Median Filtering Algorithm Research Articles

Improved Early-Stage Maize Row Detection Using Unmanned Aerial Vehicle Imagery

Monitoring row centerlines during early growth stages is essential for effective production management. However, detection becomes more challenging due to weed interference and crop row intersection in images. This study proposed an enhanced Region of Interest (ROI)-based approach for detecting early-stage maize rows. It integrated a modified green vegetation index with a dual-threshold algorithm for background segmentation. The median filtering algorithm was also selected to effectively remove most noise points. Next, an improved ROI-based feature point extraction method was used to eliminate residual noises and extract feature points. Finally, the least square method was employed to fit the row centerlines. The detection accuracy of the proposed method was evaluated using the unmanned aerial vehicle (UAV) image data set containing both regular and intersecting crop rows. The average detection accuracy of the proposed approach was between 0.456° and 0.789° (the angle between the fitted centerline and the expert line), depending on whether crop rows were regular/intersecting. Compared to the Hough Transform (HT) algorithm, the results demonstrated that the proposed method achieved higher accuracy and robustness in detecting regular and intersecting crop rows. The proposed method in this study is helpful for refined agricultural management such as fertilization and irrigation. Additionally, it can detect the missing-seedling regions and replenish seedings in time to increase crop yields.

Traditional landscape painting and art image restoration methods based on structural information guidance

Abstract In the field of traditional landscape painting and art image restoration, traditional restoration methods have gradually revealed limitations with the development of society and technological progress. In order to enhance the restoration effects of Chinese landscape paintings, an innovative image restoration algorithm is designed in this research, combining edge restoration with generative adversarial networks (GANs). Simultaneously, a novel image restoration model with embedded multi-scale attention dilated convolution is proposed to enhance the modeling capability for details and textures in landscape paintings. To better preserve the structural features of artistic images, a structural information-guided art image restoration model is introduced. The introduction of adversarial networks into the repair model can improve the repair effect. The art image repair model adds a multi-scale attention mechanism to handle more complex works of art. The research results show that the image detection model improves by 0.20, 0.07, and 0.06 in the Spearman rank correlation coefficient, Pearson correlation coefficient, and peak signal-to-noise ratio (PSNR), respectively, compared to other models. The proposed method outperforms mean filtering, wavelet denoising, and median filtering algorithms by 6.3, 9.1, and 15.8 dB in PSNR and by 0.06, 0.12, and 0.11 in structural similarity index. In the image restoration task, the structural similarity and information entropy indicators of the research model increase by approximately 9.3 and 3%, respectively. The image restoration method proposed in this study is beneficial for preserving and restoring precious cultural heritage, especially traditional Chinese landscape paintings, providing new technological means for cultural relic restoration.

Detection of Road Risk Sources Based on Multi-Scale Lightweight Networks.

Timely discovery and disposal of road risk sources constitute the cornerstone of road operation safety. Presently, the detection of road risk sources frequently relies on manual inspections via inspection vehicles, a process that is both inefficient and time-consuming. To tackle this challenge, this paper introduces a novel automated approach for detecting road risk sources, termed the multi-scale lightweight network (MSLN). This method primarily focuses on identifying road surfaces, potholes, and scattered objects. To mitigate the influence of real-world factors such as noise and uneven brightness on test results, pavement images were carefully collected. Initially, the collected images underwent grayscale processing. Subsequently, the median filtering algorithm was employed to filter out noise interference. Furthermore, adaptive histogram equalization techniques were utilized to enhance the visibility of cracks and the road background. Following these preprocessing steps, the MSLN model was deployed for the detection of road risk sources. Addressing the challenges associated with two-stage network models, such as prolonged training and testing times, as well as deployment difficulties, this study adopted the lightweight feature extraction network MobileNetV2. Additionally, transfer learning was incorporated to elevate the model's training efficiency. Moreover, this paper established a mapping relationship model that transitions from the world coordinate system to the pixel coordinate system. This model enables the calculation of risk source dimensions based on detection outcomes. Experimental results reveal that the MSLN model exhibits a notably faster convergence rate. This enhanced convergence not only boosts training speed but also elevates the precision of risk source detection. Furthermore, the proposed mapping relationship coordinate transformation model proves highly effective in determining the scale of risk sources.

Evaluation of Denoising Performance of ResNet Deep Learning Model for Ultrasound Images Corresponding to Two Frequency Parameters.

Ultrasound imaging is widely used for accurate diagnosis due to its noninvasive nature and the absence of radiation exposure, which is achieved by controlling the scan frequency. In addition, Gaussian and speckle noises degrade image quality. To address this issue, filtering techniques are typically used in the spatial domain. Recently, deep learning models have been increasingly applied in the field of medical imaging. In this study, we evaluated the effectiveness of a convolutional neural network-based residual network (ResNet) deep learning model for noise reduction when Gaussian and speckle noises were present. We compared the results with those obtained from conventional filtering techniques. A dataset of 500 images was prepared, and Gaussian and speckle noises were added to create noisy input images. The dataset was divided into training, validation, and test sets in an 8:1:1 ratio. The ResNet deep learning model, comprising 16 residual blocks, was trained using optimized hyperparameters, including the learning rate, optimization function, and loss function. For quantitative analysis, we calculated the normalized noise power spectrum, peak signal-to-noise ratio, and root mean square error. Our findings showed that the ResNet deep learning model exhibited superior noise reduction performance to median, Wiener, and median-modified Wiener filter algorithms.

Removal of salt and pepper noise using adaptive switching modified decision-based unsymmetric trimmed median filter optimized with Hyb-BCO-FBIA

An intriguing area in the IP (image processing) is the recovery of noisy photographs from the noise caused by the salt and pepper. As the mistake rate rises and the image format varies, the issue with the current task does not go away. In this study, Salt and Pepper Denoising, Hybrid Balancing Composite motion Optimization with Adaptive Switching Modified Decision based Unsymmetric Trimmed Median Filter and Forensics-Based Investigation Algorithm is proposed (R-SPN-ASMD-UTMF-Hyb-BCO-FBIA). Initially, the input images are obtained from boat-types-recognition dataset, cat-breeds-dataset, cars-image-dataset, butterfly-images 40-species dataset and birds-200 dataset. The images are pre-processed through an ASMD-UTMF filter. ASMD-UTMF does not expose any adoption of optimization systems to calculate the optimal parameters. Therefore, the proposed Hyb-BCO-FBIA is employed for optimizing the ASMD-UTMF weight parameters. The suggested system is implemented on MATLAB and the assessment metrics as Mean Square Error (MSE), Structural similarity index measurement (SSIM), Peak signal to noise ratio (PSNR), Normalized cross-correlation (NC), Image Enhancement Factor (IEF), Mean Square Error (MSE) are analysed. The proposed method attains higher PSNR, NC related with other SOTA (State-Of-The Art) methods.

Molten pool image processing and quality monitoring of laser cladding process based on coaxial vision

Aiming at the problems of the traditional detection method of cladding quality in laser cladding process, which relies on experience, has low accuracy and long recognition time, a method based on the image area of molten pool is proposed to detect cladding quality. Firstly, the median filter algorithm with dynamic adjustment of filter window is used to reduce noise and the iterative threshold segmentation algorithm is used to separate the molten pool from the boundary, then the edge of the molten pool is extracted by Canny algorithm which can adaptively change the high and low thresholds and finally the area value of the molten pool is obtained according to the correspondence between the pixel value and the actual value. The relationship between three key factors (nozzle angle, scanning speed and laser power) and molten pool area is analyzed to achieve favorable cladding quality. The results show that the influence of nozzle angle on the molten pool area is anisotropic. And the molten pool area decreases monotonically with the increase of scanning speed, while the higher velocity will destroy the formation of the molten pool. In addition, with the increase of laser power, the expansion of molten pool area is intensified. At the same time, the analysis of the change of molten pool area over time can quickly and accurately detect the three defects (protrusion, depression, and slag inclusion) in the process of cladding.

ICIF: Image fusion via information clustering and image features.

Image fusion technology is employed to integrate images collected by utilizing different types of sensors into the same image to generate high-definition images and extract more comprehensive information. However, all available techniques derive the features of the images by utilizing each sensor separately, resulting in poorly correlated image features when different types of sensors are utilized during the fusion process. The fusion strategy to make up for the differences between features alone is an important reason for the poor clarity of fusion results. Therefore, this paper proposes a fusion method via information clustering and image features (ICIF). First, the weighted median filter algorithm is adopted in the spatial domain to realize the clustering of images, which uses the texture features of an infrared image as the weight to influence the clustering results of the visible light image. Then, the image is decomposed into the base layer, bright detail layer, and dark detail layer, which improves the correlations between the layers after conducting the decomposition of a source graph. Finally, the characteristics of the images collected by utilizing sensors and feature information between the image layers are used as the weight reference of the fusion strategy. Hence, the fusion images are reconstructed according to the principle of extended texture details. Experiments on public datasets demonstrate the superiority of the proposed strategy over state-of-the-art methods. The proposed ICIF highlighted targets and abundant details as well. Moreover, we also generalize the proposed ICIF to fuse images with different sensors, e.g., medical images and multi-focus images.

ECG R-Wave Detection and Its Application in Left Ventricular Assist Device

Heart failure is one of the major diseases endangering human life. As a transitional support treatment before heart transplantation, the left ventricular assist device (LVAD) has significantly improved the quality of life and survival rate of patients with end-stage heart failure. In the automatic detection of electrocardiogram (ECG), the detection of QRS wave groups is the most critical aspect, which affects the correctness and accuracy of subsequent data analysis and processing. The paper used the data from the MIT-BIH database and the data collected from human ECG as the original number of samples for further processing. It processed the data through a high-order finite impulse response (FIR) low-pass filter and Shannon energy algorithm, and added the use of a high-order adaptive median filter algorithm on a field programmable gate array (FPGA) to minimize the noise of the processed real-time data. Finally, the tested ECG R-wave was used to drive the LVAD. After successful simulation by MATLAB and Modelsim software, the scheme of the real-time ECG signal controlling blood pump system was realized on the FPGA platform. The experiment showed that the method proposed could accurately extract the R-wave and control the LVAD to pump blood simultaneously.

Extended neighborhood-based road and median filter for impulse noise removal from depth map

In recent years there has been growing interest in the study of depth map's impulse noise detection and removal. The Rank-ordered Absolute Differences (ROAD) based on neighborhood statistics can effectively detect impulse noise for RGB images. However, since the statistical object of the ROAD is each pixel value in the neighborhood, and the neighborhood may contain other impulse noise, invalid depth zero-pixel points and other singular points, especially for large areas with depth missing, it is difficult for the algorithm to ensure the correctness and accuracy of the detection results. Therefore, the ROAD algorithm is not fully applicable to depth maps. Similarly, the median filter, as an effective impulse noise filtering algorithm, also has the same deficiency, so it is not suitable for areas in depth maps with no depth value. To address these issues, we present here an Extended Neighborhood-based ROAD and Median Filter algorithm to remove impulse noise from depth map. This approach improves the functionality of the ROAD algorithm and the Median Filter by extending the neighborhood of the current pixel adaptively, shielding zero-valued pixels and filtering out detected impulse noises in real time during detection, therefore effectively improving the accuracy of impulse noise filtering. It consequently reduces the miss rate and the error detection rate, and ultimately achieves a better edge-preserving and denoising effect. Our empirical evidence shows that the proposed algorithm outperforms existing denoising algorithms on both quantitative measures and visual perception qualities.

Improving the stability of electrostatic induction dust concentration detection using kalman filtering algorithm aided by machine learning

The suspended dust produced in the production of process industry may cause damage to occupational health and even trigger explosion accidents. To accurately detect the dust concentration, and to reduce the noises and standard deviation volatility of the inductive signal of characterized dust concentration generated when applying the electrostatic induction method, the study designs the Kalman filter based on a machine learning algorithm and realizes secondary processing of the standard deviation of inductive signal. Firstly, this study designs the dust concentration detection device using the electrostatic induction method, realizing an effective extraction and amplification of the dust inductive signal, confirming a positive correlation between the volatility of the inductive signal and dust concentration. A data processing procedure for the inductive signal is also designed. To eliminate the standard deviation volatility of inductive signal, the Kalman filter aided by machine learning is selected to process mathematical models. By comparing the conventional sliding filter algorithm, median filter algorithm and Kalman filtering aided by machine learning, it is confirmed that Kalman filtering aided by machine learning has a better effect on reducing the standard deviation of inductive signal. The standard deviation can be quickly converged to the target value through short-term iteration, effectively eliminating the fluctuation of the standard deviation value of the inductive signal, and improving the stability of the standard deviation value of the inductive signal.

1D recursive median filter based passive islanding detection strategy for grid‐connected distributed generations network

AbstractIn modern distribution networks, integration of distributed generations (DGs) at consumer premises is common. However, islanding detection in such a grid‐tied distributed generation (GTDG) network is the topmost challenge to ensure power quality and reliable operation. This paper presents a modified passive islanding detection scheme (MPIDS) for the GTDG network, using a One‐D recursive Median filter (ODRMF) algorithm. Firstly, at the point of common coupling (PCC), 3‐phase voltage is acquired. Next, the ODRMF is employed to extract 3rd harmonic and residuals from the acquired voltage signal. Afterward, two novel islanding detection indices developed are: (1) First change detection (FCD), which is calculated from the residuals, and (2) delta selected harmonic distortion (∆SHD), which is computed from 3rd harmonic content of the voltage signal. Finally, variations in the two indices are compared with the threshold to identify islanding. To validate the efficacy of the presented MPIDS, rigorous simulations in MATLAB/ Simulink are conducted on the UL‐1741 and IEEE 13‐bus GTDGs systems under different conditions. The results illustrate that the presented strategy is highly reliable in all assessed conditions and can detect the islanding as well as non‐islanding incidents effectively under balanced and unbalanced load/generation conditions with a very low non‐detection zone.

Analysis and Comparison of Image Enhancement Techniques for Improving PSNR of Liver Images by Linear Contrast Algorithm over Median Filtering

Aim: The goal of this research is to reduce noise present in the liver images in order to enhance it using linear contrast and median filters. And also to analyze output of both the filters based on its Peak Signal to Noise Ratio (PSNR). Materials and Methods: The research includes two groups; each group has a sample size of 20. Grayscale medical images collected from the kaggle website were used in this research. Samples were considered as (N=20) for guided filter and (N=20) for fast bilateral filter with total sample size 40 calculated using clinicalc.com. For this study, the affected and normal liver images were collected from the Kaggle website. Then the linear filtering, median filtering algorithms were executed using Matlab software. Sample size was calculated using clinicalc.com, and the comparison analysis has been carried out through SPSS software. This research contains two groups, with a Gpower of 80 percent. The performance of the novel median filter is evaluated and the performance measure PSNR is compared with the linear contrast filter. Result: Based on Matlab simulation results, the PSNR of novel median filters is 76.0355 and linear contrast filters have PSNR of 57.1785. From the statistical analysis, it is observed that the significant value of PSNR (Peak Signal to Noise Ratio) (0.409) and p>0.05. Conclusion: This study reveals that for the medical image enhancement purpose the novel median filter provides better PSNR than the linear contrast algorithm on ultrasound liver images.

Analysis and Comparison of Image Enhancement Techniques for Improving PSNR of Liver Images by Median Filtering over Mask Filtering

Aim: The goal of this research is to employ median filters and mask filters to reduce noise in liver images so that they can be improved. In addition, the Peak Signal to Noise Ratio of both filters’ outputs was examined (PSNR). Materials and Methods: The afflicted and normal liver photos were obtained from the Kaggle website for this investigation. Then, using Matlab software, the mask filtering and median filtering algorithms were run. Clinicalc. com was used to compute sample size, and SPSS software was used to conduct the comparative analysis. This study has two groups, each with a sample size of 20 people with an average G power of 80%. The innovative median filter’s performance is assessed, and the PSNR performance metric is compared to that of the mask filter. Results: The PSNR of innovative median filters is 64.0310, while mask filters have a PSNR of 78.0095, according to Matlab simulation data. The significant value of PSNR (Peak Signal to Noise Ratio) (0.409) and p>0.05 was found in the statistical analysis. Conclusion: The innovative median filter delivers greater PSNR than the mask filter for medical image enhancement on ultrasound liver pictures, according to this study.

A Novel Medical Image Enhancement Algorithm for Breast Cancer Detection on Mammography Images Using Machine Learning.

Mammography is the most preferred method for breast cancer screening. In this study, computer-aided diagnosis (CAD) systems were used to improve the image quality of mammography images and to detect suspicious areas. The main contribution of this study is to reveal the optimal combination of various pre-processing algorithms to enable better interpretation and classification of mammography images because pre-processing algorithms significantly affect the accuracy of segmentation and classification methods. In this study, the effect of combinations of different preprocessing methods in differentiating benign and malignant breast lesions was investigated. All image processing algorithms used for lesion detection were used in the mini-MIAS database. In the first step, label information and pectoral muscle resulting from the acquisition of mammography images were removed. In the second step, median filter (MF), contrast limited adaptive histogram equalization (CLAHE), and unsharp masking (USM) algorithms with different combinations of the resolution and visibility of images are increased. In the third step, suspicious regions are extracted from the mammograms using the k-means clustering technique. Then, features were extracted from the obtained ROIs. Finally, feature datasets were classified as normal/abnormal, and benign/malign (two class classification) using Machine Learning algorithms. Test performance measures of the classification methods were examined. In both classifications made in the study, lower classification performance values were obtained when the CLAHE algorithm was used alone as a pre-processing method compared to other pre-processing combinations. When the median filter and unsharp masking algorithms are added to the CLAHE algorithm, the performance of the classification methods has increased. In terms of classification success, Support Vector Machines, Random Forest, and Neural Networks showed the best performance. It was found by comparing the performances of the classification methods that different preprocessing algorithms were effective in detecting the presence of breast lesions and distinguishing benign and malignant.

Detection of Signal and Ground Photons From ICESat-2 ATL03 Data

The Advanced Topographic Laser Altimeter System (ATLAS) laser altimeter aboard the Ice, Cloud, and Land Elevation Satellite (ICESat-2) can measure the elevation of the Earth’s surface with unprecedented spatial detail. However, the quality of the derived signal and ground photons depends on the signal-to-noise ratio and canopy coverage. Current algorithms underperform for data collected during daytime over mountain areas with dense canopy. We demonstrate a novel procedure for signal photon detection and subsequent ground photon detection from ICESat-2 ATL03 data. We first introduce a gravity-based density model to characterize the anisotropic properties of photon distribution. Through jointly using the photon densities from the weak–strong beam pair, we are able to find key photons that have high probability being signals. A directional regional growing approach then takes these key photons as seeds to label all remaining signal photons. Finally, we introduce a weighted iterative median filter (WIMF) algorithm to identify ground photons whose height is closest to the estimated ground surface. A total of 36 ATL03 beams of two entire counties in USA are used for test and evaluation. Compared to the ATL03 and ATL08 algorithms, our signal photon finding method is more robust to the variation of topography, canopy coverage, and data collection time. Remarkably, the mislabeling caused by the after-pulsing effect does not present in our detected signal photons. Comparing current ATL03 and ATL08 products, the detected ground photons from our method are more consistent with reference to the 3DEP DEM, especially for strong beam data collected during daytime in dense canopy, high relief areas.

PCB defect detection system based on image processing

Under the background of intelligent manufacturing, the quality inspection of printed circuit board (PCB), as the carrier of electronic products, plays an important role. In view of the shortcomings of existing traditional detections, this paper has put forward a PCB detection method based on machine vision, focusing on image preprocessing algorithm and detection analysis. The median filter algorithm was used to remove the noise in the image. Logarithmic transformation was used to enhance image contrast. Sobel operator was used for edge detection to obtain the geometric center of the defect area. On this basis, the PCB image was registered by template matching method, and the difference between the preprocessed PCB image to be tested and the standard PCB image was calculated to get the difference map. Subsequently, morphological algorithm was used to remove the slight differences and obtain the defect map. In the end, the simulation results have shown that the proposed algorithm has good detection effect and high precision in PCB defect detection.

Digital processing of one-dimensional signals based on the median filtering algorithm

Wydawnictwo SIGMA-NOT wydaje czasopisma fachowe informujące swoich czytelników o najnowszych osiągnięciach naukowych i nowoczesnych rozwiązaniach technicznych w Polsce i na świecie, popularyzuje problemy techniczne oraz poszerza wiedzę i kulturę techniczną.

A boost converter‐based MPPT steady‐state oscillation‐free fast tracking control strategy for photovoltaic power systems

With the conventional perturbation and observation (P&O) method, photovoltaic (PV) converters have long maximum power point (MPP) tracking times and three-point oscillations at the steady state that can lead to output power losses and inefficiencies in grid connections. To overcome these drawbacks, a fast tracking and steady-state-oscillation-free control strategy is proposed. The strategy first stores four random duty cycle values on the basis of the duty cycle variation characteristics of the PV panel power adjustment, then calculates the odd and even duty cycle difference and judges the steady state by varying the duty cycle difference threshold. The strategy next obtains the MPP duty cycle using a median filtering algorithm (MFA) to suppress the steady-state oscillation and improves the tracking speed by resetting the appropriate duty cycle step according to the slope of the PV curve of the PV panel output and the corresponding adaptive coefficients. The proposed algorithm was simulated and experimentally validated under various irradiance conditions, and the results show that the algorithm can improve the PV panel output efficiency compared to both the conventional P&O and the adaptive P&O methods.

Machine learning modeling and prediction of peanut protein content based on spectral images and stoichiometry

For rapid nondestructive detection of peanut protein content, an experimental method combining hyperspectral imaging technology and spectrophotometry was proposed. For data redundancy and noise analysis, ten algorithms were selected for feature extraction, and revealed that the optimal characteristic band of protein content was between 400 and 550 nm. According to the results, the median filtering algorithm (MF) was used to preprocess original spectral data, the XGBoost algorithm was used to extract the top 30 feature bands, the Ridge algorithm was used to construct the protein content prediction model, and the protein content physicochemical data were measured by spectrophotometry. The optimal model was MF-XGBoost-Ridge, with hyperparameter α tuning by Optuna algorithm, with RMSE = 0.009, and a correlation R = 0.886 with a fitting time of only 0.02 s. Compared with the traditional machine learning algorithm models, the prediction accuracy of this study was high and the fitting time was short.

Intelligent Recognition Technology for the Segmentation of Traffic Indication Images Concerning Different Pavement Materials.

Traffic indication is an important part of the road environment, providing information about road conditions, restrictions, prohibitions, warnings, and the current status related to the flow of the traffic and other navigational aspects. The shape, color, and pictogram of a traffic indication are encoded into the visual characteristics of traffic signs. Not paying attention to these traffic signs could lead directly or indirectly to traffic accidents. In this article, the support traffic indication vector recognition (STIVR) method is proposed to classify the best signal detection to avoid traffic congestion and accidents. The proposed STIVR recognizes the traffic indication system automatically, reduces occurrences of traffic accidents, and helps drivers move safely on different pavement materials. Besides, the adaptive median filter (AMF) algorithm is used to pre-process and protect the traffic indication images without obscuring them. Thus, it indicates the edge of the non-smoothed nasty ferment from the service. In the detection of traffic events, indication images are enhanced, pre-treated, and divided according to symbols and their characteristics such as color, shape, or both. The output becomes a segmented image, including the available space identified as a road sign. The experimental results show that the proposed method functions well; achieves a sufficiently higher process speed and better segmentation of traffic indications and more accuracy in recognition of the objects. For example, the proposed method reaches a higher sensitivity performance of 96%.