach with traditional non‐local means and morphology‐based filtering using a multi‐resolution structurally varying bitonic filter, the non‐reference metric and equivalent number of looks values are higher, indicating improved denoising performance. Furthermore, the denoised rock volume is subjected to the next step in the digital rock workflow to compute important petrophysical properties like porosity and permeability. The findings indicate that our proposed pipeline significantly improves the accuracy of estimating physical parameters such as porosity and permeability.

Extraction of Actual Faults with Adjusting the Pixel Width Parameter to Remove Undesired Noise Pixels in the Image (RPW)

Image Denoising, Deblurring, and Enhancement techniques are most commonly used on the images to reduce or completely remove the noise. The noisy images are not capable of perfectly using the solution of the desired problems such as object edge detection, object segmentation, and object classification. Because the edges of these objects have much bluer or more noise pixels for clearly stable detection. The main motivation of this study is to solve the problem of detection and elimination of the undesired noisy pixels on the encountered images. These noisy pixels are needed to be removed from the obtained images which are the results of throughout determined image processing steps. The main reason for this study motivation come out that to find the actual inscription fault has some noisy (undesired) pixels when extracting the true difference between the two images has been subtracted from each other. The subtracted image results are used in the inscription inspection process that controls the accuracy of the inscription quality. In the inscription inspection process, subtracted image results are used to determine the accuracy of the inscription quality. These subtracted images are formed by subtraction from each other of reference images and sample images. In these subtracted images if truly exist inscriptions faults or sometimes that could be occurred undesired noisy pixels at the same time in the subtraction process. This study focused on detecting and eliminating the undesired noisy pixels in order to reach actual inscription faults in the images. Thus, the remove pixels as width algorithm (RPW) has been developed and applied to these specified images.