Search

The drape is a fabric's ability to deform when suspended under its weight in specified conditions of known size using a Drape Meter. The Drape Coefficient % (DC%) is calculated by taking the weight of paper cut out based on the shadow of the fabric. A fabric property is very important in relating to the behavior of drapes and these factors were determined by earlier researchers in developing a tool to measure drape. The Cusiks's Drape Meter was the first equipment that used the principle of shadow in reflecting the drape behavior and later on calculating the DC%. The principle introduced by Cusick has been used by a lot of researchers to determine DC% more accurately using computer captured images. In recent years, a lot of research has moved forward using software to calculate the DC% by incorporating the values of fabric properties to create an image for the drape. A lot of work on comparing the values of DC% using conventional and simulated/virtual methods was published. The usage of particular software can predict the DC% before the actual production of fabrics. Prediction can be made based on physical properties needed on particular fabrics to be produced and thus saving a lot of time and giving more choices in fabrics selection. [ABSTRACT FROM AUTHOR]

Sentiment, emotions, feelings, showing or giving judgments by face gestures, etc. can be communicated by text, speech or images. Analyzing image Polarity via images is now a burgeoning research field. An image can easily be interpreted by any human being and acts as a bridge to relate an image to the human's thoughts. The paper proposed a model for analyzing the sentiments or emotions of an image. We have used a Data-Mining Orange Tool for executing the experiment for classification and sentiment analysis of an image. The main challenge is to acquire the polarity of the unlabeled data using optimal machine learning techniques. To overcome this challenge for getting the polarity and sentiment of an unlabeled data the proposed model used various noteworthy machine learning models like Neural Network, Naïve Bayes and random forest for classifying and analyzing the image sentiment and also provide a comparison based on certain parameters like Area Under Curve, Precision, Recall, classification Accuracy, etc. The tool provides a complete package for performing image analysis using the widgets available with orange tool and a data visualization tool to get a visible representation of the output. The proposed model shows that Random Forest performance the best from the three compared algorithms with classification Accuracy of 0.747, recall & precision as 0.747 & 0.752 and the accuracy based on confusion matrix is 74.72%. [ABSTRACT FROM AUTHOR]

Image recognition plays a very important role in the application of computer vision, but there is a problem that object tracking is not ideal. The previous recognition method could not solve the problem of object tracking in the field of computer vision, and the recognition was inaccurate. Therefore, this paper proposes an artificial intelligence technology for object tracking image recognition and analysis. they used to process the image information, and the indicators are divided according to the requirements of artificial intelligence processing to reduce them Interference factors in image recognition. Then, the theory of human intelligence processes the image artificial intelligence, forms an artificial intelligence processing scheme, and recognizes the results of the image Conduct a comprehensive analysis. The revised results show that the calculation process in this paper is relatively good, and it is suitable for practical theoretical analysis, which has high significance and function, and can be used for later comprehensive judgment. [ABSTRACT FROM AUTHOR]

The use of a bioinspired Convolutional Neural Network (CNN) model in this paper's unique automated method for malaria diagnosis in blood smear images. Extensive development in computer-aided diagnosis systems has been driven by the urgent need to fight malaria, a disease that poses a serious threat to life. However, the precision, accuracy, and recall rates of current approaches are constrained, which reduces their usefulness in real-world settings. The suggested approach places a strong emphasis on incorporating bioinspired ideas into the CNN model design to overcome these limitations. The bioinspired CNN model outperforms conventional CNN architectures in terms of greater specificity and expanded capabilities by taking inspiration from nature-inspired algorithms. This concept provides a considerable improvement over current methodologies by enabling more precise and reliable malaria detection process. The strategy that is being discussed combines machine learning strategies with extensive image processing capabilities. Through the use of several approaches, this integration makes it possible to provide a comprehensive solution to the problem of malaria detection. In comparison to conventional methods, experimental results show the proposed method to be effective, with precision rates of 3.9%, accuracy rates of 2.9%, and a surprising 3.5% increase in recall levels. Thus, this paper demonstrates the need for a novel strategy to malaria detection in light of the shortcomings of current techniques. By combining a bio-inspired CNN model with image processing and machine learning methods, it is possible to greatly improve the precision, accuracy, and recall rates for automated malaria identification in blood smear images. The results of this work show significant promise for developing the discipline of medical image analysis and supporting continuing global efforts to eradicate malaria for real-time scenarios. [ABSTRACT FROM AUTHOR]

The paper presents a series of material tests for the assessment of structural and mechanical quality of nitrided layers obtained on steels: 40HM, 38HMJ. The assessment of the structural quality of the layers was made in the comparisons of metallographic images of cross-sections and spherical sections. The thickness of the iron nitride layer and the internal nitriding zone were assessed. In the structural description, metallographic analyses and measurements of profile hardness were used with the criterion HV 0.5 g=r+50, g=400 HV0.5. The mechanical quality of the WW system was assessed on the basis of the analysis of SEM images of the nature of cracks or their absence around the ones formed within the HRC indentation. The paper proposes an improvement of this method by introducing the imaging of cracks on the surface of a spherical microsection located in the HRC indentation space. The prairie spherical microsection was obtained using a modern proprietary Recalo2 research station. The paper presents the technical characteristics of the Recalo2 stand and indicates further directions for its technical improvement. [ABSTRACT FROM AUTHOR]

Thermal imaging cameras are used in many fields. The paper analyses the possibility of using thermal imaging in medicine. It has been proven that the infrared camera can be used in sports medicine. The aspects of the measurement apparatus and the features which should be paid attention to during the tests were also quoted in the paper. [ABSTRACT FROM AUTHOR]

This paper describes a modern and innovative method for attendance monitoring using an open CV. It is an open-source library and is widely used whenever we talk about facial recognition, video analysis, and image analysis. The traditional method of attendance taking is a hectic and time-consuming task that also requires a lot of physical effort. In this paper face detection, face recognition, and printing the accurate data in form of the CSV file is presented. Face detection helped to determine the position and location of the face; face recognition helped to mark the nominee's attendance and the third step is storing the data received in form of a CSV file such that the fear of attendance is delicacy has been solved. The proposed solution to the traditional attendance problem not only eradicates the burden on human resource but also provide one of the fastest and more efficient methods to take the attendance. [ABSTRACT FROM AUTHOR]

Choosing a tourist place for vacation is very important, as a user spends a lot of money and efforts to choose a location wisely. To alleviate this effort, a travel recommendation system is introduced. However, the current recommendation system falls short of providing a perfect tourist location because there are different types of users, each with their own preferences. So here, a user needs a personalized recommendation system. This paper focuses mainly on creating a machine-learning system that is a travel recommender system. It recommends a particular tourist place in two different ways. The first is based on ratings given by other users, and the second is based on previous images of places that users have previously visited. This machine learning model can be further linked to a website using Flask to make it easier for people to use it and search for their favorite destination. This system recommends a tourist attraction based on two factors: first, the ratings of each location given by other users, and second, the images users prefer. This paper mainly focuses on using SVD, LDA, and OpenCV. [ABSTRACT FROM AUTHOR]

Object localization, computer vision, video reconnaissance frameworks, and other applications all depend on image processing techniques, which are a basic component of today's computer technologies. Image segregation is a crucial step in image handling. The most popular method for breaking up images into several little pieces called fragments is termed image segregation. Image handling makes to work on the image portrayal to break down the images. A vast array of algorithms are created for segmenting images based on the unique characteristics of each pixel. In this paper various algorithms of Segregation can be evaluated, examined lastly drill down the examination for every one of the algorithms. This correlation study is helpful for expanding precision and execution of Segregation strategies in different image handling areas. The objective of the paper is to study on examination inside a wide image and study on Image segregation. [ABSTRACT FROM AUTHOR]

A modeling method for color probability map using an artificial neural network architecture is examined in this paper. An optimal architecture of the artificial neural network is determined after evaluating various structures extensively. For evaluating the performance of a specific structure of the Multi-Layered Perceptron type Neural Network (MLPNN), a measurement for evaluating the quality of a Color Probability Map (CPM) image is proposed in this paper. An optimal architecture of MLPNN for CPM is found based on the quality measurement. The resulting MLPNN model trained with CPM data is applied to traffic sign datasets. The results show that the architecture of MLPNN obtained in this experiment can detect traffic signs very efficiently when compared with the look-up table method with improved accuracy. [ABSTRACT FROM AUTHOR]

Effective administration of cold storage facilities plays a significant responsibility in maintaining the quality of perishable items and reducing wastage within the supply chain. This study unveils a creative method that employs the combined pros of image processing, the Internet of Things (IoT), and a notification system to enhance the efficiency of cold storage procedures. The IoT framework enhances this system by enabling seamless communication between the cold storage framework and a central monitoring hub. The proposed paper mainly focuses on real-time monitoring of the cold storage environment and if there is any power outage notification will be sent to the person through SMS using GSM. The notification system is integrated to provide timely alerts to relevant stakeholders. In the current implementation of the project, the DHT11 Temperature and Humidity Sensor, the MQ-3 Ethylene gas sensor is integrated into a low-cost and Wi-Fi-enabled Node-MCU Microcontroller for Cold Storage monitoring purposes. The Node-MCU posts data to a cloud-based platform, where they are dealt with and scrutinized. Integration of image processing techniques assists real-time monitoring of cold storage environment. Cameras placed strategically within the storage units capture images of stored goods, enabling the system to analyze factors such as product quantity, placement, and quality. Advanced image analysis algorithms identify anomalies, spoilage, or potential issues, thus securing the upkeep of product integrity throughout the storage duration. This real-time responsiveness minimizes the risk of product spoilage and verifies adherence to regulatory standards. [ABSTRACT FROM AUTHOR]

Curvelet Transform typically offers significantly superior performance in image analysis, multi-resolution and multidi-rectional representation as compared to Wavelet Transform. This paper exploites strong relationship between Wavelet Transform and Curvelet Transform. Also we use mother Wavelet to construct Curvelet Transform as an extension of Wavelet Transform which has broad implications, particularly for the field of signal and image processing. [ABSTRACT FROM AUTHOR]

Recently, deep learning algorithms have become one of the most popular methods and forms of algorithms used in the medical imaging analysis process. Deep learning tools provide accuracy and speed in the process of diagnosing and classifying lumbar spine problems. Deep learning tools deal with many types of medical images, including computed tomography (CT), X-rays, and magnetic resonance imaging (MRI). MRI is the most common method for diagnosing diseases of the lumbar spine. This paper aims to provide a general overview of how deep learning can be used to analyze lumbar spine images. It focuses on papers, results, and methods used by researchers in recent years. The presented works indicate that deep learning can be highly relied upon in the process of analyzing medical images of the lumbar spine and identifying the correct diagnosis. [ABSTRACT FROM AUTHOR]

The image processing area has become increasingly important in real-time applications in the current world. Such image processing techniques assist in carrying out processes on digitized images in order to deliver superior results. There are a variety of algorithms for data classification, some of which are rule-based and others which are learning-based. Various image analysis techniques and related challenges in the medical field are investigated in this research. This paper presents effective strategies for overcoming the limitations of image analysis approaches, as well as a brief discussion of image pre-processing before focusing on Image Classification and Segmentation. Our research can help readers learn more about many aspects of medical image analysis. This paper will review the most relevant studies on this topic to date and will describe existing image analysis methods for Data Preprocessing, Image Classification, and Image Segmentation. Image analysis will help readers understand how to increase the performance of their models and expand constrained datasets to take use of the possibilities of other data sets. [ABSTRACT FROM AUTHOR]

Image segmentation is a vital and crucial part of image analysis and medical systems. This is the utmost challenging task as it decides the efficiency of the outcome of the image analysis. Ultrasound images play a significant role among other medical images. The automatic segmentation of these images becomes a factual challenge due to the speckle noise and the artifacts. The selection of the segmentation approach depends on the quality of the segmentation and the scale of information required. In this paper, the fetal ultrasound image is segmented using the Spatial Fuzzy C-Mean clustering method. The feature vectors are developed for each pixel of the fetal images used as inputs for the clustering method. The clustering methods segment the fetal image based on spatial information. An anisotropic Diffusion filter is used for image enhancement before the image segmentation. Experimental results indicate that the Spatial Fuzzy C-Means clustering method can be applied with promising results. [ABSTRACT FROM AUTHOR]

The aim of the paper is to study sustainability of the research-based entrepreneurial ecosystem BioMed-Varna. The BioMed-Varna is focused on interdisciplinary research in Biomedical Image Analysis, Computational Life Sciences, and Neuroscience. Its main activities include multidisciplinary scientific research, educational projects, development of STEM practices and events/cases for educational institutions, promotion of innovation and entrepreneurial culture, and support for its members' scientific advancement. This paper investigates the development and performs a sustainability appraisal of the research-based entrepreneurial ecosystem using real-world data. The analysis applied by Social network analysis (SNA), reveals the participants' roles, activities and relationships. Using Key Point Indicators (KPIs) and network-based models, this research can support decisions about necessary changes in the ecosystem. Results can be implemented for running evaluation as well as for predictive sustainability assessment. The methodology can be transferred for further research on other regional ecosystems. [ABSTRACT FROM AUTHOR]

Digital images are usually suffering from noises that affect the appearance of the digital image, and this affected appearance could result in disrupting the details, edges, components, etc., and to remove these noises, we have to use one or more filtering techniques or methods. Noise is an unwanted signal that affects digital images which make the digital image has differences compared to the original image or even the real scene. Filtration is a technique used to do modifications to an image to make it more similar to the original image or scene. In this paper, we will use three methods maximum, median, and minimum filtering which are types of rank filtering. Rank filtering is a non-linear technique that uses a kernel that is a window with an odd size and has a minimum size of three, passes through all the pixels in the image and does ascend ordering, and then chooses a pixel within the order kernel to replace the center value of the kernel and reflect it to the direct equivalent position inside the filtered image. For choosing a value from the ordered kernel, a lot of rank filtering techniques appeared, and we will discuss in this paper three types, the minimum filter will choose the minimum value from the ascending ordered kernel, and the maximum filter will choose the maximum value and finally, the median filter will choose the middle value. This paper will compare these rank filters by using MATLAB, which is a scientific and engineering application, and there will be a function for removing noises for the mentioned three rank filters besides determining the performance for each type of rank filter and comparing them to find out the best type of filtering between rank filters mentioned. In this paper, the noise applied to the digital image is salt and pepper noise which is the most famous noise resulting usually from weather effects. The result of this paper is proving that median filtering has the best performance of removing salt and pepper noise compared with maximum and minimum filtering, and it is proved by using subjective and objective notice. [ABSTRACT FROM AUTHOR]

Hyperspectral image processing is a field of investigation for electromagnetic spectrum to obtain spectrum for each pixel inside the image of a scene with the reason of locating, figuring out and detecting the overall analysis of the image. Anomaly detection makes use of such bands that incorporates precise traits carefully associated with goal gadgets. This paper affords a take a look at on the detection of anomalies for Hyper Spectral pictures based on nicely-designed dictionaries: heritage dictionary and capability abnormality lexicon. The detection method used is "Joint sparse representation" (JSR)-based dictionary selection. This paper approaches for the quantitative analysis of the receiver operating characteristics of the different Hyperspectral data sets. For the quantitative evaluation of this data via the implemented method with the various other methods, the ROC curves with point sensible self-assurance intervals had been plotted. Low Rank Sparse Representation method adorns an amazing overall performance at the AVIRIS-1, AVIRIS-2 and HYDICE sets giving a qualitative comparison of 95.25% Experimental analysis pointed out to the matter of fact that detecting anomalies based on potential abnormality and historical past lexicon production is capable of attain advanced consequences in comparison with different winning strategies. [ABSTRACT FROM AUTHOR]

The research paper focuses on developing a custom machine learning model using Google's Teachable Machine for the classification of palm fruit images as healthy or rotten conditions. The study demonstrates successful integration of the customized model with a Raspberry Pi-based system for real-time object recognition. It achieved a remarkable 100% accuracy rate on a dedicated dataset for the palm-fruit classification. The seamless integration of the model allowed for live streaming image analysis, enabling the system to convey specific messages based on the identified fruit condition. Moreover, the work showcases the potential of custom machine learning models for real-time automation and decision-making applications. [ABSTRACT FROM AUTHOR]

Brain tumors and other cancers of the nervous system are among the primary causes of life's loss in today's world. The growth of abnormal cells in the brain can result in brain tumors, which are classified as either benign or malignant. While detecting brain tumors at an early stage is crucial for improving patient outcomes, it can be challenging due to the lack of early symptoms and the complexity of the brain's structure. Machine learning has emerged as a promising tool for detecting brain tumors accurately. In recent years, researchers have developed various machine learning models that utilize image analysis techniques to identify brain tumors based on CT and MRI scans. In this research paper, we compare the performance of several ML algorithms on a Brain Tumor Dataset to evaluate and analyze appropriate algorithm for correctly identifying the presence of a tumor in the brain. We analyzed the efficiency of the algorithms based on metrics such as sensitivity, specificity, accuracy, and false positive rate. [ABSTRACT FROM AUTHOR]

Pneumonia is a prevalent and severe infectious disease affecting millions worldwide. It is the most common cause of death, claiming more than four million lives yearly. Early detection of pneumonia is critical for prompt and effective treatment, which can significantly improve patient outcomes. In recent years, deep learning has now become a predominant tool for image analysis in the medical sector. This could significantly improve pneumonia detection's accuracy and efficiency, ultimately saving lives. The primary purpose of this paper is to propose a solution to this critical public health problem. In particular, we propose to develop a deep-learning system using X-ray images of the chest. The proposed model deals with the VGG16 architecture. It is trained on many X-rays, both with/without pneumonia of the chest, so the model can accurately distinguish between normal and infected lungs. The model can significantly improve the speed and accuracy of pneumonia detection, enabling medical professionals to diagnose and treat patients more effectively and efficiently. Ultimately, this could lead to more timely and accurate diagnoses that could help save lives and reduce the burden of pneumonia on individuals and communities. The model can classify pneumonia at 92.10% validation accuracy. [ABSTRACT FROM AUTHOR]

The proper segmentation of brain tumors is essential in medical image analysis field. Convolutional neural networks (CNNs), which make up the majority of deep learning approaches, have demonstrated encouraging results in automating this process. This research paper presents a novel two-step approach for brain segmenting and detecting tumors. In the first step, we employ a DenseNet121 model with transfer learning, fine-tuning the pre-trained weights obtained from the Image Net dataset, to recognize tumors in the brain. The second step involves utilizing a ResUnet model, which combines the strengths of ResNet50 and Unet models, for accurate segmentation. To validate our approach, we conduct experiments on "The Cancer Imaging account (TCIA)'s dataset "The Cancer Genome Atlas (TCGA)" and compare the results with other models of deep learning such as K-means clustering and VGG16. Our experimental findings demonstrate that our proposed approach achieves superior accuracy and efficiency compared to the alternative models. [ABSTRACT FROM AUTHOR]

An overview of the various methods and algorithms for edge detection in digital images is given in this survey paper. A fundamental issue in image processing is edge detection, which involves in locating the borders which separates various regions in an image. The survey starts with an explanation of edges and their importance in an image analysis, then reviews some of the most widely used edge detection techniques, including the canny edge detector, the Sobel operator, and the Laplacian of gaussian. The following section discusses some of the drawbacks and shortcomings of these techniques. A discussion of current trends and potential future directions in the field of edge detection rounds out the survey. [ABSTRACT FROM AUTHOR]

Chest X-ray (CXR) imaging is often used to diagnose pneumonia caused by COVID-19. The advantage of CXR is that it is cheap, fast, widespread, and uses less radiation. Studies of distinguishing object regions from one to another or image segmentation have been used in the medical field for further image analysis. This paper has proposed a method for segmenting lungregions using region-based active contour to measure the area segmented in CXR images. Active contour segmentation was performed using a computer vision image segmented in MATLAB. We assessed the CXR image in Andalas University Hospital and composed the data consisting of lung opacity (pneumonia) and regular. The result shows that, in both the left and right of the chest, the area in the pixel of the lung affected by COVID-19 is smaller than in the normal lung. In conclusion, this technique will benefit biomedical research investigating the regional lung. [ABSTRACT FROM AUTHOR]

Satellite images mainly utilized in the events of a natural disaster management, identifying geographical information, viz land cover classes namely, buildings, roads, vegetation, water, agriculture land, crop types, plants, bare ground, cities, atmosphere conditions. Machine Learning (ML) approaches have been utilized effectively to develop a model for classification, detection, and segmentation tasks. Therefore, Satellite image processing and analysis purpose, ML techniques plays vital role and remotely sensed data become essential while training the model. The aim of this study is to investigate the various of ML techniques in satellite image analysis. However, to predict the various events in advance across the globe, it is necessary to focus more on remote sensed data and data processing techniques for accurate classification. Even though remote sensing quality has been increased and artificial intelligence solutions are equally increased. This paper addressed various types of advanced ML techniques utilized in the classification and assessment of satellite images and used to track the earthquakes, faulting, landslides, floodings, wildfire, and hazards associated with the stated activities. Still there is a gap and interference in the approaches and it is important to fill the gap by thorough review of recent classification approaches. In this connection it is necessary to look in depth to the state-of-the-art ML techniques of satellite image processing. [ABSTRACT FROM AUTHOR]

In this paper a general framework for a privacy preserving medical Content Based Image Retrieval (CBIR) is presented. We illustrate how a homomorphic encryption scheme can be used to implement a medical diagnose system while protecting the privacy of the patients. The fully homomorphic encryption presented by Gentry [17] allows for the computation of any features over an encrypted image. We make an attempt to exploit the robust capabilities of the theory of moments in image analysis in order to develop a robust diagnose system while maintaining the security aspect. [ABSTRACT FROM AUTHOR]

The use of biometrics extends to all possible areas of human activity. For example, identification, banking services, and even paying for public transport have all been made possible through biometric systems. Particular attention is given to biometric systems based on palm vein patterns. Several factors contributed to the popularity of this modality. First, its universality is inherent to the majority of people. The distinctiveness of an individual's vein pattern allows this parameter to be used as a unique identifier. Assume that the vein pattern does not charge much overtime, indicating the constancy of this modality. The biometric systems developed for vein pattern modality allow reading the user's parameters in a non-contact way, providing a high level of hygiene, which is especially important during the COVID-19 pandemic. The main advantage of this approach is to ensure the high security of the identification data. The venous pattern can only be seen in the near-infrared (NIR) range, making it very difficult to obtain biometric characteristics under normal circumstances since veins, unlike fingerprints, are protected by the skin. A literature survey showed that research attacks on biometric systems have been carried out when an attacker had full access to the database or created an artifact based on an image obtained by an infrared (IR) camera. This paper discusses the possibility of obtaining an image of the venous pattern in the dorsal part of the palm without using the IR camera. It conducts the comparative analysis of the acquired image with the standard produced in the IR range. Furthermore, the conclusions, based on the study, about using images obtained without the IR camera to manufacture artifacts for a presentation attack on the biometric systems are also presented. [ABSTRACT FROM AUTHOR]

Breast cancer (BC) is the most prevalent type of cancer among women. However, it can be cured if detected in early stages and treated in proper way. As pathologists play the lead role in the whole process of diagnosis and prognosis, the process might include inaccuracy due to external factors such as interobserver and human error. Besides, in most places of the world there is lack of experienced pathologists and cancer experts. Therefore, computer programs can help extensively to compensate for these setbacks. Computer programs can be trained through Machine Learning (ML) algorithms in order to perform the scoring process on BC medical images such as histopathological and immunohistochemistry (IHC) images. IHC staining is a technique in which a set of biomarkers are used to detect the positive reaction to a certain type of treatment. By using whole slide imaging (WSI) for digitizing the IHC samples, the images can be prepared in digital form to be used as the entry to the computer programs. To provide an automated scoring program, researchers take advantage of image processing techniques combined with ML algorithms for segmentation and classification of positive cells based on the stain color and intensity. Since image quality highly rely on the laboratory equipment, operator's experience and other factors such as stain intensity, the programs may utilize image enhancement methods for more accurate segmentation and classification results. In this paper some of these methods are investigated based on preprocessing, segmentation, and classification steps for four biomarkers i.e., ER, PR, Her2, and Ki67. The results show that lack of IHC datasets and high computational time as well as complexity of implementation are the main obstacles that need to be investigated by researchers. [ABSTRACT FROM AUTHOR]

China's urban railway network already covers 80 percent of the country. The support of a continuous line is inextricably linked to the rapid expansion of railways. The seamless line has a complex structure, a long working period, and is susceptible to environmental and other factors. This paper mainly studies the design and implementation of seamless line displacement data detection by using image recognition technology and machine learning technology. This topic trains and learns the digital content in the seamless line displacement scale through the machine learning SVM classification algorithm, and then identifies the scale mark and other data by image analysis to calculate the final displacement. In this way, the accuracy of the identified displacement data is very high. This study detects the displacement of the seamless line and gives early warning when the displacement exceeds the safety range. After receiving the early warning information, the management personnel can handle it in time to avoid danger. Some railway portions in Harbin have been subjected to the study. The research can assist railway management departments in detecting seamless line facilities and improving maintenance efficiency. At the same time, it can provide timely warnings of potentially risky information, reducing the likelihood of accidents. [ABSTRACT FROM AUTHOR]

Tongue diagnosis is an essential part of diagnosing most illnesses, so tongue diagnosis has gained a lot of attention from experts. Tongue diagnosing is generally done by handling pictures of the tongue; however, this isn't done in Western medication. The objective of this paper is to overcome any barrier among Chinese and Western medication, just as improve the nature of division, so we proposed a consecutive strategy for preparing tongue pictures. The initial two kinds of quantitative highlights, chromatic and textural scales, are extricated from tongue pictures utilizing picture handling methods in the initial step of this system. The tongue's shape is extracted in the second shape detection process using an edge detector and an area increasing algorithm. The colour intensity extraction method is used to detect pimples and cracks in the third phase. The Level Set Algorithm produces excellent segmentation outcomes. Then the normal and abnormal tongue's mean and entropy values were compared. [ABSTRACT FROM AUTHOR]

In this paper visible and near-infrared hyperspectral imaging (VIS-NIR) was used to classify apples during sorting. At the same time the initial data from the SPECIM hyperspectrometer were subjected to preliminary processing in order to determine the NDVI vegetation indices, etc., which played the role of independent variables (predictors) in the discriminant analysis. Experimental results show that the multiple discriminant image analysis method has great potential for identifying apple defects such as rot, scab, wormholes, as well as for sorting apples by quality. At the same time errors of the second kind during the rejection of defect-free apples amounted to less than 4%. [ABSTRACT FROM AUTHOR]

The paper considers the problem of using end-to-end digital technologies and platform solutions using elements of artificial intelligence. Identification of goods prohibited to be transported across the customs border is accepted as the main object of research. Problematic issues of unambiguous identification of prohibited goods at the border with the use of inspection and inspection complexes are formulated. The dual energy method for recognizing the materials of a controlled object by the effective atomic number and the mathematical foundations of a computed tomography are outlined. Recommendations on the implementation of the method of nonlinear inverse projection and nonlinear tomosynthesis at a small number of projection angles of the controlled object of the developed model in practice are given. Around the world, the time of customs clearance of foreign trade cargoes is one of the key criteria for assessing the effectiveness of the customs service. The use of end-to-end digital technologies and platform solutions using artificial intelligence elements and decision support systems will make it possible to carry out customs control "invisibly" and quickly throughout the entire chain of goods movement [1]. As a tool to speed up customs procedures, prevent and suppress offenses at the border, high-tech equipment is used, including large-sized inspection complexes (IC). Currently, the customs authorities of the Republic of Uzbekistan are equipped with modern IC, which allow you to get an x-ray image of the vehicle and the goods transported in it. However, the analysis of X-ray images and the detection of items prohibited for transportation in them requires high qualifications from a customs officer. Consequently, the task of studying the methods of artificial intelligence and recognition of goods prohibited for transport across the customs border is relevant. Therefore, the task of researching artificial intelligence methods and automatic recognition of goods prohibited for transportation across the customs border is relevant. [ABSTRACT FROM AUTHOR]

Early identification and diagnosis of COVID-19 are critical factors in relation to infection constraints. Computed tomography imaging is considered a golden modality for detecting and evaluating lung COVID-19 infection. In this paper, a currently proposed algorithm has been developed for the three-dimensional visualization of infection regions, where the segmentation algorithm combines a grayscale morphological reconstruction technique with a fast marching method, then reconstructing the stacked two-dimensional infection regions into a three-dimensional faction based on a strategy of marching cubes, the results showed the consistent determination of ground glass opacity infection region compared to the manual delineation of a senior physician, The suggested approach promotes robust medical image analysis based on sparse data and improves COVID-19 segmentation technology state of the art. [ABSTRACT FROM AUTHOR]

Digital image processing techniques have been widely used in the medical field, including in medical image analysis. One part of the image processing technique that plays an essential role in medical image analysis is image segmentation. This paper will discuss the performance of conventional edge detection, which consists of the Sobel, Canny, Prewitt, and Robert methods in segmenting the lungs, especially COVID19 patients. Based on the conventional edge detection method, we conducted a trial of measuring the lung area and the white patches contained therein. In addition, we compared the area between the lungs of normal patients and the lungs of Covid patients. The experimental results show that of the four types of conventional edge detection methods used, all of them have almost the same performance both in processing time and the results of the calculation of lung area obtained. Based on the experimental results, the conventional edge detection method can be considered for further development. [ABSTRACT FROM AUTHOR]

Many times, the use of image processing techniques becomes a vital tool in investigation processes of security applications. This paper elaborates an attempt made in image processing domain which is needed in investigation processes of security applications to achieve deblurring of images using Wiener and Inverse filters and the comparative study on the basis of image parameters. For accurate investigation and observations, improved quality of the defocused images can be obtained using the filtering process through which blur or noise can be removed. Such blur or noise gets induced in the captured images due to shaking of security camera while continuously moving to capture the area under surveillance, improper maintenance of such camera system or unlearned lenses of the camera. The improper illumination of the area under surveillance or the fast movement of the object itself also creates sometimes a blur in the captured images. In this work, two filters namely Wiener filter and Inverse filter are used to remove the noise and to restore the images after its quality improvement. Further to understand the quality improvement of the images, an analysis of restored images is done on the basis of image parameters. Finally, the obtained results are reported in tabulated form along with the graphs of original and restored image parameters. [ABSTRACT FROM AUTHOR]

This paper presents a computational method to extract optimum rectangular Regions of Interest (RoI) in images with an associated saliency map. Although saliency maps provide an individual relevance measure for each pixel, to find the sub-image (i.e., rectangular region) that contains the set of the most relevant pixels requires an optimisation procedure to define the boundaries of the best RoI. This is achieved by the method devised in the paper, by following an approach based on balancing the amount of relevant information that is included and excluded from the RoI. The results show that such method is capable of finding the most relevant rectangular RoI and thus to extract the optimum sub-images according to the relevance measure given by a generic saliency map. Since the method is not tied to any particular type of images, it finds application in quite different fields, such as salient object extraction and processing in industry and surveillance, image compression using attention modelling, biomedical imaging, etc. [ABSTRACT FROM AUTHOR]

In this paper, a method based on high and low threshold is proposed to detect the ship edge feature due to the low accuracy rate caused by the noise. Analyze the relationship between human vision system and the target features, and to determine the ship target by detecting the edge feature. Firstly, using the second-order differential method to enhance the quality of image; Secondly, to improvement the edge operator, we introduction of high and low threshold contrast to enhancement image edge and non-edge points, and the edge as the foreground image, non-edge as a background image using image segmentation to achieve edge detection, and remove the false edges; Finally, the edge features are described based on the result of edge features detection, and determine the ship target. The experimental results show that the proposed method can effectively reduce the number of false edges in edge detection, and has the high accuracy of remote sensing ship edge detection. [ABSTRACT FROM AUTHOR]

(COVID-19) is an epidemic disease with symptoms similar to the flu. Since December 2019, the new Coronavirus has appeared in China and spread all around the world. As a result, the rapid and severe spread. For example, computed tomography (CT) and x-rays are utilized to find an available and accurate diagnostic tool. Artificial intelligence technologies make a significant contribution to the diagnosis and analysis of medical images. As a consequence, it was used to detect and diagnose Covid-19. Thus, the entire major medical scanning will be covered in this review paper, especially Focus mostly on last year's combination of Artificial Intelligence with CT and X-ray. Both are commonly used on front-line medical clinics to identify the recent results of fighting COVID-19. [ABSTRACT FROM AUTHOR]

In this paper, we have designed an Ear will identify that person. Nowadays, Biometric identification has a few applications, particularly in the security framework. One of the mainstream biometric recognizable pieces of proof is individual distinguishes through ear because every individual has an extraordinary ear example. It doesn't change rapidly; it may take less time to change than other identification. In this, we have to capture the person's ear image, and then we have analyzed the ear image use of image processing and conventional neural network. To enhance the ear images for analysis, we use grayscale histogram features to make the photos fit for the study of ear patterns. We have also used the Feature Extraction technique for calculating the entropy of the image, with the help of entropy value, contrast, and energy. We can find whether the person is authenticated/ accessible or not. Our Approach (with ≥ 75% overlap) and time taken to identify in seconds are 1.77, and the detection rate is 96.35% (331 2D images). [ABSTRACT FROM AUTHOR]

In this paper we present a novel system for the tracing of the semicircle line during the play of a basketball game. One of the difficult decisions for a referee in such a game play is to establish if a player traced the semicircle line during a throw to the basket. A wide range of solutions are focused on the image detection techniques which require a lot of expensive cameras and data processors for the run of the classification algorithms. For the moment none of this image analysis technique are 100% accurate. Our system is built around a mesh of ESP8266 system on chip microcontroller. To each ESP8266 block a set of IR proximity sensors are connected and RFID tag reader. All the players are identified by a unique RFID tag code which will identify the player who traced the line. All the data acquired from the sensors is processed by the microcontrollers and saved into the cloud. [ABSTRACT FROM AUTHOR]

Pothole detection is a challenging task as it involves inhomogeneity in intensity, complex topologies, contrast less, and noise rich background. Still, it's a very important task concerning the maintenance of roads. Potholes are being detected using computer vision which generally involves analysis of a two-dimensional image of the road or modeling of the road surface. Provided both these methods are independently used. The accuracy of this method of pothole detection is far from the top point. These bring the usage of digital image processing which develops the detection of potholes with at most accuracy. Digital Image processing provides strong receptivity, usage of huge actions, and broad benefits. In this paper, we propose a system that supports digital image processing techniques of high efficiency to result in consistent and accurate detection of potholes. This project studies an intelligent digital industrial pothole detection mechanism to increase human safety, detection capability and decrease the factor of risk. Firstly, the sources of images from the road are pre-processed to remove noise and other irrelevant features. Then a training model was developed to train the system to classify between path holes and normal cracks using convolution neural networks and MATLAB. Also, an IoT device is used in this system which updates the detected potholes on the road to the respective web server along with the location coordinates, as a part to notify a complaint to check. This system works on providing a better pothole detection technique and also updating the same to the concerned. [ABSTRACT FROM AUTHOR]

In image processing fusion having a significant importance for different applications. Generally the process of image fusion is applied in multiple image and get output is one image. Now a day's fusion is most popular in machine perception so we need accurate images after applying the fusion techniques. So in this work we compared different fusion techniques and analyzed their performance. Here different masks are applied in the images using discrete cosine transform (DCT) for better results. Out of different masking's fanshaped mask gives better quality fused images. In multimodal identification systems requires the multiple image processing technques can be fused in this context the more accurated fused techniques required,so in this proposed work we provide the best fused techniques using masking techniques. Masking is a process of get some piece of information from the image based on the piece of information from the image modify the entire remaining image. In this paper study the different image processing fusion techniques and compare those fusion techniques given a comparative results. The results help full to the researcher which fusion techniques is better suitable for their work. [ABSTRACT FROM AUTHOR]

When processing and analyzing images in everyday life, we often face tasks requiring identification and description of shapes, colors, or positions of objects. Sometimes a small detail is sufficient to give the image a different structure. A good example could be the detection of ionizing radiation, where irradiated passive solid state track detectors could be used to produce digital images containing tracks created by radiation. For the analysis of such images possessional tools are available at the market, such as the TASLImage system. TASLImage produces images from the CR-39 solid state track detectors and then analyses the tracks created by radiation based on specific parameter reflecting the type and intensity of radiation. Commercial systems, such as TASLImage are validated tools for specific applications, hence not allowing the user modifying its a source code and implementing new features. This could be overcome if the evaluation software is developed by the user. In this paper, we will describe the design of the ImageAnalyzer program that will be used in the same way as TASLImage to evaluate digital images of irradiated solid state track detectors. [ABSTRACT FROM AUTHOR]

In this paper, sufficient scientific research on identifing the similarities of two images has been conducted, and information on the availability of sufficient algorithms and software products in this area has been provided. The recognition algorithm consists of comparing two images and determining their similarity. The authors have developed a comprehensive analysis of existing algorithms for the recognition process, taking into account their capabilities and shortcomings. A new criterion, algorithm and software are developed for the recognition process, as well as the examples showing its performance and high level of accuracy has been proved. [ABSTRACT FROM AUTHOR]

Deep Learning is the process to led machine learning, natural language processing and neural networks. The various deep learning models, computer vision systems and artificial intelligence services are used to study of various real time applications. Due to lack of computing resource the conventional neural network are produces delay in progress and reduce the GPUs performance and throughput. In this paper we review difference deep learning approaches with increases GPUs performance and apply various image processing classification and localization techniques. The high availability and GPUs performance can be verified by state-of-arts results using conventional deep learning methods. [ABSTRACT FROM AUTHOR]

Injection molding simulation (Sigmasoft) is applied to increase the understanding of the emerging surface properties of ABS and PC/ABS parts after etching within the process of electroplating on plastics. The investigation is based on surface information gained by already published analyses with two-dimensional data (Scanning-Electron-Microscope combined with image analysis) and three-dimensional information stemming from confocal microscopy. With the aim of detecting correlations, this data is compared to local simulation results (e.g. shear rate, temperature, viscosity). The consequent pattern of results indicates a substantial correlation between the deformation tendencies of the butadiene particles and the simulated shear rates. Furthermore, the effect of local temperatures on the relaxation of the butadiene can be detected. The investigation is performed at four different positions on the part and the simulation results show differences caused by geometry. In addition, the simulated shrinkage potential is identified as important indicator of residual stresses within the part. The results show that higher simulated shrinkage potential affects the etching process and the resulting cavern structures, which are quality defining for the layer system. This paper focuses on a selection of results for ABS out of a huge amount of results generated for ABS as well as for PC/ABS. [ABSTRACT FROM AUTHOR]

The 3D chaotic nature of paper makes it a very valuable source of random bits that can be extracted by optical probing and image processing. Moreover the same bit series can be re-extracted with a high probability when re-probing the same object sample. We present here the general approach used for the digital extraction. Some applications of such a True Repeatable Random Number Generator in Morpho-cryptography are described. [ABSTRACT FROM AUTHOR]

The paper considers the problems of constructing a fashion image for people with disabilities. The paper substantiates the actuality and relevance of designing clothing and accessories adapted for people with disabilities from the position of the social aspect and the economic aspect. The article presents the results of the research, which are based on the method of intent analysis of the cases of collections' demonstration for people with disabilities within the framework of International Fashion Weeks 2014-2021; the analysis of advertising campaigns of clothing and accessories brands, where disabled people were one of the target audience segments; the content analysis of visual images of different types of fashionable clothes for people with disabilities from open sources. The peculiarities of clothing design for people with different types of disabilities are highlighted. Different typologies of techniques for creating a fashion image of people with disabilities in the contemporary media space are highlighted. [ABSTRACT FROM AUTHOR]

This paper presents the theoretical basis for treating hydrodynamic problems in which the use of ellipsoidal harmonics is necessary. Those include the water wave diffraction problem, the wave resistance problem and the added mass - attraction force calculation of an ellipsoid moving steadily close to a rigid wall. All these problems are tackled using Miloh's theorem for the ultimate image singularity system of ellipsoidal harmonics. [ABSTRACT FROM AUTHOR]

In this paper, a novel algorithm is proposed. Firstly, the edge of cover image is detected with Canny operator and secret data is embedded in edge pixels. Sorting method is used to randomize the edge pixels in order to enhance security. Coherent bit length L is determined by relevant edge pixels. Finally, the method of 2k correction is applied to achieve better imperceptibility in stego image. The experiment shows that the proposed method is better than LSB-3 and Jae-Gil Yu's in PSNR and capacity. [ABSTRACT FROM AUTHOR]