A study of methods for texture classification of SEM images of micro-surfaces of objects and their segmentation

dc.citation.epage50
dc.citation.issue91
dc.citation.journalTitleГеодезія, картографія і аерофотознімання
dc.citation.spage41
dc.contributor.affiliationНаціональний університет “Львівська політехніка”
dc.contributor.affiliationLviv Polytechnic National University
dc.contributor.authorІванчук, О.
dc.contributor.authorТумська, О.
dc.contributor.authorIvanchuk, O.
dc.contributor.authorTumska, O.
dc.coverage.placenameЛьвів
dc.coverage.placenameLviv
dc.date.accessioned2023-03-02T08:01:39Z
dc.date.available2023-03-02T08:01:39Z
dc.date.created2020-03-12
dc.date.issued2020-03-12
dc.description.abstractМета. Мета роботи – розробити і дослідити методи класифікації текстур РЕМ-зображень мікроповерхонь об’єктів на основі статистичних та спектральних характеристик текстурних фрагментів, а також порівняльного аналізу методів сегментації РЕМ-зображень. Методи. Визначення характеристик текстури РEM-зображень ґрунтувалось на статистичних моментах, розрахованих за гістограмою яскравості. Спектральні міри текстури обчислювались за спектром Фур’є. Для визначення спектральних текстурних характеристик вибрано параметри амплітудної та осьової функцій. Сегментацію РEM-зображень мікроповерхонь об’єктів виконано чотирма способами, а саме: методом глобальної порогової сегментації, методом нарощування області, методом поділу та злиття і методом вододілу з використанням маркерів. Результати. Опрацювання серії РЕМ-зображень ґрунтів показало найкращий результат класифікації текстур за мірою однорідності, ніж за іншими статистичними характеристиками. Обчислення спектральних характеристик РЕМ-зображень металів виявило періодичність або майже періодичність і спрямованість присутніх у зображенні елементів текстур і разом із результатами класифікації за мірою однорідності дає змогу отримати узагальнену характеристику текстури зображення. Порівняльний аналіз чотирьох методів сегментації показав, що найкращий результат визначення меж об’єктів на РЕM-зображенні отримано методом вододілу з використанням маркерів. Програмну реалізацію методів класифікації текстур та їхню сегментацію виконували в системі MatLab. Наукова новизна. Запропоновано метод класифікації РЕМ-зображень на основі спектральних текстурних характеристик за параметрами амплітудної та осьової функцій. Показано, що сегментація РEM-зображень методом поділу і злиття дає змогу задати умови для виділення на зображенні областей із певними характеристиками текстури. Практичне значення. Узагальнена характеристика текстури РЕМ-зображення, що визначається за статистичними і спектральними мірами, корисна для автоматизованого розпізнавання текстур і аналізу РЕМ-зображень. Вибір ділянок із певними характеристиками текстури є важливим етапом попередньої обробки зображень під час знаходження точок інтересу, що придатні для зіставлення РЕМ-зображень і розпізнавання об’єктів.
dc.description.abstractPurpose. The goal of this work was to develop and study the methods of texture classification of SEM images of micro surfaces of objects based on the statistical and spectral characteristics of texture fragments, as well as a comparative analysis of segmentation methods of SEM images. Methods. The determination of the texture characteristics was based on statistical moments computed by the brightness histogram of a SEM-image or its region. The spectral measures of texture of SEM image were based on properties of the Fourier spectrum. To determine the spectral texture characteristics, the parameters of the amplitude and axial functions were chosen. SEM images were segmented using four methods, namely: the global thresholding; the region growing; the region splitting and merging; and the watershed using markers. Results. The experiments on texture classification of the SEM series of soils and metals images showed the best result of texture classification by the feature of homogeneity compared to other statistical characteristics. Calculation of the spectral characteristics was used to detect the directionality of periodic or almost periodic texture elements in the SEM images of metals. Classification results using spectral properties and homogeneity values made it possible to obtain generalized texture characteristics of SEM images of metals. A comparative analysis of the four segmentation methods showed that the best result of finding the boundaries of objects in the SEM image was obtained by the watershed method using markers. Software implementation of texture classification and image segmentation methods were performed in the MatLab system. Scientific novelty. The authors proposed a method for classifying SEM-images based on spectral texture characteristics using the parameters of the amplitude and axial functions. It is shown that the segmentation by the splitting and merging method allows you to set the conditions for selecting regions with certain texture characteristics in the SEM-image. The practical significance. A generalized characteristic of SEM-image texture, determined by statistical and spectral measurements, is that it would be useful for automatic texture recognition and SEM-images analysis. The selection of regions with certain texture characteristics is the preprocessing step for finding points of interest suitable for the SEM-image matching and objects recognition.
dc.format.extent41-50
dc.format.pages10
dc.identifier.citationIvanchuk O. A study of methods for texture classification of SEM images of micro-surfaces of objects and their segmentation / O. Ivanchuk, O. Tumska // Geodesy, cartography and aerial photography. — Lviv : Lviv Politechnic Publishing House, 2020. — No 91. — P. 41–50.
dc.identifier.citationenIvanchuk O. A study of methods for texture classification of SEM images of micro-surfaces of objects and their segmentation / O. Ivanchuk, O. Tumska // Geodesy, cartography and aerial photography. — Lviv : Lviv Politechnic Publishing House, 2020. — No 91. — P. 41–50.
dc.identifier.doidoi.org/10.23939/istcgcap2020.91.041
dc.identifier.urihttps://ena.lpnu.ua/handle/ntb/57446
dc.language.isoen
dc.publisherВидавництво Національного університету “Львівська політехніка”
dc.publisherLviv Politechnic Publishing House
dc.relation.ispartofГеодезія, картографія і аерофотознімання, 91, 2020
dc.relation.ispartofGeodesy, cartography and aerial photography, 91, 2020
dc.relation.referencesAl-Janabi Akil Bahr Tarkhan, Shuvalova, L. A. (2014).
dc.relation.referencesImage enhancement using the watershed algorithm],
dc.relation.referencesInformation Processing Systems, 8 (124), 3–7.
dc.relation.referencesAsatryan, D. G., Kurkchiyan, V. V., & Kharatyan, L. R. (2014). Method for texture classification using image
dc.relation.referencesstructural features, Computer Optics, 38(3), 574–579.
dc.relation.referencesBagalkote, I. S., & Vibhute, A. S. (2016). Review on:
dc.relation.referencesTexture Discrimination Feature Analysis for Visually
dc.relation.referencesSimilar Texture of Different Fields. International
dc.relation.referencesJournal for Scientific Research & Development, 3(9), 851–856.
dc.relation.referencesBavrina, A. Ju., Ilyasova, N. Ju. (2002). Investigation of
dc.relation.referencesphotogrammetric images using brightness distribution
dc.relation.referencesprobality matrices, Computer Optics, 23, 62–65.
dc.relation.referencesBhosle, V. V., Pawar, V. P. (2013). Texture Segmentation:
dc.relation.referencesDifferent Methods. International Journal of Soft
dc.relation.referencesComputing and Engineering (IJSCE) ISSN: 2231–2307, 3(5), 69–74.
dc.relation.referencesBogucharsky, S. I. Mashtalir, S. V. (2014). Image sequences
dc.relation.referencestexture analysis based on vector quantization, Radio
dc.relation.referencesElectronics, Computer Science, Control, 2, 94–99.
dc.relation.referencesCavalin, Paulo & Soares de Oliveira, Luiz. (2017). A
dc.relation.referencesReview of Texture Classification Methods and
dc.relation.referencesDatabases. 1–8. 10.1109/SIBGRAPI-T.2017.10.
dc.relation.referencesCord, A., Bach, F., Jeulin, D. Texture classification by
dc.relation.referencesstatistical learning from morphological image
dc.relation.referencesprocessing: application to metallic surfaces. J. Microsc.239(2), 159–166 (2010).
dc.relation.referencesFisenko, V. T., Fisenko, T. Yu. (2013). Fractal methods of
dc.relation.referencestexture image segmentation], Instrument making, 56(5), 63–70.
dc.relation.referencesForsyth, D., Pons, J. Computer Vision. The Modern
dc.relation.referencesApproach, Moscow: Williams Publishing House, 2004, 928 p.
dc.relation.referencesGolduyeva, D. A., Mokshanina, M. A. (2015). Trace
dc.relation.referencestransformation as the basis of a method for segmenting
dc.relation.referenceshalftone textures. Models, systems, networks in
dc.relation.referenceseconomics, technology, nature and society, 3 (15), 128–136.
dc.relation.referencesGonzalez, R. C., & Woods, R. E. (2005). Book on
dc.relation.references“Digital image processing”. Prentice-Hall of India
dc.relation.referencesPvt. Ltd.
dc.relation.referencesGonzalez, R. C., Woods, R. E., & Eddins, S. L. (2006).
dc.relation.referencesRuan Qiuqi (Translation). Digital Image Processing
dc.relation.referencesUsing MATLAB. Publishing House of Electronics
dc.relation.referencesIndustry, 76–77.
dc.relation.referencesGonzales-Barron, U. A. & Butler, F. (2006). Statistical
dc.relation.referencesand spectral texture analysis methods for discrimination of bread crumb images. pp. 749–759.
dc.relation.referencesDOI: 10.1051/IUFoST:20060164.Gray, A, & Marshall S. & McKenzie, J. (2006). Modeling of
dc.relation.referencesevolving textures using granulometries. Chapter in
dc.relation.referencesEurasip Book Series on Signal Processing and
dc.relation.referencesCommunications, pp. 240–270.
dc.relation.referencesGulakov, V. K., Trubakov, A. O., S. N. Ogurtsov, S. N. (2011). Informative significance of texture characteristics
dc.relation.referencesbased on the adjacency matrix of brightness levels of
dc.relation.referencesimage pixels, Bulletin of the Bryansk State Technical
dc.relation.referencesUniversity. 2(30), 81–85.
dc.relation.referencesHaindl, M., Mikeš, S. (2016). Unsupervised Texture
dc.relation.referencesSegmentation. In Pattern Recognition Techniques,
dc.relation.referencesTechnology and Applications by Peng-Yeng Yin
dc.relation.references(eds), Chap. 9. 227–248
dc.relation.referencesHaralick, R. M. (1979). Statistical and structural approach to
dc.relation.referencestextures, ProceedingsIEEE, 67, 786–804.
dc.relation.referencesHu, X. (2017). Frequency Based Texture Featurte Descriptors. 147 p.
dc.relation.referencesIvanchuk, O., Tumska, O. (2017). Comparative analysis
dc.relation.referencesof the statistical and scaling characteristics of SEM
dc.relation.referencesimages, obtained on different types of SEM, Recent
dc.relation.referencesadvances in geodetic science and industry, Lviv, II (34), 119–131.
dc.relation.referencesKhokhlov, M., Fischer, A., Rittel, D. (2012). Multi-Scale
dc.relation.referencesStereo-Photogrammetry System for Fractographic.
dc.relation.referencesAnalysis Using Scanning Electron Microscopy.
dc.relation.referencesExperimental Mechanics. 52, 975–991. DOI 10.1007/s11340-011-9582-0.
dc.relation.referencesKolodnikova, N. V. (2004). A review of texture features
dc.relation.referencesfor pattern recognition tasks. Proceedings of the
dc.relation.referencesemployees of TUSUR. Tomsk, 113–124.
dc.relation.referencesKupriyanov, A. V. (2008). Segmentation of texture images
dc.relation.referencesbased on the evaluation of local statistical signs,
dc.relation.referencesBulletin of the Samara State Aerospace University,2, 245–251.
dc.relation.referencesLee, J. H., Yoo, S. I. An effective image segmentation
dc.relation.referencestechnique for the SEM image. Conference Paper May 2008, pp. 1–6. DOI: 10.1109/ICIT.2008.4608647,
dc.relation.referencesSource: IEEE Xplore.
dc.relation.referencesLiu, X. and Wang, D. L. Image and Texture Segmentation
dc.relation.referencesUsing Local Spectral Histograms. IEEE transactions
dc.relation.referenceson image processing, 15(10), 3066–3077.
dc.relation.referencesLu, D. A., & Weng, Q. (2007). A survey of image
dc.relation.referencesclassification methods and techniques for improving
dc.relation.referencesclassification performance. International Journal of
dc.relation.referencesRemote Sensing, 28(5), 823–870.
dc.relation.referencesMadasu, V. K., Yarlagadda, P. (2007). An in depth
dc.relation.referencescomparison of four texture segmentation methods.
dc.relation.referencesDigital Image Computing Techniques and Applications.
dc.relation.referencesIEEE. pp. 366-372. DOI 10.1109/DICTA.2007.83
dc.relation.referencesManjunath, B. S., Haley, G. M., Ma Wei-Ying, Newsam,
dc.relation.referencesS. D. (2005). Multiband Techniques for Texture
dc.relation.referencesClassification and Segmentation. Chap. 4.9 in
dc.relation.referencesHandbook of Image and Video Processing. (Second
dc.relation.referencesEdition) by Bovik Al. (eds), pp. 455–470. Academic
dc.relation.referencesPress., 2005.
dc.relation.referencesMaterka, A., Strzelecki, M. (1998). Texture Analysis
dc.relation.referencesMethods – A Review. Technical University of Lodz,
dc.relation.referencesInstitute of Electronics, COST B11 report, Brussels, 10(1.97), 4968.
dc.relation.referencesMelnik, V. M., Shostak, A. V. (2009). Raster electron
dc.relation.referencesstereomicrofraktografition, Luck, Vezha, 469 p.
dc.relation.referencesMelnik, G. M. (2012). Information technology of analysis
dc.relation.referencesand synthesis of structural textures in automated
dc.relation.referencessystems for processing histological images, Thesis
dc.relation.referencesfor a Candidate Degree in Engineering, Ternopil, 27 p.
dc.relation.referencesNeogi, N., Mohanta, D. K., & Dutta, P. K. (2014). Review
dc.relation.referencesof vision-based steel surface inspection systems.
dc.relation.referencesEURASIP Journal on Image and Video Processing, 2014(1), 50. doi:10.1186/1687-5281-2014-50
dc.relation.referencesNoman, A. A., Khorkov, K. S., Shamin, P. Yu. (2014).
dc.relation.referencesResearch Methods of Semiconductor Heterostructures:
dc.relation.referencesTextbook. Allowance, Vladimir: Publishing House
dc.relation.referencesof VlSU, 80 p.
dc.relation.referencesOtsu, N. (1979). A threshold selection method from graylevel histograms. IEEE transactions on systems, man,
dc.relation.referencesand cybernetics, 9(1), 62–66.
dc.relation.referencesPolyakova, M. V., Volkova, N. P., Ivanova, O. V. (2008).
dc.relation.referencesSegmentation of the image of stochastic textures by
dc.relation.referencesthe amplitude-detector method in the vast waveletremake, Information-measuring systems AAEKS, 2, 81–88.
dc.relation.referencesPotapov, A. A. (2003). New information technologies
dc.relation.referencesbased on probabilistic texture and fractal features in
dc.relation.referencesthe radar detection of low-contrast targets], Radio
dc.relation.referencesengineering and electronics, 48(9), 1101–1119.
dc.relation.referencesPrzybył, K., Gawałek, J., Koszela, K., Przybył, J., Rudzińska, M., Gierz, Ł., & Domian, E. (2019). Neural
dc.relation.referencesimage analysis and electron microscopy to detect
dc.relation.referencesand describe selected quality factors of fruit and
dc.relation.referencesvegetable spray-dried powders—Case study: Chokeberry powder. Sensors, 19(20), 4413.
dc.relation.referencesRangayyan, R. M. (2005). Chap. 7, Analysis of texture,
dc.relation.referencespp. 1277–1375. In Biomedical Image Analysis CRC
dc.relation.referencesPress LLC, Boca Raton, FL, 2005.
dc.relation.referencesShapiro, L. G. & Stockman, G. (2001). Chap. 7, Texture,
dc.relation.referencespp. 235–247. In Computer Vision, PrenticeHall, 609 p.
dc.relation.referencesSizov, P. V., Palamar, I. N. (2011). A method and system
dc.relation.referencesfor analyzing images based on segmentation using
dc.relation.referencesmethods of growing and merging areas [Electronic
dc.relation.referencesresource], III All-Russian Scientific Zvorykinsky
dc.relation.referencesReadings: Collection of articles. thesis. doc. III AllRussian Interuniversity Scientific Conference,
dc.relation.referencesMurom, 243–244.
dc.relation.referencesSmelyakov, K. S. (2008). Correlation method for texture
dc.relation.referencesrecognition such as a mixture of images based on the
dc.relation.referencesuse of histograms, Management systems for navigation
dc.relation.referencesand communication, 4(8), 18–21.
dc.relation.referencesSparavigna, A. C. (2016). A method for the segmentation of
dc.relation.referencesimages based on thresholding and applied to vesicular
dc.relation.referencestextures. Philica, (889). hal-01408383. pp. 1–10.
dc.relation.referencesSzumilas, L., Mičušík, B. & Hanbury, A. (2006). Texture
dc.relation.referencessegmentation through salient texture patches. Computer
dc.relation.referencesVision Winter Workshop, pp. 1–6.
dc.relation.referencesTsapaev, A. P., Kretinin, O. V. (2012). Image segmentation
dc.relation.referencesmethods in surface defect detection problems.
dc.relation.referencesComputer Optics, 2012, 36(3), 448–452.
dc.relation.referencesTuceryan, M., Jain, A. K. (1998). Texture Analysis.
dc.relation.referencesChapter 2.1 in The Handbook of Pattern Recognition
dc.relation.referencesand Computer Vision (2nd Edition), by C. H. Chen,
dc.relation.referencesL. F. Pau, P. S. P. Wang (eds.), pp. 207–248, World
dc.relation.referencesScientific Publishing Co.
dc.relation.referencesVizilter, Yu.V., Zheltov, S.Yu. (2011). Problems of
dc.relation.referencestechnical vision in modern aviation systems.
dc.relation.referencesp. 11–44 in Proceedings: Technical Vision in Mobile
dc.relation.referencesObject Management Systems 2010: Proceedings of
dc.relation.referencesthe scientific and technical conference-seminar.
dc.relation.referencesVol. 4. Ed. R. R. Nazirov. Moscow: KDU, 328 p.
dc.relation.referencesZavalishin, N. V., Muchnik, I. B., Sheinin, R. L. (1975).
dc.relation.referencesAutomatic classification of texture images], Avtomat.
dc.relation.referencesand Telemech., 2, 95–103.
dc.relation.referencesenAl-Janabi Akil Bahr Tarkhan, Shuvalova, L. A. (2014).
dc.relation.referencesenImage enhancement using the watershed algorithm],
dc.relation.referencesenInformation Processing Systems, 8 (124), 3–7.
dc.relation.referencesenAsatryan, D. G., Kurkchiyan, V. V., & Kharatyan, L. R. (2014). Method for texture classification using image
dc.relation.referencesenstructural features, Computer Optics, 38(3), 574–579.
dc.relation.referencesenBagalkote, I. S., & Vibhute, A. S. (2016). Review on:
dc.relation.referencesenTexture Discrimination Feature Analysis for Visually
dc.relation.referencesenSimilar Texture of Different Fields. International
dc.relation.referencesenJournal for Scientific Research & Development, 3(9), 851–856.
dc.relation.referencesenBavrina, A. Ju., Ilyasova, N. Ju. (2002). Investigation of
dc.relation.referencesenphotogrammetric images using brightness distribution
dc.relation.referencesenprobality matrices, Computer Optics, 23, 62–65.
dc.relation.referencesenBhosle, V. V., Pawar, V. P. (2013). Texture Segmentation:
dc.relation.referencesenDifferent Methods. International Journal of Soft
dc.relation.referencesenComputing and Engineering (IJSCE) ISSN: 2231–2307, 3(5), 69–74.
dc.relation.referencesenBogucharsky, S. I. Mashtalir, S. V. (2014). Image sequences
dc.relation.referencesentexture analysis based on vector quantization, Radio
dc.relation.referencesenElectronics, Computer Science, Control, 2, 94–99.
dc.relation.referencesenCavalin, Paulo & Soares de Oliveira, Luiz. (2017). A
dc.relation.referencesenReview of Texture Classification Methods and
dc.relation.referencesenDatabases. 1–8. 10.1109/SIBGRAPI-T.2017.10.
dc.relation.referencesenCord, A., Bach, F., Jeulin, D. Texture classification by
dc.relation.referencesenstatistical learning from morphological image
dc.relation.referencesenprocessing: application to metallic surfaces. J. Microsc.239(2), 159–166 (2010).
dc.relation.referencesenFisenko, V. T., Fisenko, T. Yu. (2013). Fractal methods of
dc.relation.referencesentexture image segmentation], Instrument making, 56(5), 63–70.
dc.relation.referencesenForsyth, D., Pons, J. Computer Vision. The Modern
dc.relation.referencesenApproach, Moscow: Williams Publishing House, 2004, 928 p.
dc.relation.referencesenGolduyeva, D. A., Mokshanina, M. A. (2015). Trace
dc.relation.referencesentransformation as the basis of a method for segmenting
dc.relation.referencesenhalftone textures. Models, systems, networks in
dc.relation.referenceseneconomics, technology, nature and society, 3 (15), 128–136.
dc.relation.referencesenGonzalez, R. C., & Woods, R. E. (2005). Book on
dc.relation.referencesen"Digital image processing". Prentice-Hall of India
dc.relation.referencesenPvt. Ltd.
dc.relation.referencesenGonzalez, R. C., Woods, R. E., & Eddins, S. L. (2006).
dc.relation.referencesenRuan Qiuqi (Translation). Digital Image Processing
dc.relation.referencesenUsing MATLAB. Publishing House of Electronics
dc.relation.referencesenIndustry, 76–77.
dc.relation.referencesenGonzales-Barron, U. A. & Butler, F. (2006). Statistical
dc.relation.referencesenand spectral texture analysis methods for discrimination of bread crumb images. pp. 749–759.
dc.relation.referencesenDOI: 10.1051/IUFoST:20060164.Gray, A, & Marshall S. & McKenzie, J. (2006). Modeling of
dc.relation.referencesenevolving textures using granulometries. Chapter in
dc.relation.referencesenEurasip Book Series on Signal Processing and
dc.relation.referencesenCommunications, pp. 240–270.
dc.relation.referencesenGulakov, V. K., Trubakov, A. O., S. N. Ogurtsov, S. N. (2011). Informative significance of texture characteristics
dc.relation.referencesenbased on the adjacency matrix of brightness levels of
dc.relation.referencesenimage pixels, Bulletin of the Bryansk State Technical
dc.relation.referencesenUniversity. 2(30), 81–85.
dc.relation.referencesenHaindl, M., Mikeš, S. (2016). Unsupervised Texture
dc.relation.referencesenSegmentation. In Pattern Recognition Techniques,
dc.relation.referencesenTechnology and Applications by Peng-Yeng Yin
dc.relation.referencesen(eds), Chap. 9. 227–248
dc.relation.referencesenHaralick, R. M. (1979). Statistical and structural approach to
dc.relation.referencesentextures, ProceedingsIEEE, 67, 786–804.
dc.relation.referencesenHu, X. (2017). Frequency Based Texture Featurte Descriptors. 147 p.
dc.relation.referencesenIvanchuk, O., Tumska, O. (2017). Comparative analysis
dc.relation.referencesenof the statistical and scaling characteristics of SEM
dc.relation.referencesenimages, obtained on different types of SEM, Recent
dc.relation.referencesenadvances in geodetic science and industry, Lviv, II (34), 119–131.
dc.relation.referencesenKhokhlov, M., Fischer, A., Rittel, D. (2012). Multi-Scale
dc.relation.referencesenStereo-Photogrammetry System for Fractographic.
dc.relation.referencesenAnalysis Using Scanning Electron Microscopy.
dc.relation.referencesenExperimental Mechanics. 52, 975–991. DOI 10.1007/s11340-011-9582-0.
dc.relation.referencesenKolodnikova, N. V. (2004). A review of texture features
dc.relation.referencesenfor pattern recognition tasks. Proceedings of the
dc.relation.referencesenemployees of TUSUR. Tomsk, 113–124.
dc.relation.referencesenKupriyanov, A. V. (2008). Segmentation of texture images
dc.relation.referencesenbased on the evaluation of local statistical signs,
dc.relation.referencesenBulletin of the Samara State Aerospace University,2, 245–251.
dc.relation.referencesenLee, J. H., Yoo, S. I. An effective image segmentation
dc.relation.referencesentechnique for the SEM image. Conference Paper May 2008, pp. 1–6. DOI: 10.1109/ICIT.2008.4608647,
dc.relation.referencesenSource: IEEE Xplore.
dc.relation.referencesenLiu, X. and Wang, D. L. Image and Texture Segmentation
dc.relation.referencesenUsing Local Spectral Histograms. IEEE transactions
dc.relation.referencesenon image processing, 15(10), 3066–3077.
dc.relation.referencesenLu, D. A., & Weng, Q. (2007). A survey of image
dc.relation.referencesenclassification methods and techniques for improving
dc.relation.referencesenclassification performance. International Journal of
dc.relation.referencesenRemote Sensing, 28(5), 823–870.
dc.relation.referencesenMadasu, V. K., Yarlagadda, P. (2007). An in depth
dc.relation.referencesencomparison of four texture segmentation methods.
dc.relation.referencesenDigital Image Computing Techniques and Applications.
dc.relation.referencesenIEEE. pp. 366-372. DOI 10.1109/DICTA.2007.83
dc.relation.referencesenManjunath, B. S., Haley, G. M., Ma Wei-Ying, Newsam,
dc.relation.referencesenS. D. (2005). Multiband Techniques for Texture
dc.relation.referencesenClassification and Segmentation. Chap. 4.9 in
dc.relation.referencesenHandbook of Image and Video Processing. (Second
dc.relation.referencesenEdition) by Bovik Al. (eds), pp. 455–470. Academic
dc.relation.referencesenPress., 2005.
dc.relation.referencesenMaterka, A., Strzelecki, M. (1998). Texture Analysis
dc.relation.referencesenMethods – A Review. Technical University of Lodz,
dc.relation.referencesenInstitute of Electronics, COST B11 report, Brussels, 10(1.97), 4968.
dc.relation.referencesenMelnik, V. M., Shostak, A. V. (2009). Raster electron
dc.relation.referencesenstereomicrofraktografition, Luck, Vezha, 469 p.
dc.relation.referencesenMelnik, G. M. (2012). Information technology of analysis
dc.relation.referencesenand synthesis of structural textures in automated
dc.relation.referencesensystems for processing histological images, Thesis
dc.relation.referencesenfor a Candidate Degree in Engineering, Ternopil, 27 p.
dc.relation.referencesenNeogi, N., Mohanta, D. K., & Dutta, P. K. (2014). Review
dc.relation.referencesenof vision-based steel surface inspection systems.
dc.relation.referencesenEURASIP Journal on Image and Video Processing, 2014(1), 50. doi:10.1186/1687-5281-2014-50
dc.relation.referencesenNoman, A. A., Khorkov, K. S., Shamin, P. Yu. (2014).
dc.relation.referencesenResearch Methods of Semiconductor Heterostructures:
dc.relation.referencesenTextbook. Allowance, Vladimir: Publishing House
dc.relation.referencesenof VlSU, 80 p.
dc.relation.referencesenOtsu, N. (1979). A threshold selection method from graylevel histograms. IEEE transactions on systems, man,
dc.relation.referencesenand cybernetics, 9(1), 62–66.
dc.relation.referencesenPolyakova, M. V., Volkova, N. P., Ivanova, O. V. (2008).
dc.relation.referencesenSegmentation of the image of stochastic textures by
dc.relation.referencesenthe amplitude-detector method in the vast waveletremake, Information-measuring systems AAEKS, 2, 81–88.
dc.relation.referencesenPotapov, A. A. (2003). New information technologies
dc.relation.referencesenbased on probabilistic texture and fractal features in
dc.relation.referencesenthe radar detection of low-contrast targets], Radio
dc.relation.referencesenengineering and electronics, 48(9), 1101–1119.
dc.relation.referencesenPrzybył, K., Gawałek, J., Koszela, K., Przybył, J., Rudzińska, M., Gierz, Ł., & Domian, E. (2019). Neural
dc.relation.referencesenimage analysis and electron microscopy to detect
dc.relation.referencesenand describe selected quality factors of fruit and
dc.relation.referencesenvegetable spray-dried powders-Case study: Chokeberry powder. Sensors, 19(20), 4413.
dc.relation.referencesenRangayyan, R. M. (2005). Chap. 7, Analysis of texture,
dc.relation.referencesenpp. 1277–1375. In Biomedical Image Analysis CRC
dc.relation.referencesenPress LLC, Boca Raton, FL, 2005.
dc.relation.referencesenShapiro, L. G. & Stockman, G. (2001). Chap. 7, Texture,
dc.relation.referencesenpp. 235–247. In Computer Vision, PrenticeHall, 609 p.
dc.relation.referencesenSizov, P. V., Palamar, I. N. (2011). A method and system
dc.relation.referencesenfor analyzing images based on segmentation using
dc.relation.referencesenmethods of growing and merging areas [Electronic
dc.relation.referencesenresource], III All-Russian Scientific Zvorykinsky
dc.relation.referencesenReadings: Collection of articles. thesis. doc. III AllRussian Interuniversity Scientific Conference,
dc.relation.referencesenMurom, 243–244.
dc.relation.referencesenSmelyakov, K. S. (2008). Correlation method for texture
dc.relation.referencesenrecognition such as a mixture of images based on the
dc.relation.referencesenuse of histograms, Management systems for navigation
dc.relation.referencesenand communication, 4(8), 18–21.
dc.relation.referencesenSparavigna, A. C. (2016). A method for the segmentation of
dc.relation.referencesenimages based on thresholding and applied to vesicular
dc.relation.referencesentextures. Philica, (889). hal-01408383. pp. 1–10.
dc.relation.referencesenSzumilas, L., Mičušík, B. & Hanbury, A. (2006). Texture
dc.relation.referencesensegmentation through salient texture patches. Computer
dc.relation.referencesenVision Winter Workshop, pp. 1–6.
dc.relation.referencesenTsapaev, A. P., Kretinin, O. V. (2012). Image segmentation
dc.relation.referencesenmethods in surface defect detection problems.
dc.relation.referencesenComputer Optics, 2012, 36(3), 448–452.
dc.relation.referencesenTuceryan, M., Jain, A. K. (1998). Texture Analysis.
dc.relation.referencesenChapter 2.1 in The Handbook of Pattern Recognition
dc.relation.referencesenand Computer Vision (2nd Edition), by C. H. Chen,
dc.relation.referencesenL. F. Pau, P. S. P. Wang (eds.), pp. 207–248, World
dc.relation.referencesenScientific Publishing Co.
dc.relation.referencesenVizilter, Yu.V., Zheltov, S.Yu. (2011). Problems of
dc.relation.referencesentechnical vision in modern aviation systems.
dc.relation.referencesenp. 11–44 in Proceedings: Technical Vision in Mobile
dc.relation.referencesenObject Management Systems 2010: Proceedings of
dc.relation.referencesenthe scientific and technical conference-seminar.
dc.relation.referencesenVol. 4. Ed. R. R. Nazirov. Moscow: KDU, 328 p.
dc.relation.referencesenZavalishin, N. V., Muchnik, I. B., Sheinin, R. L. (1975).
dc.relation.referencesenAutomatic classification of texture images], Avtomat.
dc.relation.referencesenand Telemech., 2, 95–103.
dc.rights.holder© Національний університет “Львівська політехніка”, 2020
dc.subjectрастровий електронний мікроскоп (РEM)
dc.subjectстатистичні та спектральні характеристики текстури РEM-зображення
dc.subjectкласифікація
dc.subjectсегментація
dc.subjectscanning electron microscope (SEM)
dc.subjectstatistical and spectral texture features of the SEM image
dc.subjectclassification
dc.subjectsegmentation
dc.subject.udc528.721.287
dc.subject.udc537.533.35
dc.titleA study of methods for texture classification of SEM images of micro-surfaces of objects and their segmentation
dc.title.alternativeДослідження методів класифікації текстур РЕМ-зображень мікроповерхонь об’єктів та їх сегментація
dc.typeArticle

Files

Original bundle

Now showing 1 - 2 of 2
Thumbnail Image
Name:
2020n91_Ivanchuk_O-A_study_of_methods_for_texture_41-50.pdf
Size:
1.31 MB
Format:
Adobe Portable Document Format
Thumbnail Image
Name:
2020n91_Ivanchuk_O-A_study_of_methods_for_texture_41-50__COVER.png
Size:
515.84 KB
Format:
Portable Network Graphics

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.79 KB
Format:
Plain Text
Description: