<?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">pribor</journal-id><journal-title-group><journal-title xml:lang="ru">Известия высших учебных заведений. Приборостроение</journal-title><trans-title-group xml:lang="en"><trans-title>Journal of Instrument Engineering</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">0021-3454</issn><issn pub-type="epub">2500-0381</issn><publisher><publisher-name>Национальный исследовательский университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/0021-3454-2024-67-9-767-775</article-id><article-id custom-type="elpub" pub-id-type="custom">pribor-69</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>СИСТЕМНЫЙ АНАЛИЗ, УПРАВЛЕНИЕ И ОБРАБОТКА ИНФОРМАЦИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>SYSTEM ANALYSIS, MANAGEMENT AND INFORMATION PROCESSING</subject></subj-group></article-categories><title-group><article-title>Распознавание рукописного текста исторических документов с применением технологий глубоких нейронных сетей</article-title><trans-title-group xml:lang="en"><trans-title>Text Recognition of Historical Documents Using Deep Neural Network Technologies</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>Унтерберг</surname><given-names>А. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Unterberg</surname><given-names>A. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Александр Максимович Унтерберг, студент</p><p>Институт космических и информационных технологий,;кафедра систем искусственного интеллекта</p><p>Красноярск</p></bio><bio xml:lang="en"><p>Aleksander M. Unterberg, Student</p><p>Institute of Space and Information Technologies; Department of Artificial Intelligence Systems</p><p>Krasnoyarsk</p></bio><email xlink:type="simple">unterberg2012@gmail.com</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>Пятаева</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Pyataeva</surname><given-names>A. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Анна Владимировна Пятаева, канд. техн. наук, доцент, руководитель лаборатории</p><p>Институт космических и информационных технологий; кафедра систем искусственного интеллекта; научно-учебная лаборатория системискусственного интеллекта</p><p>Красноярск</p></bio><bio xml:lang="en"><p>Anna V. Pyataeva, PhD, Associate Professor, Head of the laboratory</p><p>Institute of Space and Information Technologies; Department of Artificial Intelligence Systems; scientific and educational laboratory of artificial intelligence systems</p><p>Krasnoyarsk</p></bio><email xlink:type="simple">anna4u@list.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>Замыслова</surname><given-names>С. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Zamyslova</surname><given-names>S. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Светлана Сергеевна Замыслова, студентка</p><p>Институт космических и информационных технологий; кафедра систем искусственного интеллекта</p><p>Красноярск</p></bio><bio xml:lang="en"><p>Svetlana S. Zamyslova, Student</p><p>Institute of Space and Information Technologies; Department of Artificial Intelligence Systems</p><p>Krasnoyarsk</p></bio><email xlink:type="simple">zamyslova_svetlana_17-05@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>Рукосуева</surname><given-names>Е. Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Rukosueva</surname><given-names>E. D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Екатерина Дмитриевна Рукосуева, студентка</p><p>Институт космических и информационных технологий; кафедра систем искусственного интеллекта</p><p>Красноярск</p></bio><bio xml:lang="en"><p>Ekaterina D. Rukosueva, Student</p><p>Institute of Space and Information Technologies; Department of Artificial Intelligence Systems</p><p>Krasnoyarsk</p></bio><email xlink:type="simple">rukosuevakatya@gmail.com</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>Богданов</surname><given-names>К. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Bogdanov</surname><given-names>K. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Константин Валерьевич Богданов, канд. техн. наук, доцент</p><p>Институт космических и информационных технологий; кафедра программной инженерии</p><p>Красноярск</p></bio><bio xml:lang="en"><p>Konstantin V. Bogdanov, PhD, Associate Professor</p><p>Institute of Space and Information Technologies; Department of Software Engineering</p><p>Krasnoyarsk</p></bio><email xlink:type="simple">kbogdanov@sfu-kras.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Сибирский федеральный университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Siberian Federal University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>26</day><month>11</month><year>2024</year></pub-date><volume>67</volume><issue>9</issue><fpage>767</fpage><lpage>775</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Национальный исследовательский университет ИТМО, 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Национальный исследовательский университет ИТМО</copyright-holder><copyright-holder xml:lang="en">Национальный исследовательский университет ИТМО</copyright-holder><license xlink:href="https://pribor.ifmo.ru/jour/about/submissions#copyrightNotice" xlink:type="simple"><license-p>https://pribor.ifmo.ru/jour/about/submissions#copyrightNotice</license-p></license></permissions><self-uri xlink:href="https://pribor.ifmo.ru/jour/article/view/69">https://pribor.ifmo.ru/jour/article/view/69</self-uri><abstract><p>   Рассматривается задача распознавания рукописного текста на дореформенном русском языке с применением технологий глубоких нейронных сетей. В качестве исходных данных использованы отсканированные JPG-снимки исторических документов, в частности XIX века, содержащие различные шумы и помехи, что затрудняет работу алгоритма распознавания. Распознавание текста выполнено в три этапа: устранение шумов, сегментация (выделение) строк текста на изображении, так как входными данными для работы глубокой нейронной сети являются именно строки, и затем распознавание текста выделенных срок с помощью дообученной модели Tesseract OCR, осуществляющей электронный перевод изображений рукописного или печатного текста в текстовые данные. В качестве модели использована сверточно-рекуррентная нейронная сеть; модель представляет собой комбинацию сверточной нейронной сети для извлечения локальных признаков из изображения и рекуррентной нейронной сети, представленной двумя слоями двунаправленных сетей LSTM для обработки последовательности. Использование именно такой модели позволяет достоверно распознавать рукописный текст.</p></abstract><trans-abstract xml:lang="en"><p>   The application of deep neural network technologies to the problem of handwriting recognition in pre-reform Russian is considered. The initial data used are scanned JPG images of historical documents from the 19th century, in particular containing various noises and interference, which complicates the work of the recognition algorithm. Text recognition is performed in three stages: noise removal, segmentation (highlighting) of text lines in the image, since the input data for the deep neural network are precisely the lines, and then recognition of the text of the highlighted lines using the pre-trained Tesseract OCR model, which performs electronic translation of images of handwritten or printed text into text data. The model used is a convolutional recurrent neural network; the model is a combination of a convolutional neural network for extracting local features from an image and a recurrent neural network represented by two layers of bidirectional LSTM networks for processing the sequence. Using this model allows for reliable recognition of handwritten text.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>нейронные сети</kwd><kwd>обработка естественного языка</kwd><kwd>исторические документы</kwd><kwd>глубокое обучение</kwd><kwd>библиотека Tesseract OCR</kwd></kwd-group><kwd-group xml:lang="en"><kwd>neural networks</kwd><kwd>natural language processing</kwd><kwd>historical documents</kwd><kwd>deep learning</kwd><kwd>Tesseract — OCR Library</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">Carbonell M., Fornés A., Villegas M., Lladós J. A neural model for text localization, transcription and named entity recognition in full pages // Pattern Recognition Letters. 2020. Vol. 136. P. 219–227. DOI: 10.1016/j.patrec.2020.05.001.</mixed-citation><mixed-citation xml:lang="en">Carbonell M., Fornés A., Villegas M., Lladós J. Pattern Recognition Letters, 2020, vol. 136, рр. 219–227, DOI: 10.1016/j.patrec.2020.05.001.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Mestha P., Asif S., Mayekar M. Handwritten Text Line Recognition Using Deep Learning // Lecture Notes in Networks and Systems. 2022. P. 567–580. DOI: 10.1007/978-3-030-84760-9_48.</mixed-citation><mixed-citation xml:lang="en">Mestha P., Asif S., Mayekar M. Lecture Notes in Networks and Systems, 2022, рр. 567–580, DOI: 10.1007/978-3-030-84760-9_48.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Souibgui M. A., Fornes A., Kessentini Y., Megyesi B. Few shots are all you need: A progressive learning approach for low resource handwritten text recognition // Pattern Recognition Letters. 2022. Vol. 160. P. 43–49. DOI: 10.1016/j.patrec.2022.06.003.</mixed-citation><mixed-citation xml:lang="en">Souibgui M.A., Fornes A., Kessentini Y., Megyesi B. Pattern Recognition Letters, 2022, vol. 160, рр. 43–49, DOI: 10.1016/j.patrec.2022.06.003.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Kang L., Riba P., Rusinol M., Fornes A., Villegas M. Pay attention to what you read: Non-recurrent handwritten text-Line recognition //Pattern Recognition. 2022. Vol. 129. P. 108766. DOI: 10.1016/j.patcog.2022.108766.</mixed-citation><mixed-citation xml:lang="en">Kang L., Riba P., Rusinol M., Fornes A., Villegas M. Pattern Recognition, 2022, vol. 129, art. no. 108766, DOI: 10.1016/j.patcog.2022.108766.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Gonwirat S., Surinta O. CycleAugment: Efficient data augmentation strategy for handwritten text recognition in historical document images // Engineering and Applied Science Research. 2022. Vol. 49, N. 4 P. 505–520. DOI: 10.14456/easr.2022.50.</mixed-citation><mixed-citation xml:lang="en">Gonwirat S., Surinta O. Engineering and Applied Science Research, 2022, no. 4(49), pp. рр. 505–520, DOI: 10.14456/easr.2022.50.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Aradillas J., Murillo-Fuentes J., Olmos P. Boosting Offline Handwritten Text Recognition in Historical Documents with Few Labeled Lines // IEEE Access. 2021. Vol. 9. P. 76674–76688. DOI: 10.1109/ACCESS.2021.3082689.</mixed-citation><mixed-citation xml:lang="en">Aradillas J., Murillo-Fuentes J., Olmos P. IEEE Access, 2021, vol. 9, рр. 76674–76688, DOI: 10.1109/ACCESS.2021.3082689.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Im C., Kim Y., Mandl T. Deep learning for historical books: classification of printing technology for digitized images // Multimedia Tools and Applications. 2022. Vol. 81. P. 5867–5888. DOI: 10.1007/s11042-021-11754-7.</mixed-citation><mixed-citation xml:lang="en">Im C., Kim Y., Mandl T. Multimedia Tools and Applications, 2022, vol. 81, рр. 5867–5888, DOI: 10.1007/s11042-021-11754-7.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Jiju A., Tuscano S., Badgujar C. OCR Text Extraction // Intern. Journal of Engineering and Management Research. 2021. Vol. 11. P. 83–86. DOI:10.31033/ijemr.11.2.11.</mixed-citation><mixed-citation xml:lang="en">Jiju A., Tuscano Sh., Badgujar Ch. International Journal of Engineering and Management Research, 2021, no. 2(11), pp. 83–86, DOI:10.31033/ijemr.11.2.11.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Lombardi F., Marinai S. Deep Learning for Historical Document Analysis and Recognition — A Survey // Journal of Imaging. 2020. Vol. 6, N. 10. P. 110 DOI: 10.3390/jimaging6100110.</mixed-citation><mixed-citation xml:lang="en">Lombardi F., Marinai S. Journal of Imaging, 2020, no. 6(10), pp. 110, DOI: 10.3390/jimaging6100110.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Sporici D., Cusnir E., Boiangiu C. Improving the accuracy of Tesseract 4.0 OCR engine using convolution-based preprocessing // Symmetry. 2020. Vol. 12, N. 5. P. 715. DOI: 10.3390/sym12050715.</mixed-citation><mixed-citation xml:lang="en">Sporici D., Cusnir E., Boiangiu C. Symmetry, 2020, no. 5(12), pp. 715, DOI: 10.3390/sym12050715.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Pyataeva A. V., Genza S. A. Artificial neural network technology for text recognition // CEUR Workshop Proc. 2019. Vol. 2534. P. 248–252.</mixed-citation><mixed-citation xml:lang="en">Pyataeva A.V., Genza S.A. CEUR Workshop Proceedings, 2019, vol. 2534, рр. 248–252.</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>
