Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Segmentation des pores.
Статті в журналах з теми "Segmentation des pores"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "Segmentation des pores".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Sintorn, Ida-Maria, Stina Svensson, Maria Axelsson, and Gunilla Borgefors. "Segmentation of individual pores in 3D paper images." Nordic Pulp & Paper Research Journal 20, no. 3 (August 1, 2005): 316–19. http://dx.doi.org/10.3183/npprj-2005-20-03-p316-319.
Повний текст джерела
2
Bauer, Benjamin, Xiaohao Cai, Stephan Peth, Katja Schladitz, and Gabriele Steidl. "Variational-based segmentation of bio-pores in tomographic images." Computers & Geosciences 98 (January 2017): 1–8. http://dx.doi.org/10.1016/j.cageo.2016.09.013.
Повний текст джерела
3
Liu, Lei, Qiaoling Han, Yue Zhao, and Yandong Zhao. "A Novel Method Combining U-Net with LSTM for Three-Dimensional Soil Pore Segmentation Based on Computed Tomography Images." Applied Sciences 14, no. 8 (April 16, 2024): 3352. http://dx.doi.org/10.3390/app14083352.
Повний текст джерелаАнотація:
The non-destructive study of soil micromorphology via computed tomography (CT) imaging has yielded significant insights into the three-dimensional configuration of soil pores. Precise pore analysis is contingent on the accurate transformation of CT images into binary image representations. Notably, segmentation of 2D CT images frequently harbors inaccuracies. This paper introduces a novel three-dimensional pore segmentation method, BDULSTM, which integrates U-Net with convolutional long short-term memory (CLSTM) networks to harness sequence data from CT images and enhance the precision of pore segmentation. The BDULSTM method employs an encoder–decoder framework to holistically extract image features, utilizing skip connections to further refine the segmentation accuracy of soil structure. Specifically, the CLSTM component, critical for analyzing sequential information in soil CT images, is strategically positioned at the juncture of the encoder and decoder within the U-shaped network architecture. The validation of our method confirms its efficacy in advancing the accuracy of soil pore segmentation beyond that of previous deep learning techniques, such as U-Net and CLSTM independently. Indeed, BDULSTM exhibits superior segmentation capabilities across a diverse array of soil conditions. In summary, BDULSTM represents a state-of-the-art artificial intelligence technology for the 3D segmentation of soil pores and offers a promising tool for analyzing pore structure and soil quality.
4
Yosifov, Miroslav, Patrick Weinberger, Bernhard Plank, Bernhard Fröhler, Markus Hoeglinger, Johann Kastner, and Christoph Heinzl. "Segmentation of pores in carbon fiber reinforced polymers using the U-Net convolutional neural network." Acta Polytechnica CTU Proceedings 42 (October 12, 2023): 87–93. http://dx.doi.org/10.14311/app.2023.42.0087.
Повний текст джерелаАнотація:
This study demonstrates the utilization of deep learning techniques for binary semantic segmentation of pores in carbon fiber reinforced polymers (CFRP) using X-ray computed tomography (XCT) datasets. The proposed workflow is designed to generate efficient segmentation models with reasonable execution time, applicable even for users using consumer-grade GPU systems. First, U-Net, a convolutional neural network, is modified to handle the segmentation of XCT datasets. In the second step, suitable hyperparameters are determined through a parameter analysis (hyperparameter tuning), and the parameter set with the best result was used for the final training. In the final step, we report on our efforts of implementing the testing stage in open_iA, which allows users to segment datasets with the fully trained model within reasonable time. The model performs well on datasets with both high and low resolution, and even works reasonably for barely visible pores with different shapes and size. In our experiments, we could show that U-Net is suitable for pore segmentation. Despite being trained on a limited number of datasets, it exhibits a satisfactory level of prediction accuracy.
5
Tomažinčič, Dejan, Žiga Virk, Peter Marijan Kink, Gregor Jerše, and Jernej Klemenc. "Predicting the Fatigue Life of an AlSi9Cu3 Porous Alloy Using a Vector-Segmentation Technique for a Geometric Parameterisation of the Macro Pores." Metals 11, no. 1 (December 31, 2020): 72. http://dx.doi.org/10.3390/met11010072.
Повний текст джерелаАнотація:
Most of the published research work related to the fatigue life of porous, high-pressure, die-cast structures is limited to a consideration of individual isolated pores. The focus of this article is on calculating the fatigue life of high-pressure, die-cast, AlSi9Cu3 parts with many clustered macro pores. The core of the presented methodology is a geometric parameterisation of the pores using a vector-segmentation technique. The input for the vector segmentation is a μ-CT scan of the porous material. After the pores are localised, they are parameterised as 3D ellipsoids with the corresponding orientations in the Euclidian space. The extracted ellipsoids together with the outer contour are then used to build a finite-element mesh of the porous structure. The stress–strain distribution is calculated using Abaqus and the fatigue life is predicted using SIMULIA fe-safe. The numerical results are compared to the experimentally determined fatigue lives to prove the applicability of the proposed approach. The outcome of this research is a usable tool for estimating the limiting quantity of a structure’s porosity that still allows for the functional performance and required durability of a product.
6
Tong, Tong, Yan Cai, Da Wei Sun, and Peng Liu. "Automatic Segmentation of Pores in Weld Images Based on Transition Region Extraction." Applied Mechanics and Materials 217-219 (November 2012): 1964–67. http://dx.doi.org/10.4028/www.scientific.net/amm.217-219.1964.
Повний текст джерелаАнотація:
In allusion to the complex images of weld defects, weak contrast between the target and the background, a new segmentation method based on gray level difference transition region extraction is proposed. The paper analyzes the characteristic of weld defects, and then low-pass filtering and contrast enhanced are used to enhance the clarity. Finally, we extract the transition region and confirm a threshold for defects segmentation. The experimental results show that the method can extract the transition region more accurate, and segment the image much better in complex environment.
7
Yoon, Huisu, Semin Kim, Jongha Lee, and Sangwook Yoo. "Deep-Learning-Based Morphological Feature Segmentation for Facial Skin Image Analysis." Diagnostics 13, no. 11 (May 29, 2023): 1894. http://dx.doi.org/10.3390/diagnostics13111894.
Повний текст джерелаАнотація:
Facial skin analysis has attracted considerable attention in the skin health domain. The results of facial skin analysis can be used to provide skin care and cosmetic recommendations in aesthetic dermatology. Because of the existence of several skin features, grouping similar features and processing them together can improve skin analysis. In this study, a deep-learning-based method of simultaneous segmentation of wrinkles and pores is proposed. Unlike color-based skin analysis, this method is based on the analysis of the morphological structures of the skin. Although multiclass segmentation is widely used in computer vision, this segmentation was first used in facial skin analysis. The architecture of the model is U-Net, which has an encoder–decoder structure. We added two types of attention schemes to the network to focus on important areas. Attention in deep learning refers to the process by which a neural network focuses on specific parts of its input to improve its performance. Second, a method to enhance the learning capability of positional information is added to the network based on the fact that the locations of wrinkles and pores are fixed. Finally, a novel ground truth generation scheme suitable for the resolution of each skin feature (wrinkle and pore) was proposed. The experimental results revealed that the proposed unified method achieved excellent localization of wrinkles and pores and outperformed both conventional image-processing-based approaches and one of the recent successful deep-learning-based approaches. The proposed method should be expanded to applications such as age estimation and the prediction of potential diseases.
8
Song, Wenlong, Junyu Li, Kexin Li, Jingxu Chen, and Jianping Huang. "An Automatic Method for Stomatal Pore Detection and Measurement in Microscope Images of Plant Leaf Based on a Convolutional Neural Network Model." Forests 11, no. 9 (September 1, 2020): 954. http://dx.doi.org/10.3390/f11090954.
Повний текст джерелаАнотація:
Stomata are microscopic pores on the plant epidermis that regulate the water content and CO2 levels in leaves. Thus, they play an important role in plant growth and development. Currently, most of the common methods for the measurement of pore anatomy parameters involve manual measurement or semi-automatic analysis technology, which makes it difficult to achieve high-throughput and automated processing. This paper presents a method for the automatic segmentation and parameter calculation of stomatal pores in microscope images of plant leaves based on deep convolutional neural networks. The proposed method uses a type of convolutional neural network model (Mask R-CNN (region-based convolutional neural network)) to obtain the contour coordinates of the pore regions in microscope images of leaves. The anatomy parameters of pores are then obtained by ellipse fitting technology, and the quantitative analysis of pore parameters is implemented. Stomatal microscope image datasets for black poplar leaves were obtained using a large depth-of-field microscope observation system, the VHX-2000, from Keyence Corporation. The images used in the training, validation, and test sets were taken randomly from the datasets (562, 188, and 188 images, respectively). After 10-fold cross validation, the 188 test images were found to contain an average of 2278 pores (pore widths smaller than 0.34 μm (1.65 pixels) were considered to be closed stomata), and an average of 2201 pores were detected by our network with a detection accuracy of 96.6%, and the intersection of union (IoU) of the pores was 0.82. The segmentation results of 2201 stomatal pores of black poplar leaves showed that the average measurement accuracies of the (a) pore length, (b) pore width, (c) area, (d) eccentricity, and (e) degree of stomatal opening, with a ratio of width-to-maximum length of a stomatal pore, were (a) 94.66%, (b) 93.54%, (c) 90.73%, (d) 99.09%, and (e) 92.95%, respectively. The proposed stomatal pore detection and measurement method based on the Mask R-CNN can automatically measure the anatomy parameters of pores in plants, thus helping researchers to obtain accurate stomatal pore information for leaves in an efficient and simple way.
9
Soboleva, N. N., and A. N. Mushnikov. "Determination of the volume fraction of primary carbides in the microstructure of composite coatings using semantic segmentation." Frontier materials & technologies, no. 3 (2023): 95–102. http://dx.doi.org/10.18323/2782-4039-2023-3-65-9.
Повний текст джерелаАнотація:
In the process of formation of composite coatings, partial dissolution of hardening particles (most often carbides) in the matrix is possible; therefore, in some cases, the material creation mode is chosen taking into account the volume fraction of primary carbides not dissolved during coating deposition. The methods currently widely used for calculating the volume fraction of carbides in the structure of composite coatings (manual point method and programs implementing classical computer vision methods) have limitations in terms of the possibility of automation. It is expected that performing semantic segmentation using convolutional neural networks will improve both the performance of the process and the accuracy of carbide detection. In the work, multiclass semantic segmentation was carried out including the classification on the image of pores and areas that are not a microstructure. The authors used two neural networks based on DeepLab-v3 trained with different loss functions (IoU Loss and Dice Loss). The initial data were images of various sizes from electron and optical microscopes, with spherical and angular carbides darker and lighter than the matrix, in some cases with pores and areas not related to the microstructure. The paper presents mask images consisting of four classes, created manually and by two trained neural networks. The study shows that the networks recognize pores, areas not related to the microstructure, and perfectly segment spherical carbides in images, regardless of their color relative to the matrix and the presence of pores in the structure. The authors compared the proportion of carbides in the microstructure of coatings determined by two neural networks and a manual point method.
10
Wen, Hao, Chang Huang, and Shengmin Guo. "The Application of Convolutional Neural Networks (CNNs) to Recognize Defects in 3D-Printed Parts." Materials 14, no. 10 (May 15, 2021): 2575. http://dx.doi.org/10.3390/ma14102575.
Повний текст джерелаАнотація:
Cracks and pores are two common defects in metallic additive manufacturing (AM) parts. In this paper, deep learning-based image analysis is performed for defect (cracks and pores) classification/detection based on SEM images of metallic AM parts. Three different levels of complexities, namely, defect classification, defect detection and defect image segmentation, are successfully achieved using a simple CNN model, the YOLOv4 model and the Detectron2 object detection library, respectively. The tuned CNN model can classify any single defect as either a crack or pore at almost 100% accuracy. The other two models can identify more than 90% of the cracks and pores in the testing images. In addition to the application of static image analysis, defect detection is also successfully applied on a video which mimics the AM process control images. The trained Detectron2 model can identify almost all the pores and cracks that exist in the original video. This study lays a foundation for future in situ process monitoring of the 3D printing process.
11
Lingnau, Lars A., Johannes Heermant, Johannes L. Otto, Kai Donnerbauer, Lukas M. Sauer, Lukas Lücker, Marina Macias Barrientos, and Frank Walther. "Separation of Damage Mechanisms in Full Forward Rod Extruded Case-Hardening Steel 16MnCrS5 Using 3D Image Segmentation." Materials 17, no. 12 (June 20, 2024): 3023. http://dx.doi.org/10.3390/ma17123023.
Повний текст джерелаАнотація:
In general, formed components are lightweight as well as highly economic and resource efficient. However, forming-induced ductile damage, which particularly affects the formation and growth of pores, has not been considered in the design of components so far. Therefore, an evaluation of forming-induced ductile damage would enable an improved design and take better advantage of the lightweight nature as it affects the static and dynamic mechanical material properties. To quantify the amount, morphology and distribution of the pores, advanced scanning electron microscopy (SEM) methods such as scanning transmission electron microscopy (STEM) and electron channeling contrast imaging (ECCI) were used. Image segmentation using a deep learning algorithm was applied to reproducibly separate the pores from inclusions such as manganese sulfide inclusions. This was achieved via layer-by-layer ablation of the case-hardened steel 16MnCrS5 (DIN 1.7139, AISI/SAE 5115) with a focused ion beam (FIB). The resulting images were reconstructed in a 3D model to gain a mechanism-based understanding beyond the previous 2D investigations.
12
LIN, WEI, XIZHE LI, ZHENGMING YANG, LIJUN LIN, SHENGCHUN XIONG, ZHIYUAN WANG, XIANGYANG WANG, and QIANHUA XIAO. "A NEW IMPROVED THRESHOLD SEGMENTATION METHOD FOR SCANNING IMAGES OF RESERVOIR ROCKS CONSIDERING PORE FRACTAL CHARACTERISTICS." Fractals 26, no. 02 (April 2018): 1840003. http://dx.doi.org/10.1142/s0218348x18400030.
Повний текст джерелаАнотація:
Based on the basic principle of the porosity method in image segmentation, considering the relationship between the porosity of the rocks and the fractal characteristics of the pore structures, a new improved image segmentation method was proposed, which uses the calculated porosity of the core images as a constraint to obtain the best threshold. The results of comparative analysis show that the porosity method can best segment images theoretically, but the actual segmentation effect is deviated from the real situation. Due to the existence of heterogeneity and isolated pores of cores, the porosity method that takes the experimental porosity of the whole core as the criterion cannot achieve the desired segmentation effect. On the contrary, the new improved method overcomes the shortcomings of the porosity method, and makes a more reasonable binary segmentation for the core grayscale images, which segments images based on the actual porosity of each image by calculated. Moreover, the image segmentation method based on the calculated porosity rather than the measured porosity also greatly saves manpower and material resources, especially for tight rocks.
13
Devi, M. Shyamala, A. N. Sruthi, and P. Balamurugan. "Artificial neural network classification-based skin cancer detection." International Journal of Engineering & Technology 7, no. 1.1 (December 21, 2017): 591. http://dx.doi.org/10.14419/ijet.v7i1.1.10364.
Повний текст джерелаАнотація:
At present, skin cancers are extremely the most severe and life-threatening kind of cancer. The majority of the pores and skin cancers are completely remediable at premature periods. Therefore, a premature recognition of pores and skin cancer can effectively protect the patients. Due to the progress of modern technology, premature recognition is very easy to identify. It is not extremely complicated to discover the affected pores and skin cancers with the exploitation of Artificial Neural Network (ANN). The treatment procedure exploits image processing strategies and Artificial Intelligence. It must be noted that, the dermoscopy photograph of pores and skin cancer is effectively determined and it is processed to several pre-processing for the purpose of noise eradication and enrichment in image quality. Subsequently, the photograph is distributed through image segmentation by means of thresholding. Few components distinctive for skin most cancers regions. These features are mined the practice of function extraction scheme - 2D Wavelet Transform scheme. These outcomes are provides to the Back-Propagation Neural (BPN) Network for effective classification. This completely categorizes the data set into either cancerous or non-cancerous.
14
Van Eyndhoven, G., M. Kurttepeli, C. J. Van Oers, P. Cool, S. Bals, K. J. Batenburg, and J. Sijbers. "Pore REconstruction and Segmentation (PORES) method for improved porosity quantification of nanoporous materials." Ultramicroscopy 148 (January 2015): 10–19. http://dx.doi.org/10.1016/j.ultramic.2014.08.008.
Повний текст джерела
15
Braakman, Sietse T., A. Thomas Read, Darren W. H. Chan, C. Ross Ethier, and Darryl R. Overby. "Colocalization of outflow segmentation and pores along the inner wall of Schlemm's canal." Experimental Eye Research 130 (January 2015): 87–96. http://dx.doi.org/10.1016/j.exer.2014.11.008.
Повний текст джерела
16
Tang, Xin, Ruiyu He, Biao Wang, Yuerong Zhou та Hong Yin. "Intelligent Identification and Quantitative Characterization of Pores in Shale SEM Images Based on Pore-Net Deep-Learning Network Model". Petrophysics – The SPWLA Journal of Formation Evaluation and Reservoir Description 65, № 2 (1 квітня 2024): 233–45. http://dx.doi.org/10.30632/pjv65n2-2024a6.
Повний текст джерелаАнотація:
Among the various shale reservoir evaluation methods, the scanning electron microscope (SEM) image method is widely used. Its image can intuitively reflect the development stage of a shale reservoir and is often used for the qualitative characterization of shale pores. However, manual image processing is inefficient and cannot quantitatively characterize pores. The semantic segmentation method of deep learning greatly improves the efficiency of image analysis and can calculate the face rate of shale SEM images to achieve quantitative characterization. In this paper, the high-maturity shale of the Longmaxi Formation in the Changning area of Yibin City, Sichuan Province, and the low-maturity shale of Beibu Gulf Basin in China are studied. Based on the Pore-net network model, the intelligent identification and quantitative characterization of pores in shale SEM images are realized. The pore-net model is improved from the U-net deep-learning network model, which improves the ability of the network model to identify pores. The results show that the pore-net model performs better than the U-net model, FCN model, DeepLab V3 + model, and traditional binarization method. The problem of low accuracy of the traditional pore identification method is solved. The porosity of SEM images of high-maturity shale calculated by the pore-net network model is between 12 and 19% deviation from the experimental data. The calculated porosity of the SEM image of the low-maturity shale has a large deviation from the experimental data, which is between 14 and 47%. Compared with the porosity results calculated by other methods, the results calculated by pore-net are closer to the true value, which proves that the porosity calculated by the pore-net network model is reliable. The deep-learning semantic image segmentation method is suitable for pore recognition of shale SEM images. The fully convolutional neural network model is used to train the manually labeled shale SEM images, which can realize the intelligent recognition and quantitative characterization of the pores in the shale SEM images. It provides a certain reference value for the evaluation of shale oil and gas reservoirs and the study of other porous materials.
17
Báez, Francisco, Álvaro A. Camargo, and Gustavo D. A. Gastal. "Ultrastructural Imaging Analysis of the Zona Pellucida Surface in Bovine Oocytes." Microscopy and Microanalysis 25, no. 4 (May 28, 2019): 1032–36. http://dx.doi.org/10.1017/s1431927619000692.
Повний текст джерелаАнотація:
AbstractThe aims of the present study were to: (i) evaluate the ultrastructural differences in the zona pellucida (ZP) surface between immature and mature bovine oocytes, and (ii) describe a new objective technique to measure the pores in the outer ZP. Intact cumulus–oocyte complexes (COCs) obtained from a local abattoir were immediately fixed (immature group) or submitted to in vitro maturation (IVM) at 38.5 °C for 24 h in a humidified atmosphere of 5% CO2 in air (mature group). Oocytes from both groups were morphologically evaluated via Scanning Electron Microscopy (SEM) and the images were processed in the Fiji/ImageJ software using a new objective methodology through the Trainable Weka Segmentation plugin. The average number of pores in ZP was greater (p < 0.05) in the mature group than the immature group. However, the size and circularity of pores in ZP did not differ (p > 0.05) between groups. In conclusion, it has been shown that the number of pores highlighted the main ultrastructural change in the morphology of the ZP surface of bovine oocytes during the IVM process. We have described an objective method that can be used to evaluate ultrastructural modifications of the ZP surface during oocyte maturation and early embryo development.
18
Bondarev, A. V., E. T. Zhilyakova, N. B. Demina, and V. Y. Novikov. "Study of Morphology of Sorption Substances." Drug development & registration 8, no. 2 (May 30, 2019): 33–37. http://dx.doi.org/10.33380/2305-2066-2019-8-2-33-37.
Повний текст джерелаАнотація:
Introduction. Substances with sorption properties can be used to create transport drug systems, in which the main mechanism of binding, transport and release of the drug molecule is sorption. The sorbent in this case acts as a carrier of the drug molecule, followed by its delivery to the destination by desorption. One of the ways to study the processes of sorption-desorption in transport drug systems is the study of the morphology of the sorption substance. Therefore, the morphological analysis of sorption substances is important, including the size, shape, and spatial organization of their structural elements.Aim. The study of the morphology of sorption substances.Materials and methods. The materials of the study are active coal, silicon dioxide, povidone, dioctahedral smectite, kaolin and montmorillonite clay. The methods is scanning electron microscopy.Results and discussion. The scanning electron microscopy of objects was carried out using segmentation of elements as subsystems, inside of which the morphological description does not penetrate. It was established that for coal of active and silicon dioxide, the segmentation of elements is represented by three levels of organization; for povidone, smectite, kaolin and montmorillonite clay, the segmentation of elements is represented by two levels of organization. The morphology of the objects was investigated. It is established that the studied substances are microstructural objects. Porosity in samples of active coal, smectite dioctahedral, kaolin, montmorillonite clay was determined. In samples of silicon dioxide and povidone porosity is absent.Conclusion. Morphological analysis of sorption substances allowed us to develop classification of the possible interaction of the carrier substance with the drug molecule in the transport drug system. The materials under study are divided into two groups according to porous characteristics: group 1 – porous substances – sorption interaction in pores (active coal), sorption interaction in pores and by ion exchange (smectite, montmorillonite clay), sorption in secondary pores and through oxygen and hydroxyl centers (kaolin); group 2 – non-porous substances – sorption on oxygen centers (silicon dioxide), sorption by means of complex formation (povidone). The prospect of further research is the modeling of porosity and sorption interaction of the carrier substance with the drug molecule in the drug transport system.
19
Heylen, Rob, Aditi Thanki, Dries Verhees, Domenico Iuso, Jan De Beenhouwer, Jan Sijbers, Ann Witvrouw, Han Haitjema, and Abdellatif Bey-Temsamani. "3D total variation denoising in X-CT imaging applied to pore extraction in additively manufactured parts." Measurement Science and Technology 33, no. 4 (January 7, 2022): 045602. http://dx.doi.org/10.1088/1361-6501/ac459a.
Повний текст джерелаАнотація:
Abstract X-ray computed tomography (X-CT) plays an important role in non-destructive quality inspection and process evaluation in metal additive manufacturing, as several types of defects such as keyhole and lack of fusion pores can be observed in these 3D images as local changes in material density. Segmentation of these defects often relies on threshold methods applied to the reconstructed attenuation values of the 3D image voxels. However, the segmentation accuracy is affected by unavoidable X-CT reconstruction features such as partial volume effects, voxel noise and imaging artefacts. These effects create false positives, difficulties in threshold value selection and unclear or jagged defect edges. In this paper, we present a new X-CT defect segmentation method based on preprocessing the X-CT image with a 3D total variation denoising method. By comparing the changes in the histogram, threshold selection can be significantly better, and the resulting segmentation is of much higher quality. We derive the optimal algorithm parameter settings and demonstrate robustness for deviating settings. The technique is presented on simulated data sets, compared between low- and high-quality X-CT scans, and evaluated with optical microscopy after destructive tests.
20
ZHU, QINGYONG, WEIBIN YANG, and HUAIZHONG YU. "STUDY ON THE PERMEABILITY OF RED SANDSTONE VIA IMAGE ENHANCEMENT." Fractals 25, no. 06 (November 21, 2017): 1750055. http://dx.doi.org/10.1142/s0218348x17500554.
Повний текст джерелаАнотація:
Scanning electron microscopy (SEM) is of great importance for studying fractal permeability. In this work, we presented a new technique, by applying the high-order upwind compact difference schemes to solve the hyperbolic conservation laws, to enhance textural differences for accurate segmentation of the SEM images. From the enhanced SEM images, the channels and pores can be obtained by using the two-stage image segmentation. Combining with the box counting method, the key parameters for evaluation of the fractal permeability such as the tortuosity fractal dimension, the pore area fractal dimension and the maximum pore area can be derived from the segmented images. Application of the technique to the SEM images of a red sandstone from south China shows remarkable enhancement of edge details, allowing the more accurate segmentation of the SEM images. Rather than the original image algorithm, the fractal permeability derived from this new approach is closer to the experimental value, especially when the magnification falls in the range of 500–600. The results evidence that our enhanced images approach may provide stronger constraints on evaluations of permeability of sandstones.
21
Hwang, Heesu, Dohyoung Kim, Yoonmi Nam, Jong-Ho Lee, and Jin-Ha Hwang. "Synergistic Application of Machine Learning to Microstructural Characterization on Electrode Composites of Solid Oxide Fuel Cells." ECS Transactions 111, no. 6 (May 19, 2023): 445–51. http://dx.doi.org/10.1149/11106.0445ecst.
Повний текст джерелаАнотація:
Solid oxide fuel cells (SOFCs) have been recognized as one of the powerful next-generation energy conversion systems in association of the demanding green carbon technology. The electrochemical performance is crucially dependent on the intricate microstructures of porous electrodes, either cathodes or anodes. The composite electrodes should be analyzed in the sophisticated manner by characterizing the microstructural parameters. The current work combines electron microscopy with machine learning, more specifically semantic segmentation. The semantic segmentation was synergistically combined with high volume of electron micrographs enabled by FIB-SEM which has been used for microstructural analyses in SOFCs. The Ni/YSZ anode composites were selected as a model system, by incorporating the third components, i.e., pores featured by porous electrodes. The semantic segmentation-predicted image separation was connected with the conventional linear intercept approach, leading to the automated extraction of microstructural parameters. The work reports an exemplary analysis results based on the machine learning-assisted microstructure characterization in SOFC composite materials, implying that the machine learning-assisted approach becomes an essential tool in coping with high volume of electron microscopy-generated image data.
22
Fu, Yinkai, Yue Zhao, Yandong Zhao, and Qiaoling Han. "Semi-supervised segmentation of multi-scale soil pores based on a novel receptive field structure." Computers and Electronics in Agriculture 212 (September 2023): 108071. http://dx.doi.org/10.1016/j.compag.2023.108071.
Повний текст джерела
23
Suo, Limin, Zhaowei Wang, Hailong Liu, Likai Cui, Xianda Sun, and Xudong Qin. "Innovative Deep Learning Approaches for High-Precision Segmentation and Characterization of Sandstone Pore Structures in Reservoirs." Applied Sciences 14, no. 16 (August 15, 2024): 7178. http://dx.doi.org/10.3390/app14167178.
Повний текст джерелаАнотація:
The detailed characterization of the pore structure in sandstone is pivotal for the assessment of reservoir properties and the efficiency of oil and gas exploration. Traditional fully supervised learning algorithms are limited in performance enhancement and require a substantial amount of accurately annotated data, which can be challenging to obtain. To address this, we introduce a semi-supervised framework with a U-Net backbone network. Our dataset was curated from 295 two-dimensional CT grayscale images, selected at intervals from nine 4 mm sandstone core samples. To augment the dataset, we employed StyleGAN2-ADA to generate a large number of images with a style akin to real sandstone images. This approach allowed us to generate pseudo-labels through semi-supervised learning, with only a small subset of the data being annotated. The accuracy of these pseudo-labels was validated using ensemble learning methods. The experimental results demonstrated a pixel accuracy of 0.9993, with a pore volume discrepancy of just 0.0035 compared to the actual annotated data. Furthermore, by reconstructing the three-dimensional pore structure of the sandstone, we have shown that the synthetic three-dimensional pores can effectively approximate the throat length distribution of the real sandstone pores and exhibit high precision in simulating throat shapes.
24
Zhao, Xinli, Zhengming Yang, Xuewei Liu, Zhiyuan Wang, and Yutian Luo. "Analysis of pore throat characteristics of tight sandstone reservoirs." Open Geosciences 12, no. 1 (October 12, 2020): 977–89. http://dx.doi.org/10.1515/geo-2020-0121.
Повний текст джерелаАнотація:
AbstractThe characterization of pore throat structure in tight reservoirs is the basis for the effective development of tight oil. In order to effectively characterize the pore -throat structure of tight sandstone in E Basin, China, this study used high-pressure mercury intrusion (HPMI) testing technology and thin section (TS) technology to jointly explore the characteristics of tight oil pore throat structure. The results of the TS test show that there are many types of pores in the tight sandstone, mainly the primary intergranular pores, dissolved pores, and microfractures. Based on the pore throat parameters obtained by HPMI experiments, the pore throat radius of tight sandstone is between 0.0035 and 2.6158 µm. There are two peaks in the pore throat distribution curve, indicating that the tight sandstone contains at least two types of pores. This is consistent with the results of the TS experiments. In addition, based on the fractal theory and obtained capillary pressure curve by HPMI experiments, the fractal characteristics of tight sandstone pore throat are quantitatively characterized. The results show that the tight sandstones in E Basin have piecewise fractal (multifractal) features. The segmentation fractal feature occurs at a pore throat radius of approximately 0.06 µm. Therefore, according to the fractal characteristics, the tight sandstone pore throat of the study block is divided into macropores (pore throat radius > 0.06 µm) and micropores (pore throat radius < 0.06 µm). The fractal dimension DL of the macropores is larger than the fractal dimension DS of the micropores, indicating that the surface of the macropores is rough and the pores are irregular. This study cannot only provide certain support for characterizing the size of tight oil pore throat, but also plays an inspiring role in understanding the tight pore structure of tight sandstone.
25
Zhao, Jiang Kun, Yu Zhu, and Jian Feng Yu. "Segmentation by Local Binary Fitting Active Contour Model for Activated Carbon Fibers Material Microscopic Images." Advanced Materials Research 811 (September 2013): 370–74. http://dx.doi.org/10.4028/www.scientific.net/amr.811.370.
Повний текст джерелаАнотація:
Many bubbles and pores are appeared on Activated Carbon Fibers (ACFs) material microscopic images. The morphology of ACFs surface image is complicated. Some widely used traditional methods are difficult to segment the object correctly. In this paper, an implicit active contour driven by local binary fitting energy is used to segment the objects for ACFs micro-images. This method is based on local image edge information to obtain optimal level set active contour model. Experimental results show that this active contour model is flexible for analyzing images with complex porous structure.
26
Pan, Shen, and Mineichi Kudo. "Segmentation of pores in wood microscopic images based on mathematical morphology with a variable structuring element." Computers and Electronics in Agriculture 75, no. 2 (February 2011): 250–60. http://dx.doi.org/10.1016/j.compag.2010.11.010.
Повний текст джерела
27
Żak, Andrzej M., Anna Wieczorek, Agnieszka Chowaniec, and Łukasz Sadowski. "Segmentation of pores within concrete-epoxy interface using synchronous chemical composition mapping and backscattered electron imaging." Measurement 206 (January 2023): 112334. http://dx.doi.org/10.1016/j.measurement.2022.112334.
Повний текст джерела
28
Lu, Yangchun, Ting Lu, Yudong Lu, Bo Wang, Guanghao Zeng, and Xu Zhang. "The Study on Solving Large Pore Heat Transfer Simulation in Malan Loess Based on Volume Averaging Method Combined with CT Scan Images." Sustainability 15, no. 16 (August 15, 2023): 12389. http://dx.doi.org/10.3390/su151612389.
Повний текст джерелаАнотація:
Malan loess is a wind-formed sediment in arid and semi-arid regions and is an important constituent of the Earth’s critical zone. Therefore, the study of the relationship between microstructure and heat transfer in Malan loess is of great significance for the in-depth understanding of the heat transfer mechanism and the accurate prediction of the heat transfer properties of intact loess. In order to quantitatively characterize the heat transfer processes in the two-phase medium of solid particles and gas pores in the intact loess, this study used modern computed tomography to CT scan the Malan loess in Huan County, Gansu Province, the western part of the Loess Plateau, China and used the specific yield of the intact Malan loess as the parameter basis for extracting the threshold segmentation of the large pores in the scanned images for the three-dimensional reconstruction of the connected large pores. An experimental space for heat conduction of intact Malan loess was constructed, and the surface temperature of Malan loess was measured on the surface of the space with a thermal imager. The simulation of the heat conduction process was carried out using the solution program in AVIZO (2019) software using the volume averaging method combined with CT scanning to reconstruct the 3D pores. The experiments of heat conduction in the intact Malan loess showed that for a given external temperature pressure, the temperature decreases along the heat flow direction as a whole. The temperature of the pores in the normal plane along the heat flow direction is higher than the temperature of the solid skeleton. Abnormal temperature points were formed at the junction of the surface and internal pores of Maran loess, and the temperature of the jointed macropores was about 1 °C higher at the surface of the sample than that of the surrounding solid skeleton. Simulation of heat conduction in Malan loess showed that the heat transfer process in Malan loess was preferentially conducted along the large pores and then the heat was transferred to the surrounding Malan loess particle skeleton. The simulation results of heat conduction in Malan loess were in high agreement with the experimental results of heat conduction in Malan loess, which verifies the reliability of the calculated model.
29
Tkachev, Sergey, Natalia Chepelova, Gevorg Galechyan, Boris Ershov, Danila Golub, Elena Popova, Artem Antoshin, et al. "Three-Dimensional Cell Culture Micro-CT Visualization within Collagen Scaffolds in an Aqueous Environment." Cells 13, no. 15 (July 23, 2024): 1234. http://dx.doi.org/10.3390/cells13151234.
Повний текст джерелаАнотація:
Among all of the materials used in tissue engineering in order to develop bioequivalents, collagen shows to be the most promising due to its superb biocompatibility and biodegradability, thus becoming one of the most widely used materials for scaffold production. However, current imaging techniques of the cells within collagen scaffolds have several limitations, which lead to an urgent need for novel methods of visualization. In this work, we have obtained groups of collagen scaffolds and selected the contrasting agents in order to study pores and patterns of cell growth in a non-disruptive manner via X-ray computed microtomography (micro-CT). After the comparison of multiple contrast agents, a 3% aqueous phosphotungstic acid solution in distilled water was identified as the most effective amongst the media, requiring 24 h of incubation. The differences in intensity values between collagen fibers, pores, and masses of cells allow for the accurate segmentation needed for further analysis. Moreover, the presented protocol allows visualization of porous collagen scaffolds under aqueous conditions, which is crucial for the multimodal study of the native structure of samples.
30
Fager, Andrew, Hiroshi Otomo, Rafael Salazar-Tio, Ganapathi Balasubramanian, Bernd Crouse, Raoyang Zhang, Hudong Chen, and Josephina Schembre-McCabe. "Multi-scale Digital Rock: Application of a multi-scale multi-phase workflow to a Carbonate reservoir rock." E3S Web of Conferences 366 (2023): 01001. http://dx.doi.org/10.1051/e3sconf/202336601001.
Повний текст джерелаАнотація:
In some of the challenging digital rock applications the trade-off between model resolution and representative elemental volume is not captured in a single resolution model satisfying the minimum requirements for both aspects. In the wide range of lithofacies found in carbonate reservoir rocks, some facies fall in this category, where large pores, ooids or vugs, are connected by small scale porous structures that could have orders of magnitude smaller pores. In these cases a multi-scale digital rock approach is needed. We recently developed an extension to a digital rock workflow that includes a way to handle sub-resolution pore structures in single phase and multi-phase flow scenarios in addition to regular resolvable pore structures. Here we present an application of this methodology to a multi-scale limestone carbonate rock. A microCT image captures the large pores for this sample, but does not resolve all the pores smaller than the pixel size. A three phase image segmentation that considers pore, solid and under-resolved pores or porous media (PM) is generated. A high resolution confocal image model is obtained for a representative region of the smaller pores or PM region. A set of constitutive relationships (namely permeability vs. porosity, capillary pressure vs saturation and relative permeability vs saturation) are obtained by simulation from the high resolution confocal model. The low resolution segmented image, a porosity distribution image, and the constitutive relationships for the PM are input in an extended LBM multi-scale multi-phase solver. First we present results for absolute permeability and show a parametric study on PM permeability. The model recovers the expected behaviour when the PM regions are considered pore or solid. A consistent value of permeability with experiments is obtained when we use the PM permeability from the high resolution model. To demonstrate the multi-phase behaviour, we present results for capillary pressure imbibition multi-scale simulations. Here a small model for a dual porosity system is created in order to compare single scale results with the multi-scale solver. Finally, capillary imbibition results for the whole domain are shown and different wettability scenario results are discussed. This application illustrates a novel multi-scale simulation approach that can address a long standing problem in digital rock.
31
Pramana, A. A., G. Riantomo, A. P. Oktaviani, I. Setiabudi, F. D. E. Latief, and M. A. Gibrata. "Digital Rock Physics Application in Determining The Porosity of Shale Rock." Journal of Physics: Conference Series 2243, no. 1 (June 1, 2022): 012021. http://dx.doi.org/10.1088/1742-6596/2243/1/012021.
Повний текст джерелаАнотація:
Abstract This research is focusing on determining the porosity of shale rock using the Digital Rock Physics (DRP) method. The DRP method uses fiji software to process μCT-scan data of shale coreplug through segmentation and thresholding processes to determine the pores of the rock and then to determine the value of rock porosity. The purpose of this research is to be able to determine the value of rock porosity more quickly and to verify the DRP porosity result to that of laboratory test. The result shows that the porosity value obtained by the DRP method and laboratory test has a small difference so that the DRP method is quite reliable.
32
Zhang, Hao, Hewen Liu, and Jinyong Bai. "Research on image recognition method of rock and soil porous media based on dithering algorithm." E3S Web of Conferences 283 (2021): 01025. http://dx.doi.org/10.1051/e3sconf/202128301025.
Повний текст джерелаАнотація:
Rock-soil mass is a kind of material with complex internal structure, and its macro-mechanical response and failure process are influenced by internal microscopic composition and structure. Based on the research results of digital image technology in quantitative aspects of internal structure of rock and soil, a method for segmentation of rock and soil pore images based on dithering algorithm and statistical method for multiple parameters of pores is proposed in this paper. The result of verification shows that the pore recognition method proposed in this paper is reliable, can obtain the pore distribution and related parameters quickly and effectively, which has certain academic value and research significance.
33
Hu, Zhazha, Rui Zhang, Kai Zhu, Dongyin Li, Yi Jin, Wenbing Guo, Xiao Liu, Xiaodong Zhang, and Qian Zhang. "Probing the Pore Structure of the Berea Sandstone by Using X-ray Micro-CT in Combination with ImageJ Software." Minerals 13, no. 3 (March 4, 2023): 360. http://dx.doi.org/10.3390/min13030360.
Повний текст джерелаАнотація:
During diagenesis, the transformation of unconsolidated sediments into a sandstone is usually accompanied by compaction, water expulsion, cementation and dissolution, which fundamentally control the extent, connectivity and complexity of the pore structure in sandstone. As the pore structure is intimately related to fluid flow in porous media, it is of great importance to characterize the pore structure of a hydrocarbon-bearing sandstone in a comprehensive way. Although conventional petrophysical methods such as mercury injection porosimetry, low-pressure nitrogen or carbon dioxide adsorption are widely used to characterize the pore structure of rocks, these evaluations are based on idealized pore geometry assumptions, and the results lack direct information on the pore geometry, connectivity and tortuosity of pore channels. In view of the problems, X-ray micro-CT was combined with ImageJ software (version 1.8.0) to quantitatively characterize the pore structure of Berea Sandstone. Based on its powerful image processing function, a series of treatments such as contrast enhancement, noise reduction and threshold segmentation, were first carried out on the micro-CT images of the sandstone via ImageJ. Pores with sizes down to 2.25 μm were accurately identified. Geometric parameters such as pore area, perimeter and circularity could thus be extracted from the segmented pores. According to our evaluations, pores identified in this study are mostly in the range of 30–180 μm and can be classified into irregular, high-circularity and slit-shaped pores. An irregular pore is the most abundant type, with an area fraction of 72.74%. The average porosity obtained in the image analysis was 19.10%, which is fairly close to the experimental result determined by a helium pycnometer on the same sample. According to the functional relationship between tortuosity and permeability, the tortuosity values of the pore network were estimated to be in the range of 4–6 to match the laboratory permeability data.
34
Scott, Sarah, Wei-Ying Chen, and Alexander Heifetz. "Multi-Task Learning of Scanning Electron Microscopy and Synthetic Thermal Tomography Images for Detection of Defects in Additively Manufactured Metals." Sensors 23, no. 20 (October 14, 2023): 8462. http://dx.doi.org/10.3390/s23208462.
Повний текст джерелаАнотація:
One of the key challenges in laser powder bed fusion (LPBF) additive manufacturing of metals is the appearance of microscopic pores in 3D-printed metallic structures. Quality control in LPBF can be accomplished with non-destructive imaging of the actual 3D-printed structures. Thermal tomography (TT) is a promising non-contact, non-destructive imaging method, which allows for the visualization of subsurface defects in arbitrary-sized metallic structures. However, because imaging is based on heat diffusion, TT images suffer from blurring, which increases with depth. We have been investigating the enhancement of TT imaging capability using machine learning. In this work, we introduce a novel multi-task learning (MTL) approach, which simultaneously performs the classification of synthetic TT images, and segmentation of experimental scanning electron microscopy (SEM) images. Synthetic TT images are obtained from computer simulations of metallic structures with subsurface elliptical-shaped defects, while experimental SEM images are obtained from imaging of LPBF-printed stainless-steel coupons. MTL network is implemented as a shared U-net encoder between the classification and the segmentation tasks. Results of this study show that the MTL network performs better in both the classification of synthetic TT images and the segmentation of SEM images tasks, as compared to the conventional approach when the individual tasks are performed independently of each other.
35
Han, Yubo, and Ye Liu. "Intelligent Classification and Segmentation of Sandstone Thin Section Image Using a Semi-Supervised Framework and GL-SLIC." Minerals 14, no. 8 (August 5, 2024): 799. http://dx.doi.org/10.3390/min14080799.
Повний текст джерелаАнотація:
This study presents the development and validation of a robust semi-supervised learning framework specifically designed for the automated segmentation and classification of sandstone thin section images from the Yanchang Formation in the Ordos Basin. Traditional geological image analysis methods encounter significant challenges due to the labor-intensive and error-prone nature of manual labeling, compounded by the diversity and complexity of rock thin sections. Our approach addresses these challenges by integrating the GL-SLIC algorithm, which combines Gabor filters and Local Binary Patterns for effective superpixel segmentation, laying the groundwork for advanced component identification. The primary innovation of this research is the semi-supervised learning model that utilizes a limited set of manually labeled samples to generate high-confidence pseudo labels, thereby significantly expanding the training dataset. This methodology effectively tackles the critical challenge of insufficient labeled data in geological image analysis, enhancing the model’s generalization capability from minimal initial input. Our framework improves segmentation accuracy by closely aligning superpixels with the intricate boundaries of mineral grains and pores. Additionally, it achieves substantial improvements in classification accuracy across various rock types, reaching up to 96.3% in testing scenarios. This semi-supervised approach represents a significant advancement in computational geology, providing a scalable and efficient solution for detailed petrographic analysis. It not only enhances the accuracy and efficiency of geological interpretations but also supports broader hydrocarbon exploration efforts.
36
Bondarev, Alexander, Elena Zhilyakova, Anastasia Malyutina, Larissa Kozubova, Natalia Avtina, Elena Timoshenko, and Georgy Vasiliev. "Structural features of mineral carriers of medicinal substances." BIO Web of Conferences 40 (2021): 03007. http://dx.doi.org/10.1051/bioconf/20214003007.
Повний текст джерелаАнотація:
The aim of the work is to investigation of the structural features of mineral carriers of medicinal substances. Tasks: conduct electron microscopy and study the structural features of mineral sorbents; develop a classification of sorption interaction. The materials are Smectite Dioctahedral (registration certificate N 015155/01, France), Kaolin (state standard 19608-84, Russia), Montmorillonite Clay (technical specifications 9296-001-62646221-2012, Russia). The methods are scanning electron microscopy on a FEI Quanta 600 microscope with a low vacuum mode and an LFD detector. Results. Electron microscopy of objects was performed using segmentation of elements as subsystems, inside which the morphological description does not penetrate. The morphology of objects is studied. It is established that the studied substances are microstructural objects. Porosity was determined in samples of Smectite, Kaolin and Montmorillonite Clay. The classification of sorption interaction is developed. According to the presented classification, the materials under study are divided into two groups according to their porous characteristics: Group 1-sorption interaction in pores and by ion exchange (Smectite, Montmorillonite Clay); Group 2-sorption in secondary pores and by means of Oxygen and Hydroxyl centers (Kaolin).
37
Xavier, Matheus S., Sam Yang, Christophe Comte, Alireza Bab-Hadiashar, Neil Wilson, and Ivan Cole. "Nondestructive quantitative characterisation of material phases in metal additive manufacturing using multi-energy synchrotron X-rays microtomography." International Journal of Advanced Manufacturing Technology 106, no. 5-6 (December 10, 2019): 1601–15. http://dx.doi.org/10.1007/s00170-019-04597-y.
Повний текст джерелаАнотація:
AbstractMetal additive manufacturing (MAM) has found emerging application in the aerospace, biomedical and defence industries. However, the lack of reproducibility and quality issues are regarded as the two main drawbacks to AM. Both of these aspects are affected by the distribution of defects (e.g. pores) in the AM part. Computed tomography (CT) allows the determination of defect sizes, shapes and locations, which are all important aspects for the mechanical properties of the final part. In this paper, data-constrained modelling (DCM) with multi-energy synchrotron X-rays is employed to characterise the distribution of defects in 316L stainless steel specimens manufactured with laser metal deposition (LMD). It is shown that DCM offers a more reliable method to the determination of defect levels when compared to traditional segmentation techniques through the calculation of multiple volume fractions inside a voxel, i.e. by providing sub-voxel information. The results indicate that the samples are dominated by a high number of small light constituents (including pores) that would not be detected under the voxel size in the majority of studies reported in the literature using conventional thresholding methods.
38
Xiao, Xiaoling, Jiarui Zhang, Xinyu Li, Jing Zhang, and Xiang Zhang. "Study on Extraction Methods for Different Components in a Carbonate Digital Core." Mathematical Problems in Engineering 2020 (September 7, 2020): 1–6. http://dx.doi.org/10.1155/2020/8972494.
Повний текст джерелаАнотація:
It is difficult to carry out petrophysical experiments because of the serious damage caused to cores in the development of fractures and pores in carbonate reservoirs. The development of a three-dimensional digital core in carbonate reservoirs has become a hot topic in rock physics research. Compared with the three-dimensional digital core, including basic rock skeletons and pores in sandstone reservoirs, carbonate reservoirs also include secondary structures such as microfractures. The carbonate contains different components, and extracting these components is a very difficult problem. The resolution on the electrical image log image is high, which can clearly reflect the macrocomponents in various reservoirs. There are some blank areas between electrodes on the electrical image log, which affects the extraction of components in a three-dimensional digital core. Aiming at the serious heterogeneities in the carbonate reservoirs and affecting image inpainting on the electrical image log image, a new method of image inpainting based on a combination of multipoint geostatistics and an interpolation method is put forward. The experimental results show that this method generates faster and better full-bore images than other methods. Due to the multipeak histogram, the maximum interclass variance in the two times method is proposed to extract macrocomponents such as basic rock skeletons, pores, and connected parts. The microfractures can be extracted from the CT scanned images by using image segmentation from the combination of the watershed and OTSU methods. The experimental results prove that using extraction methods for different components enables better results to be obtained.
39
Song, Meihui, Yue Zhao, Yandong Zhao, and Qiaoling Han. "ACFTransUNet: A new multi-category soil pores 3D segmentation model combining Transformer and CNN with concentrated-fusion attention." Computers and Electronics in Agriculture 225 (October 2024): 109312. http://dx.doi.org/10.1016/j.compag.2024.109312.
Повний текст джерела
40
Idowu, N. A. A., C. Nardi, H. Long, T. Varslot, and P. E. E. Øren. "Effects of Segmentation and Skeletonization Algorithms on Pore Networks and Predicted Multiphase-Transport Properties of Reservoir-Rock Samples." SPE Reservoir Evaluation & Engineering 17, no. 04 (August 13, 2014): 473–83. http://dx.doi.org/10.2118/166030-pa.
Повний текст джерелаАнотація:
Summary Networks of large pores connected by narrower throats (pore networks) are essential inputs into network models that are routinely used to predict transport properties from digital rock images. Extracting pore networks from microcomputed-tomography (micro-CT) images of rocks involves a number of steps: filtering, segmentation, skeletonization, and others. Because of the amount of clay and its distribution, the segmentation of micro-CT images is not trivial, and different algorithms exist for achieving this. Similarly, several methods are available for skeletonizing the segmented images and for extracting the pore networks. The nonuniqueness of these processes raises questions about the predictive power of network models. In the present work, we evaluate the effects of these processes on the computed petrophysical and multiphase-flow properties of reservoir-rock samples. By use of micro-CT images of reservoir sandstones, we first apply three different segmentation algorithms and assess the effects of the different algorithms on estimated porosity, amount of clay, and clay distribution. Single-phase properties are computed directly on the segmented images and compared with experimental data. Next, we extract skeletons from the segmented images by use of three different algorithms. On the pore networks generated from the different skeletons, we simulate two-phase oil/ water and three-phase gas/oil/water displacements by use of a quasistatic pore-network model. Analysis of the segmentation results shows differences in the amount of clay, in the total porosity, and in the computed singlephase properties. Simulated results show that there are differences in the network-predicted single-phase properties as well. However, predicted multiphase-transport properties from the different networks are in good agreement. This indicates that the topology of the pore space is well preserved in the extracted skeleton. Comparison of the computed capillary pressure and relative permeability curves for all networks with available experimental data shows good agreements. By use of a segmentation that captures porosity and microporosity, we show that the extracted networks can be used to reliably predict multiphase-transport properties, irrespective of the algorithms used.
41
Nemati, Saber, Hamed Ghadimi, Xin Li, Leslie G. Butler, Hao Wen, and Shengmin Guo. "Automated Defect Analysis of Additively Fabricated Metallic Parts Using Deep Convolutional Neural Networks." Journal of Manufacturing and Materials Processing 6, no. 6 (November 13, 2022): 141. http://dx.doi.org/10.3390/jmmp6060141.
Повний текст джерелаАнотація:
Laser powder bed fusion (LPBF)-based additive manufacturing (AM) has the flexibility in fabricating parts with complex geometries. However, using non-optimized processing parameters or using certain feedstock powders, internal defects (pores, cracks, etc.) may occur inside the parts. Having a thorough and statistical understanding of these defects can help researchers find the correlations between processing parameters/feedstock materials and possible internal defects. To establish a tool that can automatically detect defects in AM parts, in this research, X-ray CT images of Inconel 939 samples fabricated by LPBF are analyzed using U-Net architecture with different sets of hyperparameters. The hyperparameters of the network are tuned in such a way that yields maximum segmentation accuracy with reasonable computational cost. The trained network is able to segment the unbalanced classes of pores and cracks with a mean intersection over union (mIoU) value of 82% on the test set, and has reduced the characterization time from a few weeks to less than a day compared to conventional manual methods. It is shown that the major bottleneck in improving the accuracy is uncertainty in labeled data and the necessity for adopting a semi-supervised approach, which needs to be addressed first in future research.
42
Aditya Putra Prananda, A. M. H. Pardede, and Rahmadani. "Segmentation Algorithm K – Means Based On The Maturity Level Of Blueberries." Journal of Artificial Intelligence and Engineering Applications (JAIEA) 3, no. 2 (February 15, 2024): 584–89. http://dx.doi.org/10.59934/jaiea.v3i2.433.
Повний текст джерелаАнотація:
Traditionally, farmers and consumers have determined the ripeness of blueberries by manual means, such as observing the color, pores, and skin of blueberry fruits. Such recognition takes a relatively long time and gives rise to different levels of maturity because people have visual limitations in recognition, fatigue levels and differences of opinion about good maturity. Consumers tend to pay attention to aspects such as the striking color and size of blueberries, but do not know how ripe and nutritious the fruit is for consumption. Several image processing techniques were used in this study, including image segmentation for segmentation based on color features, expansion and contraction operations to remove noise, and naming fruit objects using recursive component labeling methods. This is followed by separation and training of geometric features and colors. At the time of testing, a classification of the degree of maturity and type of fruit of the object is carried out. To more accurately identify the degree of ripeness of the fruit, check the geometric features and characteristic values of the color content. Range values are determined by statistical methods such as mean and standard deviation. Using the K-Means algorithm to segment blueberry imagery, the study aimed to develop an efficient method to distinguish blueberry ripeness levels automatically. It can help classify and group blueberries according to their degree of maturity. In addition, the results of this study can also be used for quality control of blueberries in the agricultural industry or for fruit marketing applications.
43
Ojeda-Magaña, B., J. Quintanilla-Domínguez, R. Ruelas, L. Gómez Barba, and D. Andina. "Improvement of the Image Sub-Segmentation for Identification and Differentiation of Atypical Regions." International Journal of Pattern Recognition and Artificial Intelligence 32, no. 01 (October 9, 2017): 1860011. http://dx.doi.org/10.1142/s021800141860011x.
Повний текст джерелаАнотація:
A new sub-segmentation method has been proposed in 2009 which, in digital images, help us to identify the typical pixels, as well as the less representative pixels or atypical of each segmented region. This method is based on the Possibilistic Fuzzy c-Means (PFCM) clustering algorithm, as it integrates absolute and relative memberships. Now, the segmentation problem is related to isolate each one of the objects present in an image. However, and considering only one segmented object or region represented by gray levels as its only feature, the totality of pixels is divided in two basic groups, the group of pixels representing the object, and the others that do not represent it. In the former group, there is a sub-group of pixels near the most representative element of the object, the prototype, and identified here as the typical pixels, and a sub-group corresponding to the less representative pixels of the object, which are the atypical pixels, and generally located at the borders of the pixels representing the object. Besides, the sub-group of atypical pixels presents greater tones (brighter or towards the white color) or smaller tones (darker or towards black color). So, the sub-segmentation method offers the capability to identify the sub-region of atypical pixels, although without performing a differentiation between the brighter and the darker ones. Hence, the proposal of this work contributes to the problem of image segmentation with the improvement on the detection of the atypical sub-regions, and clearly recognizing between both kind of atypical pixels, because in many cases only the brighter or the darker atypical pixels are the ones that represent the object of interest in an image, depending on the problem to be solved. In this study, two real cases are used to show the contribution of this proposal; the first case serves to demonstrate the pores detection in soil images represented by the darker atypical pixels, and the second one to demonstrate the detection of microcalcifications in mammograms, represented in this case by the brighter atypical pixels.
44
Zhang, Jingmin. "Reversible Data Hiding of Digital Image Based on Pixel Combination Algorithm." Advances in Multimedia 2022 (July 15, 2022): 1–11. http://dx.doi.org/10.1155/2022/8627056.
Повний текст джерелаАнотація:
In order to improve the security effect of image information, this paper studies the reversible information hiding of the digital images combined with the pixel combination algorithm and proposes an improved simulated annealing algorithm using the incremental calculation method of statistical functions. Moreover, according to the gray gradient information contained in the image, this paper proposes an automatic threshold determination algorithm suitable for the unimodal gray distribution images and uses this algorithm to complete the threshold determination and binary segmentation of all images. In addition, this paper optimizes the model by transforming the isolated pores inside the model and removing the isolated matrix area. Through comparative experiments, it can be seen that the reversible information hiding method for digital images based on the pixel combination algorithm proposed in this paper has a good image information confidentiality effect.
45
C Mohammed Gulzar, Et al. "Survey on Therapy Prediction using Deep Learning for Pores and Skin Diseases." International Journal on Recent and Innovation Trends in Computing and Communication 11, no. 10 (November 2, 2023): 1429–34. http://dx.doi.org/10.17762/ijritcc.v11i10.8687.
Повний текст джерелаАнотація:
Introduction: Prediction and detection of skin ailments have generally been a hard and important task for health care specialists. In the cutting-edge situation majority of the pores and skin care practitioners are the uses of traditional techniques to diagnose the ailment which may also take a large amount of time. Skin Diseases are excessive troubles in recent times as it is a consider form of environmental factors, socioeconomic elements, loss of entire weight loss program, and so on. Identifying the particular skin disease by computer vision is introduced as a novel task. Based on skin or pore disease, certain therapy can be suggested. In proposed study there are different applications based on deep learning are studied with computer vision task for better performance of proposed application. Famous deep learning algorithms may include CNN (convolutional neural network) , RNN (Recurrent Neural network), etc.
Objective: To diagnose skin disease with dermoscopic images automatically. Developing automated strategies to improve the accuracy of analysis for multiple psoriasis and skin diseases
Methods: In existing techniques many machine learning models are used which is having high complexity and require more time for analysis. So, in this study different deep learning models are studied for understanding performance difference between different models. This paper is a comparative check about skin illnesses related to ordinary skin issues in addition to cosmetology. Image selection, segmentation of skin disease detection and classification are the important steps can be used for oily, dry, and ordinary pores.
Result: The field of dermatology has seen promising results from studies on various Convolutional Neural Network (CNN) algorithms for classifying skin diseases based on clinical images. These studies have concentrated on utilizing the strength of deep learning and computer vision techniques to classify and diagnose different skin conditions using facial images precisely.
Conclusion: A survey of numerous papers is achieved on basis of technologies used, outcomes with accuracy, moral behavior, and number of illnesses diagnosed, datasets. Different existing research methodologies are compared with present deep learning architectures for understanding superior performance of deep learning models. Using deep learning, we can predict pore and skin diseases. In proposed study, introduction to different algorithms of deep learning which are combined with computer vision tasks to find the skin disease and pore disease are studied. Therapy can be predicted based on type of skin or pore disease.
46
Zhang, Feng, Ghislain Bournival, Hamed Lamei Ramandi, and Seher Ata. "Digital Cake Analysis: A Novel Coal Filter Cake Examination Technique Using Microcomputed Tomography." Minerals 13, no. 12 (November 30, 2023): 1509. http://dx.doi.org/10.3390/min13121509.
Повний текст джерелаАнотація:
Filtration is crucial for separating solids and liquids in various industries. Understanding slurry properties and filter cake structures is essential for optimising filtration performance. Conventional methods focus on interpreting filtration data to improve the understanding of filtration mechanisms. However, examining fragile filter cakes is challenging, and current techniques often alter their structure. Conventional methods only provide an average representation of cake porosity, neglecting variations in porosity and pore distribution across the cake thickness. This study introduces the Digital cake analysis, a non-destructive technique for evaluating filter cake structure. Filtration experiments using a custom-built unit were conducted on coal slurries to obtain filter cake samples. X-ray-microcomputed tomography (µCT) imaging was utilized for cake analysis. Image enhancement techniques were employed to improve the quality of the µCT images. The enhanced images were segmented into three phases (resolved pore, subresolution pore, and solid phases) for quantitative analysis. This segmentation technique allocated partial pore volume to voxels in the subresolution phase based on their intermediate grey-scale intensity, enabling more accurate porosity calculations. Unlike conventional methods, this approach computed porosity values for resolved (100% void) and subresolution (partially void) pores. This image segmentation technique facilitated accurate computations of porosity, pore size distribution, and pore properties, significantly advancing the understanding of cake structures. Digital cake analysis produced porosity measurements similar to the experimental results.
47
Silva, Miquéias A. S., Susana M. Iglesias, Paulo E. Ambrosio, Iram B. R. Ortiz, Dany S. Dominguez, and Diego Frias. "Application of Segmentation and Fuzzy Classification Techniques (TSK) in Analyzing the Composition of Lightweight Concretes Containing Ethylene Vinyl Acetate and Natural Fibers Using Micro-Computed Tomography Images." Applied Sciences 14, no. 1 (December 28, 2023): 296. http://dx.doi.org/10.3390/app14010296.
Повний текст джерелаАнотація:
The reuse of ethylene vinyl acetate (EVA) discarded from the sports and footwear industries as a partial substitute for gravel in concrete is a way of reducing anthropogenic environmental impacts by enabling the production of lighter structures with similar and superior resistance to those built with traditional concrete. Several studies have been published replacing gravel with EVA and natural fibers, resulting in lighter, more resistant, cheaper, and more ecological concrete. However, there is no methodology to characterize the composition and internal structure of these materials accurately and efficiently, which is vital for quality control in mass-produced pre-molded shapes. In this study, an automated system was developed to measure the percentage of each component in test cores using micro-computed tomography (Micro-CT). For this, (1) Micro-CT images were obtained for concrete test cores made with coarse aggregate consisting of gravel, EVA, and natural fibers in different proportions; (2) the images were segmented differentiating the gravel from the rest of the aggregate, while the remainder was further segmented with the cementitious matrix as background, and the pores, EVA fragments, and fibers as objects against this background; and (3) a Takagi–Sugeno–Kang-type fuzzy inference system was built to classify the objects in the foreground as pores, EVA, and fiber. The tool developed in this manner estimates the percentages of each concrete component and also provides an estimate of the porosity.
48
Peng, Jiayi, Zhenzhong Shen, and Jiafa Zhang. "Measuring the Effect of Pack Shape on Gravel’s Pore Characteristics and Permeability Using X-ray Diffraction Computed Tomography." Materials 15, no. 17 (September 5, 2022): 6173. http://dx.doi.org/10.3390/ma15176173.
Повний текст джерелаАнотація:
Particle shape is one of the critical parameter factors that affect gravel’s pore structure and permeability. However, few studies have considered its effects on engineering applications due to the difficulty of conducting laboratory tests. To overcome these difficulties, new methods of estimating the gravel pack shape that involve manual work and measuring the surface area of particles and pores based on support vector machine segmentation and the reconstruction of X-ray diffraction computed tomography (CT) images were proposed. Under the same conditions, CT tests were carried out on gravel packs and two other regular-shaped particle packs to investigate the influence of particle shape on the fractal dimension of gravel’s pore–particle interface and the specific surface area of the pore network. Additionally, permeability tests were performed to study the effect of particle shape on gravel’s hydraulic conductivity. The results showed that a gravel pack with a larger aspect ratio and a smaller roundness had a larger specific pore network surface area and a more complex pore structure, leading to lower permeability. This kind of gravel had a more significant length, quantity, and tortuosity of the seepage path when seepage occurred in a two-dimensional seepage field simulation. Therefore, we suggest that the filter materials of hydraulic projects should preferably use blasting gravel with a larger aspect ratio and smaller roundness to achieve better anti-seepage properties. In addition, projects can increase pores’ specific surface area using our method as a control factor in filter construction.
49
Ballóková, Beáta, Marián Lázár, Natália Jasminská, Zuzana Molčanová, Štefan Michalik, Tomáš Brestovič, Jozef Živčák, and Karol Saksl. "Development and Testing of Copper Filters for Efficient Application in Half-Face Masks." Applied Sciences 12, no. 13 (July 5, 2022): 6824. http://dx.doi.org/10.3390/app12136824.
Повний текст джерелаАнотація:
SARS-CoV-2 is the causative agent of severe acute respiratory diseases. Its main transmission pathway is through large and small respiratory droplets, as well as a direct and indirect contact. In this paper, we present the results of the development and research of copper filters produced by powder technology. Four types of copper powders were tested. Technological parameters, a microstructure, an energy dispersive X-ray (EDX) analysis, and fractography of copper (Cu) filters are reported. The pressure losses in the P-Cu-AW315 filter showed a very favorable value for using the filter in half-face masks that meet the requirements of European norms (EN). An X-ray tomography measurement was carried out at the I12-JEEP beamline. A relative volume of grains and pores was estimated (on the basis of the segmentation results) to be approximately 50% to 50% of the investigated filter volume.
50
Żak, Andrzej M., Anna Wieczorek, Agnieszka Chowaniec, and Łukasz Sadowski. "Segmentation of pores in cementitious materials based on backscattered electron measurements: A new proposal of regression-based approach for threshold estimation." Construction and Building Materials 368 (March 2023): 130419. http://dx.doi.org/10.1016/j.conbuildmat.2023.130419.
Повний текст джерела