<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">izvestswsu</journal-id><journal-title-group><journal-title xml:lang="ru">Известия Юго-Западного государственного университета</journal-title><trans-title-group xml:lang="en"><trans-title>Proceedings of the Southwest State University</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2223-1560</issn><issn pub-type="epub">2686-6757</issn><publisher><publisher-name>ЮЗГУ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21869/2223-1560-2020-24-1-144-158</article-id><article-id custom-type="elpub" pub-id-type="custom">izvestswsu-728</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>Информатика, вычислительная техника и управление</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Computer science, computer engineering and IT managment</subject></subj-group></article-categories><title-group><article-title>Алгоритм сегментации изображений на основе персистентной гомологии для решения задач поиска дефектов</article-title><trans-title-group xml:lang="en"><trans-title>An Algorithm of Image Segmentation Based on Persistent Homology for Solving Defects Searching Problems</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Еремеев</surname><given-names>С. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Eremeev</surname><given-names>S. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Еремеев Сергей Владимирович, кандидат технических наук, доцент кафедры информационных систем</p><p>ул. Орловская 23, г. Муром 602264</p></bio><bio xml:lang="en"><p>Sergey V. Eremeev, Cand. of Sci. (Engineering), Associate Professor, Department of Information Systems</p><p>23 Orlovskaya str., Murom 602264</p></bio><email xlink:type="simple">sv-eremeev@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Романов</surname><given-names>С. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Romanov</surname><given-names>S. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Романов Семен Алексеевич, магистр информационных систем, старший разработчик</p><p>пр. Нариманова 1, г. Ульяновск 432001</p></bio><bio xml:lang="en"><p>Semyon А. Romanov, Master of Information Systems, Senior Developer</p><p>1 Narimanova av., Ulyanovsk 432001</p></bio><email xlink:type="simple">cwwc@bk.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Муромский институт ФГБОУ ВО Владимирского государственного университета им. А. Г. и Н. Г. Столетовых</institution></aff><aff xml:lang="en"><institution>Murom Institute (branch) of Vladimir State University named after A.G. and N.G. Stoletovs</institution></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>ООО «СимбирСофт»</institution></aff><aff xml:lang="en"><institution>SimbirSoft LLC</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2020</year></pub-date><pub-date pub-type="epub"><day>23</day><month>06</month><year>2020</year></pub-date><volume>24</volume><issue>1</issue><fpage>144</fpage><lpage>158</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Еремеев С.В., Романов С.А., 2020</copyright-statement><copyright-year>2020</copyright-year><copyright-holder xml:lang="ru">Еремеев С.В., Романов С.А.</copyright-holder><copyright-holder xml:lang="en">Eremeev S.V., Romanov S.A.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://izvestswsu.elpub.ru/jour/article/view/728">https://izvestswsu.elpub.ru/jour/article/view/728</self-uri><abstract><p>Целью исследования является разработка алгоритма сегментации изображений на основе персистентной гомологии для решения задач поиска и классификации дефектов. Алгоритм направлен на повышение качества производимой продукции на предприятиях с непрерывным производством (металлургия, деревообрабатывающая промышленность и другие).</p><sec><title>Методы</title><p>Методы. Для сегментации изображения предлагается установить связи между пикселями изображения. В дальнейшем, в процессе итерационного разрыва связей по мере увеличения их весов пиксели будут объединяться в группы, называемые дырами. Пиксели, объединенные в единую группу, имеют как свои первоначальные характеристики, так и общие характеристики для всей группы, а также изменяют веса своих связей с представителями других групп. Таким образом, образуется история формирования отдельных групп пикселей, которые можно обозначить в виде сегментов с временной характеристикой изменения.</p></sec><sec><title>Результаты</title><p>Результаты. Итогом проведенного исследования является разработка алгоритма, предназначенного для поиска и классификации дефектов различных материалов. Разработан оптимальный алгоритм применения принципа персистентной гомологии к изображениям, проанализированы и выбраны факторы, определяющие переходные границы объектов изображения. Алгоритм сегментации опробован на изображениях металла, полученных с листопрокатного оборудования. Показаны результаты сравнения работы предложенного алгоритма с алгоритмами сегментации k-means и Mean-Shift при различных параметрах.</p></sec><sec><title>Заключение</title><p>Заключение. Применение персистентной гомологии в задачах сегментации изображений может позволить создать инструмент, применимый к материалам с различной структурой без необходимости существенных изменений. Программная реализация процесса сегментации на основе применения принципов компьютерной топологии показала высокую гибкость благодаря сохранению истории изменения сегментов.</p></sec></abstract><trans-abstract xml:lang="en"><p>Purpose of research is to develop an image segmentation algorithm based on the persistent homology for solving problems of searching and classifying defects. The algorithm is aimed at improving the quality of products at enterprises with continuous production (metallurgy, woodworking, and others).</p><sec><title>Methods</title><p>Methods. To segment an image, it is proposed to specify links between pixels in the image. In the future, during the iterative breaking of links, as their weights increase, pixels will be combined into groups called holes. Pixels that are in a single group have both their original characteristics and characteristics common for the entire group, and they also change the weights of their links with representatives of other groups. This creates a history of the formation of separate groups of pixels which can be specified as segments with a time-based characteristic of the change.</p></sec><sec><title>Results</title><p>Results. The result of the research is the development of an algorithm designed to search for and classify defects in various materials. The optimal algorithm for applying the principle of persistent homology to images has been developed, and factors determining the transition boundaries of image objects have been analyzed and selected. The segmentation algorithm was tested on metal images obtained from sheet rolling equipment. The results of comparing the proposed algorithm with the K-means and Mean-Shift segmentation algorithms for different parameters are provided in the article.</p></sec><sec><title>Conclusion</title><p>Conclusion. Using persistent homology in image segmentation tasks can enable creating a tool that can be applied to materials with different structures without any need for significant changes. The software implementation of the segmentation process based on the principles of computer topology has shown high flexibility due to the storing of the history of segment changes.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>дефектоскопия</kwd><kwd>персистентные гомологии</kwd><kwd>сегментация</kwd><kwd>компьютерная топология</kwd></kwd-group><kwd-group xml:lang="en"><kwd>defect detection</kwd><kwd>persistent homology</kwd><kwd>segmentation</kwd><kwd>computer topology</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Илющенко А. В. Анализ методов обработки изображений пиломатериалов, имеющих пороки и дефекты // Известия Санкт-Петербургской лесотехнической академии. 2017. № 218. С. 153–163.</mixed-citation><mixed-citation xml:lang="en">Ilyushchenko A. V. Analiz metodov obrabotki izobrazhenij pilomaterialov, imeyushchih poroki i defekty [Analysis of methods for processing images of lumber with flaws and defects]. Izvestiya Sankt-Peterburgskoj lesotekhnicheskoj akademii = Izvestia of the St. Petersburg Academy of Forestry Engineering, 2017, no. 218, pp. 153–163 (in Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Цапаев А. П., Кретинин О. В. Методы сегментации изображений в задачах обнаружения дефектов поверхности // Компьютерная оптика. 2012. № 36(3). С. 448–452.</mixed-citation><mixed-citation xml:lang="en">Capaev A. P., Kretinin O. V. Metody segmentacii izobrazhenij v zadachah obnaruzheniya defektov poverhnosti [Image segmentation methods in problems of surface defect detection]. Komp'yuternaya optika = Computer Optics, 2012, vol. 36, no. 3, pp. 448–452 (in Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Badrinarayanan V., Kendall A., Cipolla R. A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2017. Vol. 39. P. 2481–2495.</mixed-citation><mixed-citation xml:lang="en">Badrinarayanan V., Kendall A., Cipolla R. A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, vol. 39, pp. 2481–2495.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Learning Video Object Segmentation from Static Images / F. Perazzi, A. Khoreva, R. Benenson, B. Schiele, A. Sorkine-Hornung // IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. P. 2663–2672.</mixed-citation><mixed-citation xml:lang="en">Perazzi F., Khoreva A., Benenson R, Schiele B., Sorkine-Hornung A. Learning Video Object Segmentation from Static Images. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2663–2672.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Panoptic Segmentation / A. Kirillov, K. He, R. Girshick, C. Rother, P. Dollar // The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2019. P. 94049413.</mixed-citation><mixed-citation xml:lang="en">Kirillov A., He K., Girshick R., Rother C., Dollar P. Panoptic Segmentation. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 9404–9413.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">A multi-scale 3D Otsu thresholding algorithm for medical image segmentation / Y. Feng, H. Zhao, X. Li, X. Zhang, H. Li // Digital Signal Processing. 2017. Vol. 60. P. 186–199.</mixed-citation><mixed-citation xml:lang="en">Feng Y., Zhao H., Li X., Zhang X, Li H. A multi-scale 3D Otsu thresholding algorithm for medical image segmentation. Digital Signal Processing, 2017, vol. 60, pp. 186–199.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Head and neck target delineation using a novel PET automatic segmentation algorithm / B. Berthon, M. Evans, C. Marshall, N. Palaniappan, N. Cole, V. Jayaprakasam, T. Rackley, E. Spezi // Radiotherapy and Oncology. 2017. Vol. 122. P. 242–247.</mixed-citation><mixed-citation xml:lang="en">Berthon B., Evans M., Marshall C., Palaniappan N., Cole N., Jayaprakasam V., Rackley T., Spezi E. Head and neck target delineation using a novel PET automatic segmentation algorithm. Radiotherapy and Oncology, 2017, vol. 122, pp. 242–247.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Real-Time Superpixel Segmentation by DBSCAN Clustering Algorithm / J. Shen, X. Hao, Z. Liang, Y. Liu, W. Wang, L. Shao // IEEE Transactions on Image Processing. 2016. Vol. 25. P. 5933–5942.</mixed-citation><mixed-citation xml:lang="en">Shen J., Hao X., Liang Z., Liu Y., Wang W., Shao L. Real-Time Superpixel Segmentation by DBSCAN Clustering Algorithm. IEEE Transactions on Image Processing, 2016, vol. 25, pp. 5933–5942.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Еремеев С.В., Андрианов Д.Е., Титов В.С. Алгоритм совмещения пространственных объектов разномасштабных карт на основе топологического анализа данных // Компьютерная оптика. 2019. № 43(6). С. 1021–1029.</mixed-citation><mixed-citation xml:lang="en">Eremeev S.V., Andrianov D.E., Titov V.S. Algoritm sovmeshcheniya prostranstvennyh ob"ektov raznomasshtabnyh kart na osnove topologicheskogo analiza dannyh [An algorithm for matching spatial objects of different-scale maps based on topological data analysis]. Komp'yuternaya optika = Computer Optics, 2019, vol. 43, no. 6, pp. 1021–1029 (in Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Андрианов Д. Е., Еремеев С. В., Купцов К. В. Алгоритм семантической классификации пространственных объектов и сцен с использованием топологических признаков и классификатора random forest на многомасштабных картах // Прикаспийский журнал: управление и высокие технологии. 2018. № 4. С. 8–18.</mixed-citation><mixed-citation xml:lang="en">Andrianov D. E., Eremeev S. V., Kuptsov K. V. Algoritm semanticheskoj klassifikacii prostranstvennyh ob"ektov i scen s ispol'zovaniem topologicheskih priznakov i klassifikatora random forest na mnogomasshtabnyh kartah [Algorithm of semantic classification of spatial objects and scenes using topological features and random forest classifier on multiscale maps]. Prikaspijskij zhurnal: upravlenie i vysokie tekhnologii = Caspian Sea Journal: Management and High Technology, 2018, no. 4, pp. 8–18 (in Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Eremeev S., Seltsova E. Algorithms for Topological Analysis of Spatial Data // Advances in Intelligent Systems and Computing. 2020. Vol. 902. P. 81 – 92.</mixed-citation><mixed-citation xml:lang="en">Eremeev S., Seltsova E. Algorithms for Topological Analysis of Spatial Data. Advances in Intelligent Systems and Computing, 2020, vol. 902, pp. 81–92.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Еремеев С.В., Сельцова Е.А. Алгоритм топологического анализа пространственных структур в геоинформационных системах // Алгоритмы, методы и системы обработки данных. 2017. № 1. С. 16–27.</mixed-citation><mixed-citation xml:lang="en">Eremeev S.V., Seltsova E.A. Algoritm topologicheskogo analiza prostranstvennyh struktur v geoinformacionnyh sistemah [Algorithm of topological analysis of spatial structures in geographic information systems]. Algoritmy, metody i sistemy obrabotki dannyh = Algorithms, methods, and data processing systems , 2017, no. 1, pp. 16–27 (in Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Edelsbrunner H., Harer J. Computational topology. An introduction. AMS, Providence. 2010.</mixed-citation><mixed-citation xml:lang="en">Edelsbrunner H., Harer J. Computational topology. An introduction. AMS, Providence, 2010.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Kurlin V. A fast persistence-based segmentation of noisy 2d clouds with provable guarantees // Pattern Recognition Letters. 2016. Vol. 83. P. 3–12.</mixed-citation><mixed-citation xml:lang="en">Kurlin V. A fast persistence-based segmentation of noisy 2d clouds with provable guarantees. Pattern Recognition Letters, 2016, vol. 83, pp. 3–12.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Распознавание текстур на цифровых изображениях методами вычислительной топологии / Н.Г. Макаренко, Ф.А. Уртьев, И.С. Князева, Д.Б. Малкова, И.Т. Пак, Л.М. Каримова // Современные проблемы дистанционного зондирования Земли из космоса. 2015. № 12(1). С. 131-144.</mixed-citation><mixed-citation xml:lang="en">Makarenko N.G., Urtev F.A., Knyazeva I.S., Malkova D.B., Pak I.T., Karimova L.M. Raspoznavanie tekstur na cifrovyh izobrazheniyah metodami vychislitel'noj topologii [Recognition of textures in digital images using computational topology methods]. Sovremennye problemy distancionnogo zondirovaniya Zemli iz kosmosa = Current problems of remote sensing of the Earth from space, 2015, vol. 12, no. 1, pp. 131–144 (in Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Eremeev S., Kuptsov K., Romanov S. An approach to establishing the correspondence of spatial objects on heterogeneous maps based on methods of computational topology // Lecture Notes in Computer Science. 2018. Vol. 10716. P. 172–182.</mixed-citation><mixed-citation xml:lang="en">Eremeev S., Kuptsov K., Romanov S. An approach to establishing the correspondence of spatial objects on heterogeneous maps based on methods of computational topology. Lecture Notes in Computer Science, 2018, vol. 10716, pp. 172–182.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Алгоритм идентификации пространственных объектов растровой карты на основе топологического анализа данных / С.В. Еремеев, Д.Е. Андрианов, К.В. Купцов, Ю.А. Ковалев // Телекоммуникации. 2017. № 7. С. 39–44.</mixed-citation><mixed-citation xml:lang="en">Eremeev S.V., Andrianov D.E., Kuptsov K.V., Kovalev Y.A. Algoritm identifikacii prostranstvennyh ob"ektov rastrovoj karty na osnove topologicheskogo analiza dannyh [Algorithm for identification of spatial objects in a raster map based on topological data analysis]. Telekommunikacii = Telecommunications, 2017, no. 7, pp. 39–44 (in Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Room segmentation: Survey, implementation, and analysis / R. Bormann, F. Jordan, W. Li, J. Hampp, M Hägele // IEEE International Conference on Robotics and Automation (ICRA). 2016. P. 1018–1026.</mixed-citation><mixed-citation xml:lang="en">Bormann R., Jordan F., Li W., Hampp J., Hägele M. Room segmentation: Survey, implementation, and analysis. IEEE International Conference on Robotics and Automation (ICRA), 2016, pp. 1018–1026.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">El-Khatib S., Skobtsov Y., Rodzin S. Theoretical and Experimental Evaluation of Hybrid ACO-k-means Image Segmentation Algorithm for MRI Images Using Drift-analysis // Procedia Computer Science. 2019. Vol. 150. P. 324–332.</mixed-citation><mixed-citation xml:lang="en">El-Khatib S., Skobtsov Y., Rodzin S. Theoretical and Experimental Evaluation of Hybrid ACO-k-means Image Segmentation Algorithm for MRI Images Using Drift-analysis. Procedia Computer Science, 2019, vol. 150, pp. 324–332.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Kavzoglu T., Tonbul H. A comparative study of segmentation quality for multiresolution segmentation and watershed transform // 8th International Conference on Recent Advances in Space Technologies (RAST). 2017. P. 113–117.</mixed-citation><mixed-citation xml:lang="en">Kavzoglu T., Tonbul H. A comparative study of segmentation quality for multiresolution segmentation and watershed transform. 8th International Conference on Recent Advances in Space Technologies (RAST), 2017, pp. 113–117.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
