<?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">isplta</journal-id><journal-title-group><journal-title xml:lang="ru">Известия Санкт-Петербургской лесотехнической академии</journal-title><trans-title-group xml:lang="en"><trans-title>Izvestia Sankt-Peterburgskoj lesotehniceskoj akademii</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2079-4304</issn><issn pub-type="epub">2658-5871</issn><publisher><publisher-name>СПбГЛТУ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21266/2079-4304.2025.255.375-389</article-id><article-id custom-type="elpub" pub-id-type="custom">isplta-610</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>ДРЕВЕСИНОВЕДЕНИЕ, ТЕХНОЛОГИЯ И ОБОРУДОВАНИЕ ДЕРЕВОПЕРЕРАБОТКИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>WOOD SCIENCE. MECHANICAL WOODWORKING INDUSTRY</subject></subj-group></article-categories><title-group><article-title>Разработка модели глубокого обучения для распознавания коры древесины на снимке поперечного распила</article-title><trans-title-group xml:lang="en"><trans-title>Developing a deep learning model for recognizing wood bark in a cross-section image</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>Богомолов</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Bogomolov</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Богомолов Александр Алексеевич – учебный мастер кафедры автоматизации, метрологии и управления в технических системах</p><p>194021, Институтский пер., д. 5, лит. У, Санкт-Петербург</p></bio><bio xml:lang="en"><p>Bogomolov Aleksandr A. – engineer of the Department of Automation, Metrology and Management in Technical Systems</p><p>194021. Institute per. 5. St. Petersburg</p></bio><email xlink:type="simple">setalx@mail.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>Молодых</surname><given-names>Е. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Molodykh</surname><given-names>E. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Молодых Елизавета Игоревна – аспирант кафедры автоматизации, метрологии и управления в технических системах</p><p>194021, Институтский пер., д. 5, лит. У, Санкт-Петербург</p></bio><bio xml:lang="en"><p>Molodykh Elizaveta I. – PhD student of the Department of Automation, Metrology and Management in Technical Systems</p><p>194021. Institute per. 5. St. Petersburg</p></bio><email xlink:type="simple">mmu49@mail.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>Галкина</surname><given-names>Е. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Galkina</surname><given-names>E. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Галкина Екатерина Анатольевна – старший преподаватель кафедры техносферной безопасности </p><p>190005, ул. 2-я Красноармейская, д. 4, Санкт-Петербург</p></bio><bio xml:lang="en"><p>Galkina Ekaterina A. – Senior Lecturer, Department of Technosphere Safety</p><p>190005, 2nd Krasnoarmeyskaya str. 4. St. Petersburg</p></bio><email xlink:type="simple">galo4enok@yandex.ru</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-8542-9380</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Куницкая</surname><given-names>О. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Kunitskaia</surname><given-names>O. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Куницкая Ольга Анатольевна – профессор кафедры «Технология и оборудование лесного комплекса», доктор технических наук</p><p>677007, 3-й км Сергеляхского ш., д. 3, г. Якутск</p></bio><bio xml:lang="en"><p>Kunitskaia Olga A. – DSc (Technical), Professor of Department of Forestry Technology and Equipment</p><p>577007, 3rd km of Sergelyakhskoe highway 3. Yakutsk</p></bio><email xlink:type="simple">ola.ola07@mail.ru</email><xref ref-type="aff" rid="aff-3"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Хохлов</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Khokhlov</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Хохлов Артём Анатольевич – соискатель кафедры «Технология и оборудование лесного комплекса»</p><p>677007, 3-й км Сергеляхского ш., д. 3, г. Якутск</p></bio><bio xml:lang="en"><p>Khokhlov Artem A. – applicant in the Department of Forestry Technology and Equipment</p><p>577007, 3rd km of Sergelyakhskoe highway 3. Yakutsk</p></bio><email xlink:type="simple">T.igorevna123@yandex.ru</email><xref ref-type="aff" rid="aff-3"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Пушков</surname><given-names>Ю. Л.</given-names></name><name name-style="western" xml:lang="en"><surname>Pushkov</surname><given-names>Y. L.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Пушков Юрий Леонидович – доцент кафедры лесного машиностроения, сервиса и ремонта, кандидат технических наук</p><p>194021, Институтский пер., д. 5, лит. У, Санкт-Петербург</p></bio><bio xml:lang="en"><p>Pushkov Yuriy L. – PhD (Technical), Associate Professor of the Department of Forestry Engineering, Service and Repair</p><p>194021. Institute per. 5. St. Petersburg</p></bio><email xlink:type="simple">PushkovYL@spbftu.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>Горюнов</surname><given-names>Н. Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Goryunov</surname><given-names>N. D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Горюнов Никита Дмитриевич – студент</p><p>194021, Институтский пер., д. 5, лит. У, Санкт-Петербург</p><p> </p></bio><bio xml:lang="en"><p>Goryunov Nikita D. – student </p><p>194021. Institute per. 5. St. Petersburg</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1035-9231</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Андронов</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Andronov</surname><given-names>A. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Андронов Александр Вячеславович – доцент кафедры лесного машиностроения, сервиса и ремонта, доктор технических наук</p><p>194021, Институтский пер., д. 5, лит. У, Санкт-Петербург</p></bio><bio xml:lang="en"><p>Andronov Aleksandr V. – DSc (Technical), Associate Professor of the Department of Forestry Machinery, Service and Repair</p><p>194021. Institute per. 5. St. Petersburg</p></bio><email xlink:type="simple">andronovalexandr@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-4569-9508</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Хитров</surname><given-names>Е. Г.</given-names></name><name name-style="western" xml:lang="en"><surname>Khitrov</surname><given-names>E. G.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Хитров Егор Германович – доцент </p><p>195251, ул. Политехническая, д. 29, Санкт-Петербург</p><p> </p></bio><bio xml:lang="en"><p>Khitrov Egor G. – DSc (Technical), Associate Professor of the Higher School of Software Engineering of Peter the Great, Associate Professor</p><p>195251, Politekhnicheskaya str. 29. St. Petersburg</p></bio><email xlink:type="simple">hitrov_eg@spbstu.ru</email><xref ref-type="aff" rid="aff-4"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский государственный лесотехнический университет имени С.М. Кирова</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Saint Petersburg State Forest Technical University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Санкт-Петербургский государственный архитектурно-строительного университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Saint Petersburg State University of Architecture and Civil Engineering</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru"><institution>Арктический государственный агротехнологический университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Arctic State Agrotechnological University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-4"><aff xml:lang="ru"><institution>Санкт-Петербургский политехнический университет Петра Великого</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Great St. Petersburg Polytechnic University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>13</day><month>12</month><year>2025</year></pub-date><volume>0</volume><issue>255</issue><fpage>375</fpage><lpage>389</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Богомолов А.А., Молодых Е.И., Галкина Е.А., Куницкая О.А., Хохлов А.А., Пушков Ю.Л., Горюнов Н.Д., Андронов А.В., Хитров Е.Г., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Богомолов А.А., Молодых Е.И., Галкина Е.А., Куницкая О.А., Хохлов А.А., Пушков Ю.Л., Горюнов Н.Д., Андронов А.В., Хитров Е.Г.</copyright-holder><copyright-holder xml:lang="en">Bogomolov A.A., Molodykh E.I., Galkina E.A., Kunitskaia O.A., Khokhlov A.A., Pushkov Y.L., Goryunov N.D., Andronov A.V., Khitrov E.G.</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://izvestiya-lta.spbftu.ru/jour/article/view/610">https://izvestiya-lta.spbftu.ru/jour/article/view/610</self-uri><abstract><p>Целью исследования является разработка и апробация архитектуры модели глубокого обучения на основе сверточной искусственной нейронной сети для определения доли коры на цифровом снимке поперечного распила древесины. Результаты работы получены с использованием методов технического зрения и глубокого обучения. При разработке архитектуры модели использована справочная документация искусственных нейронных сетей Faster R-CNN, RPN, Mask R-CNN, Segment Anything. При программной реализации модели в исследовательских целях использованы модели искусственных нейронных сетей с открытым исходным кодом Mask R-CNN и Segment Anything (модель Mask R-CNN была интегрирована в общий стек с моделью Segment Anything (SAM), а функции генерации карты признаков переданы блоку Encoder; блоки memory attention сети SAM были удалены для оптимизации решения в плане требуемого объема оперативной памяти). Обучение и валидация модели проведены с использованием авторского набора цифровых снимков поперечных распилов лесоматериалов, доступного в репозитории. Измеренные значения метрики точности Precision при валидации показывают, что предлагаемая архитектура модели глубокого обучения позволяет успешно решать задачу сегментации и определения доли коры на снимках. Результаты экспериментов с информационной моделью глубокого обучения позволяют оценить связь ее архитектуры и числа обучаемых параметров с результатами определения доли коры на снимках сортиментов: при переходе от модели с числом весов 38 млн до модели с 217 млн весов отмечается стабилизация метрики Precision. В связи с этим целесообразно выполнить дальнейшие исследования по поиску оптимального числа обучаемых параметров, обеспечивающего наилучшее сочетание точности и скорости обработки снимков.</p></abstract><trans-abstract xml:lang="en"><p>The aim of this study is to develop and validate a deep learning model architecture based on a convolutional artificial neural network for determining the proportion of bark in a digital image of cross-cut timber. The results were obtained using computer vision and deep learning methods. Reference documentation for the Faster R-CNN, RPN, Mask R-CNN, and Segment Anything artificial neural networks was used in developing the model architecture. The open-source Mask R-CNN and Segment Anything artificial neural network models were used in the software implementation of the model for research purposes (the Mask R-CNN model was integrated into a common stack with the Segment Anything (SAM) model, and the feature map generation functions were transferred to the Encoder block; the memory attention blocks of the SAM network were removed to optimize the solution in terms of the required amount of RAM). The model was trained and validated using the author's dataset of digital images of cross-cut timber, available in the repository. The measured Precision metric values during validation demonstrate that the proposed deep learning model architecture successfully solves the problem of segmentation and bark fraction determination in images. Experiments with the deep learning model allow us to evaluate the relationship between its architecture and the number of trainable parameters with the results of bark fraction determination in assortment images: stabilization of the Precision metric is observed when moving from a model with 38 million weights to a model with 217 million weights. Therefore, further research is warranted to determine the optimal number of trainable parameters that provides the best balance of accuracy and image processing performance.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>круглые лесоматериалы</kwd><kwd>сегментация изображения</kwd><kwd>фреймворк Pytorch</kwd><kwd>сверточные ИНС</kwd></kwd-group><kwd-group xml:lang="en"><kwd>round timber</kwd><kwd>image segmentation</kwd><kwd>Pytorch framework</kwd><kwd>convolutional neural networks</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Исследование выполнено за счет гранта Российского научного фонда № 23-16-00092</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Беляев Н.Л. Повышение точности цифрового учёта круглых лесоматериалов: дис. … канд. техн. наук. Петрозаводск: ПетрГУ, 2023. 163 с.</mixed-citation><mixed-citation xml:lang="en">Beliaev N.L. Povyshenie tochnosti tsifrovogo ucheta kruglykh lesomaterialov: Diss. … Cand. Tech. Sci. Petrozavodsk: PetrGU, 2023. 163 p. (In Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Инструменты библиотеки OPENCV для выявления коры на торцевом снимке поперечного спила дерева. URL: https://clck.ru/3Es7QJ (дата обращения: 01.02.2025).</mixed-citation><mixed-citation xml:lang="en">The Faster R-CNN model is based on the Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks paper. URL: clck.ru/3PpfEE (accessed February 01, 2025).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">The Faster R-CNN model is based on the Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks paper. URL: clck.ru/3PpfEE (дата обращения: 01.02.2025).</mixed-citation><mixed-citation xml:lang="en">Han S., Jiang X., Wu Z. An Improved YOLOv5 Algorithm for Wood Defect Detection Based on Attention. IEEE Access, 2023, vol. 11, pp. 71800–71810. DOI: 10.1109/ACCESS.2023.3293864</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Han S., Jiang X., Wu Z. An Improved YOLOv5 Algorithm for Wood Defect Detection Based on Attention // IEEE Access. 2023. Vol. 11. P. 71800-71810. DOI: 10.1109/ACCESS.2023.3293864</mixed-citation><mixed-citation xml:lang="en">Kim T.K., Hong J., Ryu D., Kim S., Byeon S.Y., Huh W., Kim K., Baek G.H., Kim H.S. Identifying and extracting bark key features of 42 tree species using convolutional neural networks and class activation mapping. Scientific Reports, 2022, vol. 12, art. no. 4772. DOI: 10.1038/s41598-022-08571-9.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Kim T.K., Hong J., Ryu D., Kim S., Byeon S.Y., Huh W., Kim K., Baek G.H., Kim H.S. Identifying and extracting bark key features of 42 tree species using convolutional neural networks and class activation mapping // Scientific Reports. 2022. Vol. 12. Art. no. 4772. DOI: 10.1038/s41598-022-08571-9.</mixed-citation><mixed-citation xml:lang="en">Kunickaya O., Pomiguev A., Kruchinin I., Storodubtseva T., Voronova A., Levushkin D., Borisov V., Ivanov V. Analysis of modern wood processing techniques in timber terminals. Central European Forestry Journal, 2022, vol. 68(1), pp. 51–59.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Kunickaya O., Pomiguev A., Kruchinin I., Storodubtseva T., Voronova A., Levushkin D., Borisov V., Ivanov V. Analysis of modern wood processing techniques in timber terminals // Central European Forestry Journal. 2022. Vol. 68(1). P. 51–59.</mixed-citation><mixed-citation xml:lang="en">OPENCV library tools for identifying bark on a cross-sectional image of a tree. – URL: https://clck.ru/3Es7QJ (accessed February 01, 2025).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Region Proposal Network (RPN): A Complete Guide. URL: clck.ru/3PpfF3 (дата обращения: 01.02.2025).</mixed-citation><mixed-citation xml:lang="en">Region Proposal Network (RPN): A Complete Guide. URL: clck.ru/3PpfF3 (accessed February 01, 2025).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Robert M., Dallaire P., Giguère Ph. Tree bark re-identification using a deeplearning feature descriptor // 17th Conference on Computer and Robot Vision (CRV). 2020. P. 25–32. DOI: 10.1109/CRV50864.2020.00012.</mixed-citation><mixed-citation xml:lang="en">Robert M., Dallaire P., Giguère Ph. Tree bark rеidentification using a deep- learning feature descriptor. 17th Conference on Computer and Robot Vision (CRV). 2020, pp. 25–32. DOI: 10.1109/CRV50864.2020.00012.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Wang R., Chen Y., Liang F., Wang B., Mou X., Zhang G. BPN-YOLO: A Novel Method for Wood Defect Detection Based on YOLOv7 // Forests. 2024. Vol. 15(7). Art. no. 1096. DOI: 10.3390/f15071096.</mixed-citation><mixed-citation xml:lang="en">Wang R., Chen Y., Liang F., Wang B., Mou X., Zhang G. BPN-YOLO: A Novel Method for Wood Defect Detection Based on YOLOv7. Forests, 2024, vol. 15(7), art. no. 1096. DOI: 10.3390/f15071096.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">What is Mask R-CNN and how does it work? URL: clck.ru/3PpfGp (дата обращения: 01.02.2025).</mixed-citation><mixed-citation xml:lang="en">What is Mask R-CNN and how does it work? URL: clck.ru/3PpfGp (accessed February 01, 2025).</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>
