Digital Image Processing Methods Research Articles

Yapılarda Bozulma ve Nem Hasarının Dijital Görüntü İşleme Yöntemi ile Tespiti

Resolving building physics damages is of great importance in terms of the healthy functioning of the building and its sustainability. The first thing to be done in this direction, the correct determination of the damages, is the most important step in order to solve the problems. It directly adds to the smooth progress of the repair work and the cost of the repair. Trying to detect building physics problems with the naked eye involves subjective judgments, and destructive methods damage the structure. In this study, it is aimed to detect moisture damage/deterioration in buildings in a non-destructive and objective way by using digital image processing method, which is one of the artificial intelligence applications. 3.600 image data of damaged states taken from the surfaces of different structures were subjected to machine learning using convolutional neural network architecture and the test data were classified and the application results were obtained. As a result of the validity test, it was observed that the method was effective on moisture damage and deterioration, and achieved a high accuracy rate. With this study, it is revealed that artificial intelligence applications used in various fields today can be used to detect moisture damage and deterioration, which is one of the building physics problems.

Crop Disease Source Location and Monitoring System Based on Diffractive Light Identification Airborne Spore Sensor Network

Traditional methods based on the Internet of Things (IoT) or IoT methods based on microscopic imaging are difficult to automatically realize early warning of crop diseases. In this article, a diffraction imaging IoT system based on spore detection is proposed to indirectly monitor crop diseases instead of directly taking crop disease images. Multiple NB-IoT nodes are deployed to build an IoT system to realize the judgment of spore diffraction image transmission, which is based on the detection of environmental temperature and humidity. The method of digital image processing is applied to filter out impurities and count microparticles with the accuracy of 85%. By obtaining the number of spores in different positions, the microparticles diffusion model is established to study the law of microparticles transmission in specific space. According to the diffusion model, the weighted centroid and particle filter algorithm are applied to locate the particle source in windless and windy conditions. Thirteen nodes are arranged in a 2 m <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times $ </tex-math></inline-formula> 2 m laboratory to carry out the experiment. The maximum error in windless and windy conditions is 0.18 and 0.35 m. Compared with the traditional microscopic imaging-based IoT method, the detection limit of the proposed diffraction imaging method is 1/50. It provides inspiration for the IoT in the early detection and disease location of crop diseases.

Vehicle Detection in a Video Frame Using Machine Learning Technology

Motion tracking is one of the most active research titles of the computer vision concepts. Vehicle detection process on road are used for vehicle tracking, counts, traffic analysis and vehicle categorizing objectives and it can be implemented under different environments changes. Vehicle counting process provides appropriate information about traffic flow, and the vehicle crash occurrences and also traffic peak times in roadways[2]. Analysis of traffic may account traffic and also streamline the process, Analysis of traffic may account for the number of vehicles in an area per some time period[1]. Most of the design involve use of sensors to detect the vehicles. As it is a detection of vehicle in a video frame it uses the algorithms like Gaussian Mixture Model background subtraction it is a widely used approach for foreground detection. By the digital image processing methods which including object detection, edge detection, frame differentiation and kalman filter using the different library and algorithm with real time image[2]. This paper describes the detection of vehicle in a video frame, tracking in the video frame, counts the number of vehicle passes through the indicative line in roadways.

A robust digital image processing method for measuring the planar burr length at milling

The burr formation is one of the difficulties at the cutting processes; moreover, its size and characteristics show changes along the edge; therefore, it is hard to measure. The main aim of the paper is to develop a novel algorithm that is suitable for measuring the planar burr length of such contours that cannot be scanned below. The proposed method uses a digital microscope attached to a machine tool and using existing image processing algorithms in combination with novel approaches. The advantage of the current method is that, it allows collecting the height of burr along the workpiece automatically since it is able to handle and avoid interruptions, branches and provide uniform thickness for the determined contour. Another advantage is the extended measurement ability for workpieces which contains inner contours and cannot be illuminated from below. The method was tested with sample images and also with face milling experiments, and the results were validated with the data originating from a coordinate measurement machine. The result shows a good agreement at the validation. The available accuracy mainly depends on the applied measuring equipment (resolution and magnification of camera) and set up. The theoretical accuracy of the proposed method can even approximate the magnitude of the pixels. In this research work, the achieved accuracy was ±0.06 mm in the best case, and ±0.1 mm in the worst case with the used experimental device.

Image-processing-based model for the characterization of surface roughness and subsurface damage of silicon wafer in diamond wire sawing

The damages of silicon wafer in diamond wire sawing have a significant impact on its mechanics, economy, and use properties, which should be evaluated accurately and quickly. A theoretical model is developed to determine the surface roughness Rz (ten-point mean height) and subsurface damage (SSD) depth by the fracture width of silicon wafer. The model takes into account the scratch groove direction and material pile-up effect of silicon wafer. A digital image processing method is integrated into the model to extract the fracture parameters of silicon wafer. Many silicon wafers are processed under different slicing parameters, for which the fracture parameters and surface roughness Rz are measured by confocal microscopy, and the SSD depth is measured with the method of cross-section scanning microscopy. The scratch-induced material pile-up height is evaluated by nanoscratching. The calculated and measured fracture parameters, surface roughness Rz, and SSD depth are analyzed by contrast. The result shows that the model can accurately and quickly determine the surface roughness Rz and SSD depth with an average relative error of less than 12.0% in 20 s. The distribution characteristics of fractures, surface roughness, and SSD are analyzed. The result shows that more fractures have relatively smaller fracture width, depth, length, or related SSD depth. The image-processing-based model would be a reasonable approach for estimating the damages in silicon wafers during wire sawing.

Integration of geographic information technologies and digital image processing for responding to emergency situations at oil pipeline transportation facilities

In this article, we consider an approach to integrating geoinformation technologies and digital image processing methods aimed at increasing the efficiency of computer technologies in controlling complex distributed systems (CDS) in emergency situations. The analysis is conducted using an example of the activity of oil pipeline transport enterprises, including pipelines, oil pumping stations, administrative, repair and emergency response units. The novelty of the proposed version of integration of geoinformation technologies and digital image processing consists in the application of a set-theoretic approach to a uniform formal description of various types of spatial data, digital images and their interrelationships necessary for constructing three-dimensional models of production facilities of CDS. This has allowed criteria, composition and structure of these 3D models to be defined using different levels of detail of the object models in order to reduce the computational load and speed up the 3D visualization of objects of CDS. These are necessary to support the decision-making when responding to certain types of emergency situations. The advantage of the proposed approach is that it increases the efficiency of decision-making support in countering some emergencies, which, among others, is achieved through the use of three-dimensional visualization of technological and operational (obtained in the event of an accident) information about the production facilities of the CDS, whereas the quality and fullness of the optimized 3D model directly affect the decisions made in response to the emergencies. The developed methods and algorithms have been practically implemented when building 3D geoinformation models.

Green Path Project Develops Using Image Processing

Abstract: The Green Path project develops Image Processing which includes changing the nature of an image in the order to improve its pictorial information for human interpretation, for autonomous machine perception. In digital image processing, image is converted to an array of small integers, called pixels, representing a physical quantity such as scene radiance, stored in a digital memory, and processed by computer. Interest in digital image processing methods is in two principal applications areas: first one is improvement of pictorial information for human interpretation; and second one is processing of image data for storage, transmission, and representation for image or machine. Edge detection is one of the most difficult tasks in image processing hence it is a problem of fundamental importance in image processing method. In this paper we find out different steps of digital image processing. Like, a high-speed filter implementation is presented. Then Filter solves the purpose of removing the impulse noise from the image and reducing distortion in the image. The Image Processing is very important in the project. Then indicate a specific spot required for pointing to show the main spot for empty places. So, we required to divide the image pixelization points and coloring into different parts. And last one spotted the spot which is very important for project. Image processing is a method to perform operations on an image to extract information from it or enhance it. Digital image processing has a broad range of applications such as image restoration, medical imaging, remote sensing, image segmentation, etc. Every process requires a different technique. Keywords: Image Processing, scene radiance

Disease Prediction Using Machine Learning and Deep Learning

Abstract: Health being the state of complete physical and mental wellbeing is an imperative part of humankind .Healthcare sector been a capital incentive sector having complicated entry barrier for investors like acquiring land for making hospital, stamp duties on it, human resource crunch which further act as roadblock for the government in providing universal good healthcare services to its citizenry . In this regard artificial intelligence is leading to disruption in the healthcare sector which is helping poor in safeguarding them from been exploited by extravagant out of pocket expenditure on unnecessary medical checkups and treatments and providing them on time health services. Moreover the compartmentalization of healthcare services between centre and state as it been the state subject in 7 schedule of Indian Constitution further make the task more discommoded. Artificial Intelligence finds a lot of applications in the healthcare sector which includes cancer detection, diabetes detection, heart disease detection, Malaria detection, Kidney disease detection and a lot more. So, leveraging on the opportunities thrown by the COVID and keeping in view the relaxations in Telehealth regularisation in the law of land by the government with taking silence bias in consideration we are developing a ecosystem for non communicable disease which can be use by a person with restricted medical knowledge as well as in ease of their home thereby making early disease detection and diagnosis handy. Therefore, disease must automatically be detected with higher precision if we provide the necessary inputs to our web solution so as to benefit user that are reluctant to visit hospital on the onset of minor symptoms .It will also helps in easing patient load on the doctor, healthcare system as our solution can give a basic idea of severity of the disease to the patient treating doctor by means of image processing technology at an early stage. It consists of image capturing, preprocessing images, image segmentation, extraction of features and disease classification. The digital image processing method is one of those strong techniques used far earlier than human eyes could see to identify the tough symptoms. There is a great demand for such a solutions in the world of today which would enable to detect disease earlier. We have proposed in this study a system where the web application can detect various type of disease namely cancer, diabetes, heart, liver, kidney diseases, malaria, pneumonia this may be done if the associated disease parameters are known properly. Keywords: Disease Detection, Artificial Intelligence, Healthcare, Machine Learning, Convolutional Neural Networks.

AUTOMATIC EXTRACTION OF FACADES AND WINDOWS FROM MLS POINT CLOUDS USING VOXELSPACE AND VISIBILITY ANALYSIS

Abstract. This contribution presents a method for extracting a 3D model of facades and windows from a point cloud. The point cloud is segmented based on a voxel octree, in which the facades are sought as planes. These can be used to filter out potential window points within the building, which are then analysed on their visibility by checking the occupancy grid of the voxel space. Here, methods of digital image processing are used for analysing both point clusters behind the facade and holes in the estimated facade planes as window candidates. Facades and windows are both simplified as rectangles. The test data set was gathered in a Mobile Laser Scanning campaign. While the segmentation fails in some cases, the extraction of facades and windows shows good results: 25 facades with 702 detected windows yield a detection rate of 86% with a false alarm rate of 13%. The reconstructed sizes of the windows differ from reference measurements in the range of centimetres to a few decimetres. These refined geometries can be used to enrich existing building models or for vehicle navigation without GNSS.

TRANSFER LEARNING IN THE CLASSIFICATION OF SATELLITE IMAGES SHOWING AMAZON RAINFOREST

Abstract. In recent years, we have been dealing with the dynamic technological progress of the space sector, which allows for the observation of the Earth with better temporal, spatial and spectral resolution. The increasing availability of satellite data has contributed to the development of data processing algorithms. Thanks to the use of digital image processing methods and deep neural networks, it is possible to perform automatic image classification, segmentation or detection and recognition of objects on the images. This article presents the methodology that allows to accelerate the classification process of satellite images representing the Amazon rainforest based on the Transfer Learning method. Additionally, the influence of the choice of optimization, i.e. the network weight estimation strategy, on the classification of objects was checked. In order to verify the method, an additional raster image classifier was created on the basis of Lidar data. Research shows that the transfer learning method allows the preparation of an image classifier based on a small database (less than 100 images representing one class). The network training process can be shortened to a few minutes.

Formation of the pediatric electroretinogram database parameters for the development of doctor’s decisionmaking algorithm

Electroretinography is a non-invasive electrophysiological method standardized by the International Society for Clinical Electrophysiology of Vision (ISCEV). Electroretinography has been used for the clinical application and standardization of electrophysiological protocols for diagnosing the retina since 1989. Electroretinography become fundamental ophthalmological research method that may assesses the state of the retina. To transfer clinical practice to patients the establishment of standardized protocols is an important step. It is important for monitoring successful molecular therapy in retinal degeneration. Retinitis pigmentosa or achromatopsia and, consequently, affected cones or rods photoreceptors is corresponded to complete absent of electrical response. Thus, detection of even modest improvements after therapeutic treatment is required. Standardized protocols allow the implementation of electroretinography under conditions of optimization of sensitivity and specificity during clinical trials. It should be noted that the literature on retinal diseases demonstrates clinical cases in which patients may have several retinal diseases at the same time. In such cases, it is necessary to detect a group of characteristics of electrophysiological signals with high accuracy to improve the application of various diagnostic solutions. The classification of electroretinogram signals depends on the quality of labeled biomedical information or databases, in addition to this, the accuracy of the classification results obtained depends not only on computer technology, but also on the quality of the input data. To date, the analysis of electroretinogram signals is realized manually and largely depends on the experience of clinicians. The development of automated algorithms for analyzing electroretinogram signals may simplify routine processes and improve the quality of diagnosing eye diseases. This article describes the formation of the parameters of pediatric electroretinogram database parameters for the development of doctor’s decision-making algorithm. The signal parameters were obtained by extracting the parameters from the wavelet scalogram of the electroretinogram signal using digital image processing and machine learning methods.

Measurement of Photosynthetic Pigment Content using Convolutional Neural Network

Estimation of photosynthetic pigment levels from leaves can be done using conventional methods using laboratory equipment such as spectrophotometers and using digital image processing from leaf images with a computational model. In digital image processing methods, various models are used, such as neural network, CNN, and linear regression. Measurement of photosynthetic pigment levels using image processing methods uses color value data from image data as input to the model used. In this study, we will analyze the effect of various types of color space and inpaint preprocessing settings on the accuracy of the CNN model in measuring leaf photosynthetic pigment levels. The color space types being tested are 4 single color spaces RGB, HSV, LAB, and YCbCr, as well as 6 color combination spaces RGB+HSV, RGB+LAB, RGB+YCbCr, HSV+LAB, HSV+YCbCr, and LAB+YCbCr. The choice of the type of color space takes into account the phenomenon of color constancy and the characteristics of the color space on the lighting elements. In addition, image data is divided into two types, namely through inpaint preprocessing and not, so that in total there are 20 types of input data. After the CNN model training process with various types of color spaces and different preprocessing settings as input data, observations were made on the accuracy values, namely the training MAE and the validation MAE for each model. From 20 types of input data, 3 types of input data are obtained which are recommended as input data that provide the best model accuracy value based on MAE validation with values ​​of 0.08761, 0.09252, and 0.09288. The three recommended input data from the sequence of accuracy values ​​are RGB+LAB without inpaint, RGB with inpaint, and LAB+YCbCr without inpaint.

Robust Dynamic Indoor Visible Light Positioning Method Based on CMOS Image Sensor

A real-time imaging recognition and positioning method based on visible light communication flat light source is proposed. This method images the visible light communication flat light source through the rolling shutter effect of the complementary metal-oxide semiconductor imaging sensor and obtains the rectangular area outline of the light source. The light and dark stripe information of image with the digital image processing method realizes light source matching recognition by defining the concept, the autocorrelation sequence, which can be used to obtain the identity of the light source, and the rectangular vertex coordinate information of flat light source achieves high-precision vision positioning on the basis of inertial measurement unit attitude sensor-assisted imaging. Simultaneously, the corresponding positioning module is developed for positioning testing. The test results indicate that the plane positioning error is less than 4.5 cm, and the positioning frequency is greater than 10 Hz, which provides a high-precision visual positioning solution for indoor positioning.

Significant Differences in the Value of the Void Fraction in Various Types of Low-Viscosity Two-Phase Flow Patterns in Capillary Tubes with a Particular Slope

A two-phase flow is the simplest form of multi-phase flow. Two-phase flow has basic parameters, including flow behavior, flow pattern, void fraction, pressure gradient, or pressure drop. The development and application of fluid flow in small channels (mini and micro) are in the Micro Electromechanical System (MEMS). In general, the application of two-phase flow can be found in various applications in the industrial world, such as boilers, cores, and steam generators in nuclear reactors, petroleum transportation, electronic cooling, and different other types of chemical reactors. One of the most common challenges is void fractions and flow patterns in horizontal and vertical pipelines. The purpose of this study was to find out the significant difference in the characteristic value of fundamental parameters, primarily void fractions and flow patterns that occur in capillary pipes with a slope of 15o to horizontal. The fraction value and shape of this flow pattern are essential because it determines the pressure drop value, which means determining the level of danger that can occur if the pressure drop value reaches the extreme value. The fluid used a mixture of air-water and glycerin with 0, 10, 20, and 30% concentrations. To determine the void fraction is used digital image processing method with MATLAB R2014a application. A 1200 fps high-speed camera and 640 x 480-pixel resolution are used for video shooting. The experiment was conducted at superficial gas (JG) velocities of 0.025 - 66.3 m/s and superficial fluid velocities (JG) intervals of 0.033 – 4.935 m/s. The experiment results showed a significant difference between the void fraction value for the bubbly flow pattern and the churn flow pattern, which has not been widely discussed in previous studies. The analysis concluded that the higher the velocity of superficial gases, the void fraction value increases. This increase in the void fraction is why there is a significant change in flow patterns from bubble flow patterns to churn. In addition, it was also found that the increased viscosity of the fluid significantly affected changes in flow patterns, incredibly bubbly and plug, but its velocity decreased. It is also the result that the higher homogeneous void fraction (β) value affects the increase in the length of bubbly flow patterns and plugs.

ANALISIS NILAI AKURASI PENGOLAHAN CITRA PENDETEKSIAN RINTANGAN KERJA TRAKTOR MENGGUNAKAN K-MEANS CLUSTERING

The use of agricultural tractors as mechanical aids for tillage using agricultural tractors can make work lighter, faster, more efficient and do big jobs in a relatively short time. Along with the development of technology, many innovations have been developed by humans, including in the field of digital image processing. Segmentation is one of the methods in digital image processing to distinguish objects in an input image. One of the algorithms that can be used for image segmentation is K-Means. Many algorithms are used in image classification. Algorithms that can be used to complete the supervised classification include Paralleepiped, Minimum Distance, Mahalanobis Distance, Maximum Likelihood, Naive Bayesian, K-Nearest Neighbor. Algorithms that can be used to solve unsupervised classifications include Isodata, K-Means, Improved Split and Merge Classification (ISMC), and Adaptive Clustering (CA). Based on this description, this research was conducted to facilitate the data processing process, it is necessary to have a data grouping system to determine decisions in the analysis to determine the level of accuracy in the detection of obstacles resulting from image processing where obstacles are detected, noise and obstacles are not detected. processed and grouped based on their characteristics so that it is known that the cluster is low, medium cluster and high cluster to be able to analyze the data, it is necessary to have a deeper analysis using the K-Means Clustering method and implement K-Means results into Rapidminer to see the results of visualizing the K-Means algorithm data grouping.

Vacant Car Parks Detection Using Digital Image Processing Methods

Long car queues are often encountered in some public facilities because visitors should be around to find an empty parking space. One way to minimize this case is to use a parking information system that shows the location of the parking lot that is empty or occupied with their amounts. This research presented two digital image processing methods for detecting empty space occupied in the image of the car parking area. There are vehicle detection and edge detection method. Vehicle detection is the method used to detect objects in the image by subtracting the parking area image, an empty parking lot, from the image containing the car. In contrast, the edge detection method detects the object's edge. The results from these two methods were then compared using the AND function to obtain the condition of an empty or occupied box for each box in the parking lot. Threshold values affect the determination of the parking lot. In this research, the data used are images of open car parks in the Malang Town Square (Matos) shopping center, Mall Olympic Garden (MOG), and data sourced from journals with similar topics [16]. The test results show that the best detection results are obtained in detecting occupied parking spaces in the parking lot in Malang Town Square (Matos), with a threshold of 10 and an accuracy of 99.4% with a threshold of 10.&#x0D;

Research of methods of distribution of graphic objects on websites for assessment of interface quality

Formulation of the problem. An actual problem when creating web resources is the test-ing of the designed design, which is the direction of testing the user interface. This paper con-siders ways to automate the analysis of the interface of web pages in terms of visual perception of man. The aim of the work. The aim of the work is to improve the quality of automated testing of the graphical user interface based on the use of methods of analysis of color digital images and detection of graphic objects. Methods of selecting objects on digital images. The traditional method of segmentation is described – threshold binarization, which results in a binary image. The JSEG algorithm is more advanced. According to this method, instead of estimating the parameters of the texture model, the homogeneity of each image fragment is checked, which leads to a reduction in the amount of computation. Website interface evaluation methods. In order to qualitatively evaluate the user interface, it is necessary to identify the basic principles on which designers rely when designing interfaces. Basic principles of interface construction: shape, size, brightness, color, direction, location. Determining the brightness characteristics of the image. To estimate the brightness pa-rameters, you can use the estimation of the image histogram, which displays the brightness value. The optimal type of brightness histogram is the normal distribution. Determining the number of primary colors in the image. Performed by constructing a histogram for an indexed image on a given color map. It is optimal to use no more than 3 primary colors. Selectionobjects in the image. The methods of image segmentation described above are implemented and the imperfection of these methods is shown. The application of the JSEG algorithm gave a more positive result, but requires additional adaptation to our tasks. Conclusions. The study and comparative analysis of digital image processing methods to automate the process of assessing the quality of the graphical user interface. It is concluded that the application of the classical approach to image segmentation did not give the desired result for image analysis of web pages, namely there are problems of inability to separate adjacent graphics at the threshold binarization, and combine text characters into one block. The JSEG algorithm includes color quantization and spatial segmentation operations, due to which the result of object selection is better, but still requires further settings.

Various Denoising Methods in Digital Image Processing: A literature Survey

Various Denoising Methods in Digital Image Processing: A literature Survey

Research on Void Signal Recognition Algorithm of 3D Ground-Penetrating Radar Based on the Digital Image

The three-dimensional ground-penetrating radar system is an effective method to detect road void disease. Ground penetrating radar image interpretation has the characteristics of multi-solution, long interpretation period, and high professional requirements of processors. In recent years, researchers have put forward solutions for automatic interpretation of ground-penetrating radar images, including automatic detection algorithm for subgrade diseases based on support vector machines, etc., but there are still some shortcomings such as training models with a large amount of data or setting parameters. In this article, a three-dimensional ground-penetrating radar void signal recognition algorithm based on the digital image is proposed, and the algorithm uses digital images to characterize radar signals. With the help of digital image processing methods, the images are processed by binarization, corrosion, expansion, connected area inspection, fine length index inspection, and three-dimensional matching inspection, so as to identify and determine the void signals and extract the void area volume index. The algorithm has been verified by laboratory tests and engineering projects, and the results show that the void identification algorithm can accurately identify the void area position; the error level between the measured values and the measured values of length, width, buried depth, and area is between 2.2 and 17.3%, and the error is generally within the engineering acceptance range. The volume index calculated by the algorithm has a certain engineering application value; compared with the support vector machine, the regressive convolution neural network, and other recognition methods, it has the advantage of not needing a large amount of data to train or modify parameters.

The Effect of Feature Selection on Gray Level Co-Occurrence Matrix (GLCM) for the Four Breast Cancer Classifications

Breast cancer is ranked first as the most common cancer case affecting women in the world. Early detection of breast cancer can increase the chances of survival in patients. The role of the radiologist is necessary for the detection of breast cancer, and the radiologists often have limitations in conducting disease consultations with so many patients. The detection gives a subjective result because the process is based on the decision-making of the radiologists. In this work, we proposed a system to detect and classify breast cancer accurately to anticipate delays in patient handling and subjective result. We proposed a digital image processing method using mammograms to classify breast cancer into four categories based on tissue density, namely BI-RADS I, II, III, and IV. The main stages carried out in this research are images processing, feature extraction, data normalization, feature selection, classification, and parameter optimization. This method uses GLCM to extract texture features and two feature selection methods namely, RFE-RF and Chi-Square. The method was tested with various classifiers such as SVM, KNN, Random Forests, and Decision Trees. The hyper-parameters of the classifier were optimized using GridSearch. The final result is measure using accuracy. In this work, Random Forest with the RFE-RF gives the highest accuracy of 99.7%. Feature selection offers a significant impact on improving accuracy. The results of this work prove that our system can classify breast cancer with high accuracy. So that our system can solve problems to assist radiologists in screening mammograms and help make decisions to diagnose patients with breast cancer based on density.