Image Processing Procedure Research Articles

Lightweight Deep Learning Algorithm for Sorting Medical Waste Embedded System

The recent COVID-19 pandemic has led to an increased number of hospitalized patients, and in some countries, the overwhelming problem has even caused the collapse of the healthcare system. Thus, the associated waste generated and inadequate waste disposal may have deleterious impacts on public health and the surrounding environment. This paper aims to design and implement an automatic medical waste identification and sorting mechanism that can distinguish the items disposed of via a series of image processing procedures. Specifically, the system can classify, sort, and calculate the disposed items based on their visual appearance. To establish this, both software and hardware systems have been devised. Particularly, the vision system for object detection and classification is constructed based on several popular pre-trained convolutional neural networks. Upon verifying the type of waste (i.e., general infection, dangerous infection, and general garbage), an automatic sorting mechanism will be triggered to dispose of the object in the corresponding garbage bin. The experimentation has been validated on a total of self-collected 2025 images from 3 categories, and the best accuracy attained is 99.34% when adopting GoogLeNet as the backbone architecture.

Active dosimetry for VHEE FLASH radiotherapy using beam profile monitors and charge measurements

The discovery of the FLASH effect has revealed a high potential for treating cancer more efficiently by sparing healthy tissue. The surge in related medical research activities over the last couple of years has triggered a demand for technology with the capability of generating and measuring ionizing radiation at ultra-high dose-rates (UHDR). A reliable dosimetry system is an integral part of a radiotherapy machine. Because existing active dosimetry methods are unable to handle the dose-rates required for FLASH, UHDR dosimetry has emerged as an important area of research. In this paper we present an active dosimetry method based on a scintillating screen and an integrating current transformer. This method provides a simultaneous measurement of the absolute dose delivery as well as the 2D dose distribution. The measurements have been correlated with corresponding readings from radiochromic films (RCFs), and a procedure for image processing has been established. Moreover, different methods of calibrating the active dosimetry system against RCFs have been introduced and evaluated. Lastly, we present results which demonstrate that an agreement with RCFs of better than 5% can be realistically expected if camera parameters are carefully optimized.

Quantification of immiscible displacement in a rough-walled fracture through direct visualization

Subsurface substance migration in the fractured rock aquifer is mainly controlled by fractures, and immiscible fluid-fluid displacement in fractures is important to many geophysical processes and engineering activities. Using a fracture-visualization system, we present the qualitative and quantitative assessment of fracture geometry associated with fluid movement and distribution in the rough fracture. Based on fracture geometry and statistical analysis, we first conducted a quantitative study of fracture surface roughness and aperture distribution. Then, fractal dimensions of displacement front and residual oil distribution were determined by image processing procedures. Influenced by wettability and micro-scale roughness, at the end of the displacement, residual oil saturation of molded sample is lower (6.45%–25.74%), and displacement pattern is more uniform, indicating that displacement effect is better. Due to smaller differences in residual oil saturation (9.08%) under different injection directions, the impact of wettability on the displacement process is greater than that of anisotropic roughness. Additionally, the fractal dimension of the displacement front increased under low injection rates initially but decreased when the rate was increased later. Overall, visualized temporal monitoring of experimental images enabled us to provide a preliminary assessment of the impact of anisotropic roughness and the material constituting the fracture wall on invading fluid saturation and the fractal dimension of the displacement front under various injection rates.

Hybrid clinical-radiomics model based on fully automatic segmentation for predicting the early expansion of spontaneous intracerebral hemorrhage: A multi-center study

BackgroundEarly prediction of hematoma expansion (HE) is important for the development of therapeutic strategies for spontaneous intracerebral hemorrhage (sICH). Radiomics can help to predict early hematoma expansion in intracerebral hemorrhage. However, complex image processing procedures, especially hematoma segmentation, are time-consuming and dependent on assessor experience. We provide a fully automated hematoma segmentation method, and construct a hybrid predictive model for risk stratification of hematoma expansion. PurposeTo propose an automatic approach for predicting early hemorrhage expansion after spontaneous intracerebral hemorrhage using deep-learning and radiomics methods. MethodsA total of 258 patients with sICH were retrospectively enrolled for model construction and internal validation, while another two cohorts (n=87, 149) were employed for independent validation. For hemorrhage segmentation, an iterative segmentation procedure was performed to delineate the area using an nnU-Net framework. Radiomics models of intra-hemorrhage and multiscale peri-hemorrhage were established and evaluated, and the best discriminative-scale peri-hemorrhage radiomics model was selected for further analysis. Combining clinical factors and intra- and peri-hemorrhage radiomics signatures, a hybrid nomogram was constructed for the early HE prediction using multivariate logistic regression. For model validation, the receiver operating characteristic (ROC) curve analyses and DeLong test were used to evaluate the performances of the constructed models, and the calibration curve and decision curve analysis were performed for clinical application. ResultsOur iterative auto-segmentation model showed satisfactory results for hematoma segmentation in all four cohorts. The Dice similarity coefficient of this hematoma segmentation model reached 0.90, showing an expert-level accuracy in hematoma segmentation. The consumed time of the efficient delineation was significantly decreased, from 18 min to less than 2 min, with the assistance of the auto-segmentation model. The radiomics model of 2-mm peri-hemorrhage had a preferable area under ROC curve (AUC) of 0.840 (95 % confidence interval [CI]: 0.768, 0.912) compared with the original (0-mm dilatation) model with an AUC of 0.796 (95 % CI: 0.717, 0.875). The clinical–radiomics hybrid model showed better performances for HE prediction, with AUC of 0.853, 0.852, 0.772, and 0.818 in the training, internal validation, and independent validation cohorts 1 and 2, respectively. ConclusionsThe fully automatic clinical–radiomics model based on deep learning and radiomics exhibits a good ability for hematoma segmentation and a favorable performance in stratifying HE risks.

Application of a dual-modality colorimetric analysis methodto inkjet printing lateral flow detection of Salmonella typhimurium.

Lateral flow assay (LFA) color signal quantification methods were developed by utilizing both International Commission on Illumination (CIE) LAB (CIELAB) color space and grayscale intensity differences. The CIELAB image processing procedure included calibration, test, control band detection, and color difference calculation, which can minimize the noise from the background. The LFA platform showcases its ability to accurately discern relevant colorimetric signals. The rising occurrence of infectious outbreaks from foodborne pathogens like Salmonella typhimurium presents significant economic, healthcare, and public health risks. The study introduces an aptamer-based lateral flow (ABLF) platform by using inkjet printing for specially detecting S. typhimurium. The ABLF utilized gold-decorated polystyrene microparticles, functionalized with specific S. typhimurium aptamers (Ps-AuNPs-ssDNA). The platform demonstrates a detection limit of 102 CFU mL-1 in buffer solutions and 103 CFU mL-1 in romaine lettuce tests. Furthermore, it sustained performance for over 8 weeks at room temperature. The ABLF platform and analysis methods are expected to effectively resolve the low-sensitivity problems of the former LFA systems and to bridge the gap between lab-scale platforms to market-ready solutions by offering a simple, cost-effective, and consistent approach to detecting foodborne pathogens in real samples.

Identification Tools of Microplastics from Surface Water Integrating Digital Image Processing and Statistical Techniques.

The primary objective of this study was to demonstrate the potential of digital image analysis as a tool to identify microplastic (MP) particles in surface waters and to facilitate their characterisation in terms of 2D and 3D morphology. Digital image analysis preceded by microscopic analysis was used for an exhaustive quantitative and qualitative evaluation of MPs isolated from the Vistula River. Using image processing procedures, 2D and 3D shape descriptors were determined. Principal Component Analysis was used to interpret the relationships between the parameters studied, characterising MP particle geometry, type and colour. This multivariate analysis of the data allowed three or four main factors to be extracted, explaining approximately 90% of the variation in the data characterising MP morphology. It was found that the first principal component for granules, flakes and films was largely represented by strongly correlated with 2D shape descriptors (area, perimeter, equivalent area diameter) and 3D shape descriptors (Corey Shape Factor, Compactness, Dimensionality). Considering the scraps, principal component PC1 was represented by only five of the above descriptors, and the Compactness variable had the largest contribution to principal component PC2. In addition, for granules, flakes and films, a relationship between 2D shape and the colour of their particles could be observed. For the most numerous MP group identified of multicoloured scraps, no such association was found. The results of our study can be used for further multivariate analysis regarding the presence of microplastic floating on the river surface, with a particular focus on particles of secondary origin. This is of key importance for optimising future efforts in conducting small-scale and multidimensional monitoring of and reducing plastics in the aquatic environment.

An image processing approach for fatigue crack identification in cellulose acetate replicas

The cellulose acetate replication technique is an important method for studying material fatigue. However, extracting accurate information from pictures of cellulose replicas poses challenges because of distortions and numerous artifacts. This paper presents an image processing procedure for effective fatigue crack identification in plastic replicas. The approach employs thresholding, adaptive Gaussian thresholding, and Otsu binarization to convert gray-scale images into binary ones, enhancing crack visibility. Morphological operations refine object shapes, and Connected Components Analysis facilitates crack identification. Despite limited data, the handcrafted feature extraction algorithm proves robust, addressing challenges. The algorithm shows efficacy in detecting cracks as small as 30 μm, even in the presence of cellulose replication artifacts. The results highlight ability to capture significant cracks’ orientation, length, and growth stages, essential for understanding fatigue mechanisms. Analysis of results, especially evaluation metrics encompassing false positives and false negatives, provides a comprehensive understanding of the algorithm’s strengths and limitations. The proposed tool is available on GitHub.

MA‐ResUNet: Multi‐attention optic cup and optic disc segmentation based on improved U‐Net

AbstractGlaucoma poses a significant threat to vision, capable of causing irreversible damage and, in severe instances, leading to permanent blindness. Accurate optic cup (OC) and optic disc (OD) segmentation are essential in glaucoma screening. In this study, a novel OC and OD segmentation approach is proposed. Based on U‐Net, it is optimized by introducing cardinality dimensions. Moreover, attention gates are implemented to reinforce salient features while suppressing irrelevant information. Additionally, a convolutional block attention module (CBAM) is integrated into the decoder segment. This fusion hones in on effective information in both channel and spatial dimensions. Meanwhile, an image processing procedure is proposed for image normalization and enhancement. All of these increase the accuracy of the model. This model is evaluated on the ORIGA and REFUGE datasets, demonstrating the model's superiority in OC and OD segmentation compared to the state‐of‐the‐art methods. Additionally, after the proposed image processing, cup‐to‐disc ratio (CDR) prediction on a batch of 155 in‐house fundus images yields an absolute CDR error of 0.099, which is reduced by 0.04 compared to the case where only conventional processing was performed.

Experimental and Numerical Study of Computer Vision-Based Real-Time Monitoring of Polymeric Particle Mixing Process in Rotary Drum.

In the drum mixing of particulate polymers, segregation may occur. By measuring the mixing status in real time, it is possible to implement corrective measures to prevent separation and improve the efficiency of the process. This study aims to develop and validate a real-time vision system designed to monitor the mixing process of polymeric particles in a rotary drum mixer, employing a novel centroid-based model for determining the mixing index. The proposed centroid-based model is capable of addressing the radial particle segregation issue without the need for extra image-processing procedures like image subdivision or pixel randomization. This innovative approach greatly improves computational efficiency by processing over 68 image frames per second. The new processing method is 2.8 times faster than the gray-level co-occurrence matrix method and 21.6 times faster than the Lacey index approach. This significantly improves real-time monitoring capabilities and enables real-time image processing using only affordable single-board computers and webcams. The proposed vision-based system for monitoring rotary drum mixing has undergone validation via cross-validation using discrete element method simulations, ensuring its accuracy and reliability.

Application of gaussian filter and extraction features for quality control of fruit raw materials in the puree industry

The purpose of research in using Android-based raw material quality control applications in fruit puree factories is to enhance the industry's precision, uniformity, and efficiency. This application is developed to implement digital image processing utilizing two distinct methods: Gaussian filters and feature extraction. The implemented application captures guava data using the camera of an Android phone and subsequently resizes the image to dimensions of 600x600 pixels. Subsequently, the image colors are recovered by employing a Gaussian filter that operates on normalized Red-Green-Blue values. A minimum of 120 photos of red guava fruit from the raw material of one of the puree companies were subjected to image processing procedures. The application solely focuses on the color and texture of the fruit's skin, ensuring that the sample remains undamaged while adhering to hygienic guidelines. The ripeness degree of guava fruit is determined by employing an image classification algorithm with the K-nearest neighbor method. The application validation using K-fold cross-validation achieved an accuracy of 90.0% and a precision of 90.27% when applied to color imagery. When feature extraction was used, the accuracy was 83.3%, with a precision of 83.4%. Color extraction provides a more precise method for identifying ripe guava. The utilization of guava fruit ripeness detection in the quality control of raw materials for the puree sector has been simplified and made more user-friendly through the development of an Android-based application. Officers are not obligated to possess specialized expertise regarding the quality of raw materials.

An improved model for wavelet coefficients estimation and its application to image denoising

Image denoising is a significant procedure in image processing, and a good denoising method can improve the image quality. This study focuses on enhancing the estimation model of wavelet coefficients by improving the threshold function. Thus, a general construction method for a class of threshold functions is introduced, and sufficient conditions are given to ensure that the threshold functions are continuous, first-order differentiable and higher-order differentiable. It makes an existing class of improved threshold functions a particular case and enables the construction of other needed threshold functions based on this general approach. Experiments have shown that using the new threshold functions yields better denoising results for images containing salt and pepper noise, Gaussian noise and speckle noise. Moreover, as the smoothness of the threshold function is enhanced, the denoising effect is also improved. The improved wavelet coefficients estimation model can effectively boost the quality of image denoising, further enhancing the accuracy and effectiveness of computer vision algorithms.

Enhancement fracture behavior of sustainable cementitious composites using synergy between fly ash (FA) and nanosilica (NS) in the assessment based on digital image processing procedure

The present study has investigated the strength properties and fracture toughness of concrete composites reinforced 5 % nanosilica (NS) by adding different contents of fly ash (FA), i.e.: 0 %, 15 % and 25 %. The evaluated fracture toughness, under three-point flexural loads, were critical stress intensity factor (KIcS) and critical crack tip opening displacement (CTODc). Digital image processing procedure was used in this studies. It was stated that both the 5 % addition of NS and the total share of the nanomodifier with FA grains in the composition of the concrete mix significantly improve the strength properties of concretes, as well as their fracture toughness under first model of cracking in linear and non-linear terms. Moreover, it was observed that in concrete containing only NS the fracture process was clearly delayed and relatively short, whereas crack patterns in this composite were almost perfectly straight with significant crack width. On the other hand, in concretes icorporating NS + FA crack patterns were strongly curved (frequently with branching) with few microcracks in the vicinity of the main cracks. Concretes including FA and NS can be used in the execution of specific types of reinforced concrete structures subjected to fatigue or dynamic loads, e.g. bridge structures or industrial buildings.

Torsion constants and virtual mechanical tests are valid image-based surrogate measures of ovine fracture healing.

In large animal studies, the mechanical reintegration of the bone fragments is measured using postmortem physical testing, but these assessments can only be performed once, after sacrifice. Image-based virtual mechanical testing is an attractive alternative because it could be used to monitor healing longitudinally. However, the procedures and software required to perform finite element analysis (FEA) on subject-specific models for virtual mechanical testing can be time consuming and costly. Accordingly, the goal of this study was to determine whether a simpler image-based geometric measure-the torsion constant, sometimes known as polar moment of inertia-can be reliably used as a surrogate measure of bone healing in large animals. To achieve this, postmortem biomechanical testing and microCT scans were analyzed for a total of 33 operated and 20 intact ovine tibiae. An image-processing procedure to compute the attenuation-weighted torsion constant from the microCT scans was developed in MATLAB and this code has been made freely available. Linear regression analysis was performed between the postmortem biomechanical data, the results of virtual mechanical testing using FEA, and the torsion constants measured from the scans. The results showed that virtual mechanical testing is the most reliable surrogate measure of postmortem torsional rigidity, having strong correlations and high absolute agreement. However, when FEA is not practical, the torsion constant is a viable alternative surrogate measure that is moderately correlated with postmortem torsional rigidity and can be readily calculated.

Integrated Automatic Optical Inspection and Image Processing Procedure for Smart Sensing in Production Lines.

An integrated automatic optical inspection (iAOI) system with a procedure was proposed for a printed circuit board (PCB) production line, in which pattern distortions and performance deviations appear with process variations. The iAOI system was demonstrated in a module comprising a camera and lens, showing improved supportiveness for commercially available hardware. The iAOI procedure was realized in a serial workflow of image registration, threshold setting, image gradient, marker alignment, and geometric transformation; furthermore, five operations with numerous functions were prepared for image processing. In addition to the system and procedure, a graphical user interface (GUI) that displays sequential image operation results with analyzed characteristics was established for simplicity. To demonstrate its effectiveness, self-complementary Archimedean spiral antenna (SCASA) samples fabricated via standard PCB fabrication and intentional pattern distortions were demonstrated. The results indicated that, compared with other existing methods, the proposed iAOI system and procedure provide unified and standard operations with efficiency, which result in scientific and unambiguous judgments on pattern quality. Furthermore, we showed that when an appropriate artificial intelligence model is ready, the electromagnetic characteristic projection for SCASAs can be simply obtained through the GUI.

PulmoNet: a novel deep learning based pulmonary diseases detection model

Pulmonary diseases are various pathological conditions that affect respiratory tissues and organs, making the exchange of gas challenging for animals inhaling and exhaling. It varies from gentle and self-limiting such as the common cold and catarrh, to life-threatening ones, such as viral pneumonia (VP), bacterial pneumonia (BP), and tuberculosis, as well as a severe acute respiratory syndrome, such as the coronavirus 2019 (COVID-19). The cost of diagnosis and treatment of pulmonary infections is on the high side, most especially in developing countries, and since radiography images (X-ray and computed tomography (CT) scan images) have proven beneficial in detecting various pulmonary infections, many machine learning (ML) models and image processing procedures have been utilized to identify these infections. The need for timely and accurate detection can be lifesaving, especially during a pandemic. This paper, therefore, suggested a deep convolutional neural network (DCNN) founded image detection model, optimized with image augmentation technique, to detect three (3) different pulmonary diseases (COVID-19, bacterial pneumonia, and viral pneumonia). The dataset containing four (4) different classes (healthy (10,325), COVID-19 (3,749), BP (883), and VP (1,478)) was utilized as training/testing data for the suggested model. The model’s performance indicates high potential in detecting the three (3) classes of pulmonary diseases. The model recorded average detection accuracy of 94%, 95.4%, 99.4%, and 98.30%, and training/detection time of about 60/50 s. This result indicates the proficiency of the suggested approach when likened to the traditional texture descriptors technique of pulmonary disease recognition utilizing X-ray and CT scan images. This study introduces an innovative deep convolutional neural network model to enhance the detection of pulmonary diseases like COVID-19 and pneumonia using radiography. This model, notable for its accuracy and efficiency, promises significant advancements in medical diagnostics, particularly beneficial in developing countries due to its potential to surpass traditional diagnostic methods.

Review of Satellite Remote Sensing and Unoccupied Aircraft Systems for Counting Wildlife on Land

Although many medium-to-large terrestrial vertebrates are still counted by ground or aerial surveys, remote-sensing technologies and image analysis have developed rapidly in recent decades, offering improved accuracy and repeatability, lower costs, speed, expanded spatial coverage and increased potential for public involvement. This review provides an introduction for wildlife biologists and managers relatively new to the field on how to implement remote-sensing techniques (satellite and unoccupied aircraft systems) for counting large vertebrates on land, including marine predators that return to land to breed, haul out or roost, to encourage wider application of these technological solutions. We outline the entire process, including the selection of the most appropriate technology, indicative costs, procedures for image acquisition and processing, observer training and annotation, automation, and citizen science campaigns. The review considers both the potential and the challenges associated with different approaches to remote surveys of vertebrates and outlines promising avenues for future research and method development.

An Integrated Framework for Image Acquisition, Processing, and Analysis Procedures for Automated Damage Evaluation of Concrete Surfaces.

Concrete surface cracks serve as early indicators of potential structural threats. Visual inspection, a commonly used and versatile concrete condition assessment technique, is employed to assess concrete degradation by observing signs of damage on the surface level. However, the method tends to be qualitative and needs to be more comprehensive in providing accurate information regarding the extent of damage and its evolution, notwithstanding its time-consuming and environment-sensitive nature. As such, the integration of image analysis techniques with artificial intelligence (AI) has been increasingly proven efficient as a tool to capture damage signs on concrete surfaces. However, to improve the performance of automated crack detection, it is imperative to intensively train a machine learning model, and questions remain regarding the required image quality and image collection methodology needed to ensure the model's accuracy and reliability in damage quantitative analysis. This study aims to establish a procedure for image acquisition and processing through the application of an image-based measurement approach to explore the capabilities of concrete surface damage diagnosis. Digitizing crack intensity measurements were found to be feasible; however, larger datasets are required. Due to the anisotropic behavior of the damage, the model's ability to capture crack directionality was developed, presenting no statistically significant differences between the observed and predicted values used in this study with correlation coefficients of 0.79 and 0.82.

A fast and efficient numerical algorithm for image segmentation and denoising

<abstract><p>Image segmentation is the process of partitioning an image into homogenous regions, and represents one of the most fundamental and important procedures in image processing. Image denoising is a process to remove unwanted noise from a digital image, enhancing its visual quality. Various algorithms, like non-local means and deep learning-based approaches, have been developed to remove noise while preserving important image details. Currently, the prevalent application of pattern recognition technology is achieved through the implementation of image segmentation algorithms. In this study, we present a new, highly efficient, and fast computational scheme specifically developed for a phase-field mathematical model of image segmentation. The numerical methodology is based on an operator splitting method (OSM). The split operators are solved by using closed-form analytic solutions and a finite difference method (FDM) with an alternating direction explicit (ADE) method. To show the notable efficiency and rapid computational performance of the proposed computational algorithm, we conduct a series of numerical experiments. Through these computational tests, we confirm a significant contribution to the advancement of methodologies employed in the critical domain of image processing.</p></abstract>

Finding the Most Dominant Color in an Image using K-Means Algorithm Based on Machine Learning

Abstract: The research project, titled "Finding the Most Dominant Color in an Image Using K-Means Algorithm," leverages machine learning techniques to extract fundamental color information from digital photographs. Employing the K-Means clustering methodology, this research identifies the most prominent colors in an image by grouping pixels with similar color values. This innovative approach holds significant real-world implications across various domains, including text analysis, graphic design, and image processing. By automating the color extraction process, this study enhances the efficiency of tasks such as image classification, object detection, and the generation of visual content. It demonstrates the power of machine learning in simplifying complex image processing procedures, offering the potential to enhance a wide range of visual-based applications.

CMID: Crossmodal Image Denoising via Pixel-Wise Deep Reinforcement Learning.

Removing noise from acquired images is a crucial step in various image processing and computer vision tasks. However, the existing methods primarily focus on removing specific noise and ignore the ability to work across modalities, resulting in limited generalization performance. Inspired by the iterative procedure of image processing used by professionals, we propose a pixel-wise crossmodal image-denoising method based on deep reinforcement learning to effectively handle noise across modalities. We proposed a similarity reward to help teach an optimal action sequence to model the step-wise nature of the human processing process explicitly. In addition, We designed an action set capable of handling multiple types of noise to construct the action space, thereby achieving successful crossmodal denoising. Extensive experiments against state-of-the-art methods on publicly available RGB, infrared, and terahertz datasets demonstrate the superiority of our method in crossmodal image denoising.