<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD with OASIS Tables with MathML3 v1.4 20241031//EN" "https://jats.nlm.nih.gov/archiving/1.4/JATS-archive-oasis-article1-4-mathml3.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" dtd-version="1.4" article-type="research-article" xml:lang="en"><front><journal-meta><journal-title-group><journal-title xml:lang="ru">Математическая физика и компьютерное моделирование</journal-title></journal-title-group><issn publication-format="print">2587-6325</issn><issn publication-format="electronic">2587-6902</issn></journal-meta><article-meta><article-id pub-id-type="doi">10.15688/mpcm.jvolsu.2023.1.3</article-id><article-categories><subj-group><subject>Other</subject></subj-group></article-categories><title-group><article-title xml:lang="ru">Разработка классификатора фотоизображений патологий для ультрамалого набора данных</article-title><trans-title-group xml:lang="en"><trans-title>Development of a classifier of photo images of pathologies for an ultra-small data set</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><name-alternatives><name xml:lang="ru"><surname>Адамов</surname><given-names>Антон Андреевич</given-names></name><name xml:lang="en"><surname>Adamov</surname><given-names>Anton A.</given-names></name></name-alternatives><xref ref-type="aff" rid="aff1"/><email>anton.a.adamov@gmail.com</email><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-7394-0744</contrib-id></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="ru"><surname>Гндоян</surname><given-names>Ирина Асатуровна</given-names></name><name xml:lang="en"><surname>Gndoyan</surname><given-names>Irina A.</given-names></name></name-alternatives><xref ref-type="aff" rid="aff2"/><email>irina.gndoyan@mail.ru</email><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-7581-9473</contrib-id></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="ru"><surname>Дятчина</surname><given-names>Алена Игоревна</given-names></name><name xml:lang="en"><surname>Dyatchina</surname><given-names>Alena I.</given-names></name></name-alternatives><xref ref-type="aff" rid="aff2"/><email>alena.dyatchina@yandex.ru</email><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-9632-5800</contrib-id></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="ru"><surname>Храмов</surname><given-names>Владимир Николаевич</given-names></name></name-alternatives><xref ref-type="aff" rid="aff1"/><email>vladimir.khramov@volsu.ru</email><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-8988-0929</contrib-id></contrib><aff-alternatives id="aff1"><aff xml:lang="en"><institution>Volgograd State University(Volgograd, Russian Federation)</institution></aff><aff xml:lang="ru"><institution>Волгоградский государственный университет( г. Волгоград, Российская Федерация)</institution></aff></aff-alternatives><aff-alternatives id="aff2"><aff xml:lang="en"><institution>Volgograd State Medical University(Volgograd, Russian Federation)</institution></aff><aff xml:lang="ru"><institution>Волгоградский государственный медицинский университет(г. Волгоград, Российская Федерация)</institution></aff></aff-alternatives></contrib-group><pub-date pub-type="epub" iso-8601-date="2023-02-01"><day>01</day><month>02</month><year>2023</year></pub-date><volume>26</volume><issue>1</issue><fpage>33</fpage><lpage>48</lpage><history><date date-type="received" iso-8601-date="2023-01-11"><day>11</day><month>01</month><year>2023</year></date><date date-type="accepted" iso-8601-date="2023-02-21"><day>21</day><month>02</month><year>2023</year></date></history><permissions><license xlink:href="https://creativecommons.org/licenses/by-nc/4.0/" xlink:title="CC BY-NC 4.0"><ali:license_ref>https://creativecommons.org/licenses/by-nc/4.0/</ali:license_ref><license-p xml:lang="ru">CC BY-NC 4.0</license-p></license></permissions><abstract xml:lang="ru"><p>Цель работы: создать алгоритм и реализовать его в программном средстве для классификации фотоизображений патологий центральной области глазного дна человека, выявляемых при помощи исследования аутофлюоресценции, по 8 типам-паттернам: нормальный, минимальные изменения, фокальный, пятнистый, линейный, кружевоподобный, ретикулярный, крапчатый. Методы: алгоритмы машинного обучения (сверточные нейронные сети) и компьютерного зрения (гистораммные методы, перцептивные хэш-алгоритмы). Главная особенность задачи: ультрамалый набор уникальных фотоизображений с точно диагностируемым типом патологии (18 штук). Точность прогнозов при решении задачи с помощью нейросети 12,5%. Точность прогнозов разработанного алгоритма с использованием комбинации гистограмм, перцептивного хэша и 1 опорного фото нормального состояния глазного дна равна 60% при подборе параметров классификатора из набора 1 фото на 1 патологию. При использовании 3 опорных фото нормы — 85%. Предложенное решение может использоваться в медицине, офтальмологии, фотонике и оптике биотканей, машинном обучении как в научно-исследовательских, так и учебных целях.</p></abstract><abstract xml:lang="en" abstract-type="summary"><p>The purpose of the work is to create an algorithm and implement it in a software tool for classifying photographic images of pathology of the central region of the human fundus, detected by autofluorescence research, according to 8 types-patterns: normal, minimal changes, focal, spotted, linear, lacelike, reticular, speckled. Methods used machine learning algorithms (convolutional neural networks) and computer vision (histogram methods, perceptual hash algorithms). The main feature of the task is an ultra-small set of unique photoimages with an accurately diagnosed type of pathology (18 pieces). The accuracy of forecasts when solving a problem using a neural network is 12.5%. The accuracy of the predictions of the developed algorithm using a combination of histograms, perceptual hash and one reference photo of the normal state of the fundus is 60% when selecting the classifier parameters from a set of one photo for one pathology. When using three reference photos, the norm is 85%. The proposed solution can be used in medicine, ophthalmology, photonics and optics of biological tissues, machine learning for both research and educational purposes.</p></abstract><kwd-group xml:lang="ru"><kwd>обработка фотоизображений</kwd><kwd>компьютерное зрение</kwd><kwd>машинное обучение</kwd><kwd>классификация изображений</kwd><kwd>гистограмма</kwd><kwd>перцептивный хэш</kwd><kwd>офтальмологическая диагностика</kwd><kwd>компьютеризация медицины</kwd></kwd-group><kwd-group xml:lang="en"><kwd>photo image processing</kwd><kwd>computer vision</kwd><kwd>machine learning</kwd><kwd>image classification</kwd><kwd>histogram</kwd><kwd>perceptual hash</kwd><kwd>ophthalmological diagnostics</kwd><kwd>computerization of medicine</kwd></kwd-group></article-meta></front><back><ref-list><ref id="ref1"><mixed-citation publication-type="other" xml:lang="ru">База данных: Патологии центральной области глазного дна человека, выявляемые при помощи исследования аутофлюоресценцией. — Электрон. текстовые дан. — Режим доступа: https://notabug.org/Tonypythony/meddb. — Загл. с экрана.</mixed-citation></ref><ref id="ref2"><mixed-citation publication-type="other" xml:lang="ru">Бобков, А. В. Системы распознавания образов : учеб. пособие / А. В. Бобков. — М. : Изд-во МГТУ им. Н. Э. Баумана, 2018. — 187 c.</mixed-citation></ref><ref id="ref3"><mixed-citation publication-type="other" xml:lang="ru">Гермашев, И. В. Применение моделей нечеткой математики для решения задач медицинской диагностики / И. В. Гермашев, В. И. Дубовская // Математическая физика и компьютерное моделирование. — 2021. — Т. 24, № 4. — C. 53–65. — DOI: https://doi.org/10.15688/mpcm.jvolsu.2021.4.4</mixed-citation></ref><ref id="ref4"><mixed-citation publication-type="other" xml:lang="ru">Гндоян, И. А. Аутофлюоресценция глазного дна в диагностике возрастной макулярной дегенерации / И. А. Гндоян, А. В. Петраевский, А. И. Дятчина // Вестник офтальмологии. — 2020. — Т. 136, № 5. — C. 136–141. — DOI: https://doi.org/10.17116/oftalma2020136051136</mixed-citation></ref><ref id="ref5"><mixed-citation publication-type="other" xml:lang="ru">Гонсалес, Р. Цифровая обработка изображений / Р. Гонсалес, Р. Вудс. — М. : Техносфера, 2005. — 1072 c.</mixed-citation></ref><ref id="ref6"><mixed-citation publication-type="other" xml:lang="ru">Джереми, Х. Глубокое обучение с fastai и PyTorch: минимум формул, минимум кода, максимум эффективности / Х. Джереми, Г. Сильвейн. — СПб. : Питер, 2022. — 624 c.</mixed-citation></ref><ref id="ref7"><mixed-citation publication-type="other" xml:lang="ru">Ильясова, Н. Ю. Применение сверточных нейронных сетей для анализа изображений глазного дна / Н. Ю. Ильясова, А. С. Широканев, И. А. Климов // Сборник трудов ИТНТ-2019. — 2019. — Т. 4. — C. 111–118.</mixed-citation></ref><ref id="ref8"><mixed-citation publication-type="other" xml:lang="ru">Использование программы IBM WATSON в лечении онкологических заболеваний в Южной Корее. — Электрон. текстовые дан. — Режим доступа: https://medical-express.ru/branches/oncologiya/ibm-watson-v-medicine. — Загл. с экрана.</mixed-citation></ref><ref id="ref9"><mixed-citation publication-type="other" xml:lang="ru">Классификатор фотоизображений АФ глазного дна. — Электрон. текстовые дан. — Режим доступа: https://github.com/Antoniii/humashineye. — Загл. с экрана.</mixed-citation></ref><ref id="ref10"><mixed-citation publication-type="other" xml:lang="ru">Крейман, Г. Биологическое и компьютерное зрение / Г. Крейман. — М. : ДМК Пресс, 2022. — 314 c.</mixed-citation></ref><ref id="ref11"><mixed-citation publication-type="other" xml:lang="ru">Логинов, В. Н. Разработка web-приложения системы идентификации дефектов металла на полутоновых изображениях с использованием каскадного классификатора Хаара на платформе Asp .Net Core MVC / В. Н. Логинов, К. А. Щипанов, В. В. Лавров // Вестник Череповецкого государственного университета. — 2019. — № 4. — C. 8–22.</mixed-citation></ref><ref id="ref12"><mixed-citation publication-type="other" xml:lang="ru">Лосев, А. Г. Интеллектуальный анализ данных микроволновой радиотермометрии в диагностике рака молочной железы / А. Г. Лосев, В. В. Левшинский // Математическая физика и компьютерное моделирование. — 2017. — № 5 (342). — C. 16–22. — DOI: https://doi.org/10.15688/mpcm.jvolsu.2017.5.6</mixed-citation></ref><ref id="ref13"><mixed-citation publication-type="other" xml:lang="ru">Лошманов, В. И. Разработка и валидация метода классификации офтальмологической патологии с применением глубокого машинного обучения / В. И. Лошманов, А. Г. Кравец // Вестник Астраханского государственного технического университета. Серия: Управление, вычислительная техника и информатика. — 2021. — № 2. — C. 57–65. — DOI: 10.24143/2072-9502-2021-2-57-65</mixed-citation></ref><ref id="ref14"><mixed-citation publication-type="other" xml:lang="ru">Методы и алгоритмы контурного анализа для задач классификации сложноструктурируемых изображений / М. В. Дюдин, А. Д. Поваляев, Е. С. Подвальный, Р. А. Томакова // Вестник ВГТУ. — 2014. — Т. 10, № 3–1. — C. 54–59.</mixed-citation></ref><ref id="ref15"><mixed-citation publication-type="other" xml:lang="ru">Молодяков, С. А. Применение функций OpenCV в компьютерном зрении (60 примеров на Python) / С. А. Молодяков. — СПб. : Изд-во Политехн. ун-та, 2022. — 296 c.</mixed-citation></ref><ref id="ref16"><mixed-citation publication-type="other" xml:lang="ru">Обнаружение объектов без машинного обучения. — Электрон. текстовые дан. — Режим доступа: https://newtechaudit.ru/obnaruzhenie-obektov-bez-ispolzovaniya-mashinnogoobucheniya/. — Загл. с экрана.</mixed-citation></ref><ref id="ref17"><mixed-citation publication-type="other" xml:lang="ru">Обработка грамм. изображений в цифровой фотографии. Анализ гисто— Электрон. текстовые дан. — Режим доступа: http://photomagic2007.narod.ru/Stati/analiz_gist/analiz_gist.html. — Загл. с экрана.</mixed-citation></ref><ref id="ref18"><mixed-citation publication-type="other" xml:lang="ru">Орельен, Ж. Прикладное машинное обучение с помощью Scikit-Learn, Keras и TensorFlow: концепции, инструменты и техники для создания интеллектуальных систем / Ж. Орельен. — СПб. : ООО «Диалектика», 2020. — 1040 c.</mixed-citation></ref><ref id="ref19"><mixed-citation publication-type="other" xml:lang="ru">Павельева, Е. А. Обработка и анализ изображений на основе использования информации о фазе / Е. А. Павельева // Компьютерная оптика. — 2018. — Т. 42, № 6. — C. 1022–1034.</mixed-citation></ref><ref id="ref20"><mixed-citation publication-type="other" xml:lang="ru">Половинкин, А. Н. Алгоритмы классификации изображений с большим числом категорий объектов / А. Н. Половинкин // Вестник ННГУ. — 2013. — № 4-1. — C. 225–232.</mixed-citation></ref><ref id="ref21"><mixed-citation publication-type="other" xml:lang="ru">Посохов, И. Методика построения функции принадлежности для классификации изображений на основе гистограмм яркости / И. Посохов, И. С. Логунова. — Электрон. текстовые дан. — Режим доступа: https://ceur-ws.org/Vol-1197/paper20.pdf. — Загл. с экрана.</mixed-citation></ref><ref id="ref22"><mixed-citation publication-type="other" xml:lang="ru">Пухова, Е. А. Оценка гистограммных преобразований в печатном процессе / Е. А. Пухова, Ю. С. Андреев, О. В. Панкин // Известия ТулГУ. Технические науки. — 2018. — № 6. — C. 1–10.</mixed-citation></ref><ref id="ref23"><mixed-citation publication-type="other" xml:lang="ru">Функция cv2.blur() в OpenCV Python. — Электрон. текстовые дан. — Режим доступа: https://tonais.ru/library/funktsiya-cv2-blur-opencv-python. — Загл. с экрана.</mixed-citation></ref><ref id="ref24"><mixed-citation publication-type="other" xml:lang="ru">Шакирьянов, Э. Д. Компьютерное зрение на Python. Первые шаги / Э.Д. Шакирьянов. — Электрон. текстовые дан. — Режим доступа: https://www.litres.ru/get_pdf_trial/63606057.pdf. — Загл. с экрана.</mixed-citation></ref><ref id="ref25"><mixed-citation publication-type="other" xml:lang="ru">Шолле, Ф. Глубокое обучение на Python / Ф. Шолле. — СПб. : Питер, 2018. — 400 c.</mixed-citation></ref><ref id="ref26"><mixed-citation publication-type="other" xml:lang="ru">Элбон, К. Машинное обучение с использованием Python. Сборник рецептов / К. Элбон. — СПб. : БХВ-Петербург, 2019. — 384 c.</mixed-citation></ref><ref id="ref27"><mixed-citation publication-type="other" xml:lang="ru">Ярышев, С. Н. Технологии глубокого обучения и нейронных сетей в задачах видеоанализа / С. Н. Ярышев, В. А. Рыжова. — СПб. : Ун-т ИТМО, 2022. — 82 c.</mixed-citation></ref><ref id="ref28"><mixed-citation publication-type="other" xml:lang="ru">Aykat, S. Deep Learning in Retinal Diseases Diagnosis: A Review / S. Aykat, S. Senan // Machine Learning and AI Techniques in Interactive Medical Image Analysis. — 2023. — P. 34. — DOI: 10.4018/978-1-6684-4671-3.ch001</mixed-citation></ref><ref id="ref29"><mixed-citation publication-type="other" xml:lang="ru">Classification of Fundus Autofluorescence Patterns in Early Age-Related Macular Disease / A. Bindewald, A. C. Bird, S. S. Dandekar, J. Dolar-Szczasny, J. Dreyhaupt, F. W. Fitzke, W. Einbock, F. G. Holz, J. J. Jorzik, C. Keilhauer, N. Lois, J. Mlynski, D. Pauleikhoff, G. Staurenghi, S. Wolf // Investigative Ophthalmology &amp; Visual Science. — 2005. — Vol. 46, № 9. — P. 3309–3314.</mixed-citation></ref><ref id="ref30"><mixed-citation publication-type="other" xml:lang="ru">Detection of Duplicate Images Using Image Hash Functions. — Electronic text data. — Mode of access: https://towardsdatascience.com/detection-of-duplicate-images-using-imagehash-functions-4d9c53f04a75. — Title from screen.</mixed-citation></ref><ref id="ref31"><mixed-citation publication-type="other" xml:lang="ru">FCOS: Fully Convolutional One-Stage Object Detection. — Electronic text data. — Mode of access: https://arxiv.org/abs/1904.01355. — Title from screen.</mixed-citation></ref><ref id="ref32"><mixed-citation publication-type="other" xml:lang="ru">Feature Pyramid Networks for Object Detection. — Electronic text data. — Mode of access: https://arxiv.org/abs/1612.03144. — Title from screen.</mixed-citation></ref><ref id="ref33"><mixed-citation publication-type="other" xml:lang="ru">Histogram Matching. — Electronic text data. — Mode of access: https://scikitimage.org/docs/stable/auto_examples/color_ exposure/plot_histogram_matching.html#sphx-glr-auto-examples-color-exposure-plothistogram-matching-py. — Title from screen.</mixed-citation></ref><ref id="ref34"><mixed-citation publication-type="other" xml:lang="ru">IBM Bets Future on Cognitive Platform Watson. — Electronic text data. — Mode of access: https://koreajoongangdaily.joins.com/news/article/article.aspx?aid=3032651. — Title from screen.</mixed-citation></ref><ref id="ref35"><mixed-citation publication-type="other" xml:lang="ru">IBM’s Watson to Be Used at Korean Hospital. — Electronic text data. — Mode of access: https://www.koreatimes.co.kr/www/tech/2020/03/129_213747.html. — Title from screen.</mixed-citation></ref><ref id="ref36"><mixed-citation publication-type="other" xml:lang="ru">Image Classification from Scratch. — Electronic text data. — Mode of access: https://keras.io/examples/vision/image_classification_from_scratch/. — Title from screen.</mixed-citation></ref><ref id="ref37"><mixed-citation publication-type="other" xml:lang="ru">Image Similarity Assessment. Master’s Thesis. — Electronic text data. — Mode of access: https://dspace5.zcu.cz/bitstream/11025/12532/1/dip_fric_vojtech.pdf. — Title from screen.</mixed-citation></ref><ref id="ref38"><mixed-citation publication-type="other" xml:lang="ru">Jie, Z. Novel Block-DCT and PCA Based Image Perceptual Hashing Algorithm / Z. Jie // IJCSI International Journal of Computer Science Issues. — 2013. — Vol. 10, iss. 1, № 3. — P. 399–403.</mixed-citation></ref><ref id="ref39"><mixed-citation publication-type="other" xml:lang="ru">Kim, H. Exploiting the vulnerability of deep learning-based artificial intelligence models in medical imaging: Adversarial attacks / H. Kim, D. C. Jung, B. W. Choi // Journal of the Korean Society of Radiology. — 2019. — № 80 (2). — P. 259–273. — DOI: 10.3348/jksr.2019.80.2.259</mixed-citation></ref><ref id="ref40"><mixed-citation publication-type="other" xml:lang="ru">MedPy 0.4.0. — Electronic text data. — Mode of access: https://pypi.org/project/MedPy/. — Title from screen.</mixed-citation></ref><ref id="ref41"><mixed-citation publication-type="other" xml:lang="ru">Mutli Label Classification. — Electronic text data. — Mode of access: https://www.kaggle.com/code/mustafa9901/mutli-label-classification. — Title from screen.</mixed-citation></ref><ref id="ref42"><mixed-citation publication-type="other" xml:lang="ru">Retinal Disease Classification. — Electronic text data. — Mode of access: https://www.kaggle.com/datasets/andrewmvd/retinal-disease-classification. — Title from screen.</mixed-citation></ref><ref id="ref43"><mixed-citation publication-type="other" xml:lang="ru">Verma, M. AI and Machine Learning: Supervised Learning Techniques Based on IoMT / M. Verma // The Internet of Medical Things (IoMT) and Telemedicine Frameworks and Applications. — 2023. — P. 177–188. — DOI: 10.4018/978-1-6684-3533-5.ch010</mixed-citation></ref><ref id="ref44"><mixed-citation publication-type="other" xml:lang="en">Baza dannykh: Patologii tsentralnoy oblasti glaznogo dna cheloveka, vyyavlyaemye pri pomoshchi issledovaniya autoflyuorestsentsiey [Database: Pathologies of the Central Area of the Human Fundus Detected by Autofluorescence Examination]. URL: https://notabug.org/Tonypythony/meddb.</mixed-citation></ref><ref id="ref45"><mixed-citation publication-type="other" xml:lang="en">Bobkov A.V. Sistemy raspoznavaniya obrazov: ucheb. posobie [Image Recognition Systems: Tutorial]. Moscow, Izd-vo MGTU im. N.E. Baumana, 2018. 187 p.</mixed-citation></ref><ref id="ref46"><mixed-citation publication-type="other" xml:lang="en">Germashev I.V., Dubovskaya V.I. Primenenie modeley nechetkoy matematiki dlya resheniya zadach meditsinskoy diagnostiki [Application of Fuzzy Mathematics Models for Solving Medical Diagnostics Problems]. Matematicheskaya fizika i kompyuternoe modelirovanie [Mathematical Physics and Computer Modeling], 2021, vol. 24, no. 4, pp. 53-65. DOI: https://doi.org/10.15688/mpcm.jvolsu.2021.4.4</mixed-citation></ref><ref id="ref47"><mixed-citation publication-type="other" xml:lang="en">Gndoyan I.A., Petraevskiy A.V., Dyatchina A.I. Autoflyuorestsentsiya glaznogo dna v diagnostike vozrastnoy makulyarnoy degeneratsii [Fundus Autofluorescence in the Diagnosis of Age-Related Macular Degeneration]. Vestnik oftalmologii, 2020, vol. 136, no. 5, pp. 136-141. DOI: https://doi.org/10.17116/oftalma2020136051136</mixed-citation></ref><ref id="ref48"><mixed-citation publication-type="other" xml:lang="en">Gonsales R., Vuds R. Tsifrovaya obrabotka izobrazheniy [Digital Image Processing]. Moscow, Tekhnosfera Publ., 2005. 1072 p.</mixed-citation></ref><ref id="ref49"><mixed-citation publication-type="other" xml:lang="en">Dzheremi Kh., Silveyn G. Glubokoe obuchenie s fastai i PyTorch: minimum formul, minimum koda, maksimum effektivnosti [Deep Learning for Coders with Fastai and PyTorch: AI Applications Without a PhD]. Saint Petersburg, Piter Publ., 2022. 624 p.</mixed-citation></ref><ref id="ref50"><mixed-citation publication-type="other" xml:lang="en">Ilyasova N.Yu., Shirokanyov A.S., Klimov I.A. Primenenie svyortochnykh neyronnykh setey dlya analiza izobrazheniy glaznogo dna [Application of Convolutional Neural Networks for the Analysis of Fundus Images]. Sbornik trudov ITNT-2019, 2019, vol. 4, pp. 111-118.</mixed-citation></ref><ref id="ref51"><mixed-citation publication-type="other" xml:lang="en">Ispolzovanie programmy IBM WATSON v lechenii onkologicheskikh zabolevaniy v Yuzhnoy Koree [Using the IBM WATSON Program in the Treatment of Cancer in South Korea]. URL: https://medical-express.ru/branches/oncologiya/ibm-watson-v-medicine.</mixed-citation></ref><ref id="ref52"><mixed-citation publication-type="other" xml:lang="en">Klassifikator fotoizobrazheniy AF glaznogo dna [Classifier of AF Images of the Fundus]. URL: https://github.com/Antoniii/humashineye.</mixed-citation></ref><ref id="ref53"><mixed-citation publication-type="other" xml:lang="en">Kreyman G. Biologicheskoe i kompyuternoe zrenie [Biological and Computer Vision]. Moscow, DMK Press Publ., 2022. 314 p.</mixed-citation></ref><ref id="ref54"><mixed-citation publication-type="other" xml:lang="en">Loginov V.N., Shchipanov K.A., Lavrov V.V. Razrabotka web-prilozheniya sistemy identifikatsii defektov metalla na polutonovykh izobrazheniyakh s ispolzovaniem kaskadnogo klassifikatora Khaara na platforme Asp .Net Core MVC [Development of a Web Application for the Identification of Metal Defects on Halftone Images Using the Cascade Haar Classifier on the Asp Platform .Net Core MVC]. Vestnik Cherepovetskogo gosudarstvennogo universiteta [Bulletin of Cherepovets State University], 2019, no. 4, pp. 8-22.</mixed-citation></ref><ref id="ref55"><mixed-citation publication-type="other" xml:lang="en">Losev A.G., Levshinskiy V.V. Intellektualnyy analiz dannykh mikrovolnovoy radiotermometrii v diagnostike raka molochnoy zhelezy [Intelligent Analysis of Microwave Radiothermometry Data in the Diagnosis of Breast Cancer]. Matematicheskaya fizika i kompyuternoe modelirovanie [Mathematical Physics and Computer Modeling], 2017, no. 5 (342), pp. 16-22. DOI: https://doi.org/10.15688/mpcm.jvolsu.2017.5.6</mixed-citation></ref><ref id="ref56"><mixed-citation publication-type="other" xml:lang="en">Loshmanov V.I., Kravets A.G. Razrabotka i validatsiya metoda klassifikatsii oftalmologicheskoy patologii s primeneniem glubokogo mashinnogo obucheniya [Development and Validation of the Method of Classification of Ophthalmic Pathology Using Deep Machine Learning]. Vestnik Astrakhanskogo gosudarstvennogo tekhnicheskogo universiteta. Seriya: Upravlenie, vychislitelnaya tekhnika i informatika [Bulletin of the Astrakhan State Technical University. Series: Management, Computer Engineering and Computer Science], 2021, no. 2, pp. 57-65. DOI: 10.24143/2072-9502-2021-2-57-65</mixed-citation></ref><ref id="ref57"><mixed-citation publication-type="other" xml:lang="en">Dyudin M.V., Povalyaev A.D., Podvalnyy E.S., Tomakova R.A. Metody i algoritmy konturnogo analiza dlya zadach klassifikatsii slozhnostrukturiruemykh izobrazheniy [Methods and Algorithms of the Contour Analysis for Problems of the Categorizations Complex-Structured Images]. Vestnik VGTU [Bulletin of VSTU], 2014, vol. 10, no. 3–1, pp. 54-59.</mixed-citation></ref><ref id="ref58"><mixed-citation publication-type="other" xml:lang="en">Molodyakov S.A. Primenenie funktsiy OpenCV v kompyuternom zrenii (60 primerov na Python) [Application of OpenCV Functions in Computer Vision (60 Python Examples)]. Saint Petersburg, Izd-vo Politekhn. un-ta Publ., 2022. 296 p.</mixed-citation></ref><ref id="ref59"><mixed-citation publication-type="other" xml:lang="en">Obnaruzhenie obyektov bez mashinnogo obucheniya [Object Detection Without Using Machine Learning]. URL: https://newtechaudit.ru/obnaruzhenie-obektov-bez-ispolzovaniyamashinnogo-obucheniya/. in Digital</mixed-citation></ref><ref id="ref60"><mixed-citation publication-type="other" xml:lang="en">Obrabotka izobrazheniy v tsifrovoy fotografii. Analiz gistogramm [Image Processing Photography. Histogram Analysis]. URL: http://photomagic2007.narod.ru/Stati/analiz_gist/analiz_gist.html.</mixed-citation></ref><ref id="ref61"><mixed-citation publication-type="other" xml:lang="en">Orelyen Zh. Prikladnoe mashinnoe obuchenie s pomoshchyu Scikit-Learn, Keras i TensorFlow: kontseptsii, instrumenty i tekhniki dlya sozdaniya intellektualnykh sistem [Applied Machine Learning Using Scikit-Learn, Kurs and TensorFlow: Concepts, Tools and Techniques for Creating Intelligent Systems]. Saint Petersburg, OOO «Dialektika» Publ., 2020. 1040 p.</mixed-citation></ref><ref id="ref62"><mixed-citation publication-type="other" xml:lang="en">Pavelyeva E.A. Obrabotka i analiz izobrazheniy na osnove ispolzovaniya informatsii o faze [Processing and Analysis of Images Based on the Use of Phase Information]. Kompyuternaya optika [Computer optics], 2018, vol. 42, no. 6, pp. 1022-1034.</mixed-citation></ref><ref id="ref63"><mixed-citation publication-type="other" xml:lang="en">Polovinkin A.N. Algoritmy klassifikatsii izobrazheniy s bolshim chislom kategoriy obyektov [Algorithms for Classifying Images with a Large Number of Object Categories]. Vestnik NNGU [Bulletin of the UNN], 2013, no. 4-1, pp. 225-232.</mixed-citation></ref><ref id="ref64"><mixed-citation publication-type="other" xml:lang="en">Posokhov I., Logunova I.S. Metodika postroeniya funktsii prinadlezhnosti dlya klassifikatsii izobrazheniy na osnove gistogramm yarkosti [Methodology for Constructing the Membership Function for Classifying Images Based on Brightness Histograms]. URL: https://ceur-ws.org/Vol-1197/paper20.pdf.</mixed-citation></ref><ref id="ref65"><mixed-citation publication-type="other" xml:lang="en">Pukhova E.A., Andreev Yu.S., Pankin O.V. Otsenka gistogrammnykh preobrazovaniy v pechatnom protsesse [Evaluation of Histogram Transformations in the Printing Process]. Izvestiya TulGU. Tekhnicheskie nauki [News of TulSU. Technical Sciences], 2018, no. 6, pp. 1-10.</mixed-citation></ref><ref id="ref66"><mixed-citation publication-type="other" xml:lang="en">Funktsiya cv2.blur() v OpenCV Python [Cv2.blur() Function in OpenCV Python]. URL: https://tonais.ru/library/funktsiya-cv2-blur-opencv-python.</mixed-citation></ref><ref id="ref67"><mixed-citation publication-type="other" xml:lang="en">Shakiryanov E.D. Kompyuternoe zrenie na Python. Pervye shagi [Computer Vision in Python. First Steps]. URL: https://www.litres.ru/get_pdf_trial/63606057.pdf.</mixed-citation></ref><ref id="ref68"><mixed-citation publication-type="other" xml:lang="en">Sholle F. Glubokoe obuchenie na Python [Deep Learning with Python]. Saint Petersburg, Piter Publ., 2018. 400 p.</mixed-citation></ref><ref id="ref69"><mixed-citation publication-type="other" xml:lang="en">Elbon K. Mashinnoe obuchenie s ispolzovaniem Python. Sbornik retseptov [Machine Learning Using Python. Basic Collection]. Saint Petersburg, BKhV-Peterburg Publ., 2019. 384 p.</mixed-citation></ref><ref id="ref70"><mixed-citation publication-type="other" xml:lang="en">Yaryshev S.N., Ryzhova V.A. Tekhnologii glubokogo obucheniya i neyronnykh setey v zadachakh videoanaliza [Technologies of Deep Learning and Neural Networks in Video Analysis Tasks]. Saint Petersburg, Un-t ITMO Publ., 2022. 82 p.</mixed-citation></ref><ref id="ref71"><mixed-citation publication-type="other" xml:lang="en">Aykat S., Senan S. Deep Learning in Retinal Diseases Diagnosis: A Review. Machine Learning and AI Techniques in Interactive Medical Image Analysis, 2023, pp. 34. DOI: 10.4018/978-1-6684-4671-3.ch001</mixed-citation></ref><ref id="ref72"><mixed-citation publication-type="other" xml:lang="en">Bindewald A., Bird A.C., Dandekar S.S., Dolar-Szczasny J., Dreyhaupt J., Fitzke F.W., Einbock W., Holz F.G., Jorzik J.J., Keilhauer C., Lois N., Mlynski J., Pauleikhoff D., Staurenghi G., Wolf S. Classification of Fundus Autofluorescence Patterns in Early Age-Related Macular Disease. Investigative Ophthalmology &amp; Visual Science, 2005, vol. 46, no. 9, pp. 3309-3314.</mixed-citation></ref><ref id="ref73"><mixed-citation publication-type="other" xml:lang="en">Detection of Duplicate Images Using Image Hash Functions. URL: https://towardsdatascience.com/detection-of-duplicate-images-using-image-hash-functions4d9c53f04a75.</mixed-citation></ref><ref id="ref74"><mixed-citation publication-type="other" xml:lang="en">FCOS: Fully Convolutional https://arxiv.org/abs/1904.01355.</mixed-citation></ref><ref id="ref75"><mixed-citation publication-type="other" xml:lang="en">Feature Pyramid https://arxiv.org/abs/1612.03144. Networks One-Stage for Object Object Detection. Detection. URL: URL:</mixed-citation></ref><ref id="ref76"><mixed-citation publication-type="other" xml:lang="en">Histogram Matching. URL: https://scikit-image.org/docs/stable/auto_examples/color_ exposure/plot_histogram_matching.html#sphx-glr-auto-examples-color-exposure-plothistogram-matching-py.</mixed-citation></ref><ref id="ref77"><mixed-citation publication-type="other" xml:lang="en">IBM Bets Future on Cognitive Platform Watson. https://koreajoongangdaily.joins.com/news/article/article.aspx?aid=3032651.</mixed-citation></ref><ref id="ref78"><mixed-citation publication-type="other" xml:lang="en">IBM’s Watson to Be Used at Korean https://www.koreatimes.co.kr/www/tech/2020/03/129_213747.html. Hospital. URL: URL:</mixed-citation></ref><ref id="ref79"><mixed-citation publication-type="other" xml:lang="en">Image Classification from Scratch. URL: https://keras.io/examples/vision/image_classification_from_scratch/.</mixed-citation></ref><ref id="ref80"><mixed-citation publication-type="other" xml:lang="en">Image Similarity Assessment. Master’s https://dspace5.zcu.cz/bitstream/11025/12532/1/dip_fric_vojtech.pdf. Thesis. URL:</mixed-citation></ref><ref id="ref81"><mixed-citation publication-type="other" xml:lang="en">Jie Z. Novel Block-DCT and PCA Based Image Perceptual Hashing Algorithm. IJCSI International Journal of Computer Science Issues, 2013, vol. 10, iss. 1, no. 3, pp. 399-403.</mixed-citation></ref><ref id="ref82"><mixed-citation publication-type="other" xml:lang="en">Kim H., Jung D.C., Choi B.W. Exploiting the Vulnerability of Deep Learning-Based Artificial Intelligence Models in Medical Imaging: Adversarial Attacks. Journal of the Korean Society of Radiology, 2019, no. 80 (2), pp. 259-273. DOI: 10.3348/jksr.2019.80.2.259</mixed-citation></ref><ref id="ref83"><mixed-citation publication-type="other" xml:lang="en">MedPy 0.4.0. URL: https://pypi.org/project/MedPy/.</mixed-citation></ref><ref id="ref84"><mixed-citation publication-type="other" xml:lang="en">Mutli Label Classification. URL: https://www.kaggle.com/code/mustafa9901/mutlilabel-classification.</mixed-citation></ref><ref id="ref85"><mixed-citation publication-type="other" xml:lang="en">Retinal Disease Classification. URL: https://www.kaggle.com/datasets/andrewmvd/retinal-disease-classification.</mixed-citation></ref><ref id="ref86"><mixed-citation publication-type="other" xml:lang="en">Verma M. AI and Machine Learning: Supervised Learning Techniques Based on IoMT. The Internet of Medical Things (IoMT) and Telemedicine Frameworks and Applications, 2023, pp. 177-188. DOI: 10.4018/978-1-6684-3533-5.ch010 46</mixed-citation></ref></ref-list></back></article>
