Programming and Computer SoftwareProgramming and Computer SoftwareПрограммирование0132-34743034-5847The Russian Academy of Sciences68812410.31857/S0132347425030071GRLAPGCOMPUTER GRAFICS AND VISUALIZATIONКОМПЬЮТЕРНАЯ ГРАФИКА И ВИЗУАЛИЗАЦИЯResearch ArticleAnalyzing the influence of hyperparameters on the efficiency of OCR model for pre-reform handwritten textsАнализ влияния гиперпараметров на эффективность OCR-модели для дореформенных рукописных текстовhttps://orcid.org/0000-0003-2816-9433SherstnevP. A.ШерстневП. А.
Russian Federation
sherstpasha99@gmail.comhttps://orcid.org/0009-0003-4966-2427KozhinK. D.КожинК. Д.
Russian Federation
kozhin-sfu@yandex.ruhttps://orcid.org/0000-0002-0140-263XPyataevaA. V.ПятаеваА. В.
Russian Federation
anna4u@list.ruArtificial Intelligence Center of Siberian Federal UniversityЦентр Искусственного Интеллекта Сибирского Федерального Университета04072025370792207202522072025Copyright ©; 2025, Russian Academy of SciencesCopyright ©; 2025, Российская академия наук2025Russian Academy of SciencesРоссийская академия наукhttps://transsyst.ru/0132-3474/article/view/688124

The article considers the influence of hyperparameters on the efficiency of models of optical handwriting recognition of pre-reform period on the example of handwritten reports of governors of the Yenisei province of the XIX century. A comparative analysis of model configurations with different architectural components, including normalization modules, feature extraction blocks and predictors, is carried out. Particular attention is paid to the role of input image resolution and the size of hidden layers in achieving an optimal balance between prediction accuracy and computational cost. The results obtained allow us to identify key parameters for the development of optical character recognition systems adapted to historical texts with non-standard orthography and complex structure. Prospects for further research include evaluating synthetic methods for extending training data and analyzing alternative architectures such as transformers.

В статье рассматривается влияние гиперпараметров на эффективность моделей оптического распознавания рукописного текста дореформенного периода на примере рукописных отчетов губернаторов Енисейской губернии XIX в. Проведен сравнительный анализ конфигураций моделей с различными архитектурными компонентами, включая модули нормализации, блоки выделения признаков и предсказатели. Особое внимание уделено роли разрешения входного изображения и размера скрытых слоев в достижении оптимального баланса между точностью предсказания и вычислительными затратами. Полученные результаты позволяют определить ключевые параметры для разработки систем оптического распознавания символов, адаптированных к историческим текстам с нестандартной орфографией и сложной структурой. Перспективы дальнейших исследований включают оценку синтетических методов расширения обучающих данных и анализ альтернативных архитектур, таких как трансформеры.

optical character recognitionhyperparametershandwritten text recognitionpre-reform orthographynormalization modulesneural networkshistorical documentsmodel architectureaccuracyoptimizationоптическое распознавание символовгиперпараметрыраспознавание рукописного текстадореформенная орфографиямодули нормализациинейронные сетиисторические документыархитектура моделиточностьоптимизацияKaratzas D., Gomez-Bigorda L., Nicolaou A., Ghosh S., Bagdanov A., Iwamura M. ICDAR 2015 robust reading competition, 2015 13th International Conference on Document Analysis and Recognition (ICDAR), Tunis, 2015, IEEE, 2015, pp. 1156–1160. https://doi.org/10.1109/ICDAR.2015.7333942Karatzas D., Gomez-Bigorda L., Nicolaou A. et al. ICDAR 2015 Robust Reading Competition // Proceedings of the International Conference on Document Analysis and Recognition (ICDAR). IEEE, 2015. DOI: 10.1109/ICDAR.2015.7333942.Lattner C. LLVM: An infrastructure for multi-stage optimization, Master’s Thesis, Urbana, IL: University of Illinois, 2002.Lattner C. LLVM: An Infrastructure for Multi-Stage Optimization. Master’s thesis, Computer Science Dept., University of Illinois at Urbana-Champaign, Urbana, IL.de Campos T.E., Babu B.R., and Varma M. Character recognition in natural images, Proceedings of the Fourth International Conference on Computer Vision Theory and Applications – Vol. 2: VISAPP (VISIGRAPP 2009), SciTePress, 2009, pp. 273–280. https://doi.org/10.5220/0001770102730280de Campos T., Babu B., Varma M. Character Recognition in Natural Images // Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP). 2009.Chammas E., Mokbel Ch., Likforman-Sulem L. Handwriting recognition of historical documents with few labeled data, 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), Vienna, 2018, IEEE, 2018, pp. 43–48. https://doi.org/10.1109/das.2018.15Chammas E., Mokbel C., Likforman-Sulem L. Handwriting Recognition of Historical Documents with Few Labeled Data. Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). 2018.Mohammed H., Jampour M. From detection to modelling: An end-to-end paleographic system for analysing historical handwriting styles, Document Analysis Systems. DAS 2024, Sfikas G. and Retsinas G., Eds., Lecture Notes in Computer Science, Cham: Springer, 2024, pp. 363–376. https://doi.org/10.1007/978-3-031-70442-0_22Mohammed H., Jampour M. From Detection to Modelling: An End-to-End Paleographic System for Analysing Historical Handwriting Styles. Lecture Notes in Computer Science 2024. 14994. P. 363–376.Galushko I.N. Correcting OCR recognition of the historical sources texts using fuzzy sets (on the example of an early 20th century newspaper), Istoricheskaya Informatika, 2023, no. 1, pp. 102–113. https://doi.org/10.7256/2585-7797.2023.1.40387Галушко И.Н. Корректировка результатов OCR-распознавания текста исторического источника с помощью нечетких множеств (на примере газеты начала XX века) // Историческая информатика. 2023. № 1. https://cyberleninka.ru/article/n/korrektirovka-rezultatov-ocr-raspoznavaniya-teksta-istoricheskogo-istochnika-s-pomoschyu-nechetkih-mnozhestv-na-primere-gazetyRogov A.A., Skabin A.V., Shterkel’ I.A. On deciphering handwritten historical documents, CEUR Workshop Proceedings, 2012.Рогов А.А., Скабин А.В., Штеркель И.А. О дешифровке рукописных исторических документов // CEUR Workshop Proceedings. 2012.Yumasheva Yu.Yu. Automated handwriting recognition using artificial intelligence algorithms: Russian and foreign experience, Digital Orientalia, 2023, vol. 3, nos. 1–2, pp. 24–32. https://doi.org/10.31696/s278240120026084-5Юмашева Ю.Ю. Автоматизированное распознавание рукописных текстов с помощью алгоритмов искусственного интеллекта: российский и зарубежный опыт // Digital Orientalia. 2023. Т. 3. № 1–2. С. 24–32.Li M., Lv T., Chen J., Cui L., Lu Yi., Florencio D., Zhang Ch., Li Zh., Wei F. TrOCR: Transformer-based optical character recognition with pre-trained models, arXiv Preprint, 2021. https://doi.org/10.48550/arXiv.2109.10282Li M., Lv T., Chen J. et al. TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models // arXiv preprint arXiv:2109.10282. 2021. https://arxiv.org/abs/2109.10282Coquenet D., Chatelain C., Paquet T. End-toend handwritten paragraph text recognition using a vertical attention network, IEEE Trans. Pattern Anal. Mach. Intell., 2023, vol. 45, no. 1, pp. 508–524. https://doi.org/10.1109/TPAMI.2022.3144899Coquenet D., Chatelain C., Paquet T. End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network // arXiv preprint arXiv:2012.03868. 2020. https://arxiv.org/abs/2012.03868Baek Yo., Lee B., Han D., Yun S., Lee H. Character region awareness for text detection, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019, IEEE, 2019, pp. 9357–9366. https://doi.org/10.1109/CVPR.2019.00959Baek Y., Lee B., Han D., Yun S., Lee H. Character Region Awareness for Text Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019. P. 9365–9374. DOI: 10.1109/CVPR.2019.00960.Zhou X., Yao C., Wen H., Wang Yu., Zhou Sh., He W., Liang J. EAST: An efficient and accurate scene text detector, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, IEEE, 2017, pp. 2642–2651. https://doi.org/10.1109/CVPR.2017.283Zhou X., Yao C., Wen H., Wang Y., Zhou S., He W., Liang J. EAST: An Efficient and Accurate Scene Text Detector. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. P. 5551–5560. DOI: 10.1109/CVPR.2017.587.Liao M., Wan Zh., Yao C., Chen K., Bai X. Real-time scene text detection with differentiable binarization, Proceedings of the AAAI Conference on Artificial Intelligence, 2020, vol. 34, no. 7, pp. 11474–11481. https://doi.org/10.1609/aaai.v34i07.6812Liao M., Wan Z., Yao C., Chen K., Bai X. (2020). Real-time Scene Text Detection with Differentiable Binarization. Proceedings of the AAAI Conference on Artificial Intelligence. V. 34. № 7. P. 11474–11481. DOI: 10.1609/aaai.v34i07.6884.Wang W., Xie E., Li X., Hou W., Lu T., Y G., Shao Sh. Shape robust text detection with progressive scale expansion network, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, 2019, IEEE, 2019, pp. 9336–9345. https://doi.org/10.1109/cvpr.2019.00956Lang W., Xie E., Li X., Hou W., Lu T., Yu G., Shao S. Shape Robust Text Detection with Progressive Scale Expansion Network. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019. P. 9336–9345. DOI: 10.1109/CVPR.2019.00956.Baek J., Kim G., Lee J., Park S., Han D., Yun S., Oh S.J., Lee H. What is wrong with scene text recognition model comparisons? Dataset and model analysis, 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 2019, IEEE, 2019, pp. 4714–4722. https://doi.org/10.1109/ICCV.2019.00481Baek J., Kim G., Lee J., Park S., Han D., Yun S., Oh S.J., Lee H. What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 2019. P. 4715–4723. DOI: 10.1109/ICCV.2019.00485.Smith R. An overview of the Tesseract OCR engine, Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), Curitiba, Brazil, 2007, IEEE, 2007, vol. 2, pp. 629–633. https://doi.org/10.1109/icdar.2007.4376991Smith R. An Overview of the Tesseract OCR Engine. Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR). 2007. P. 629–633. DOI: 10.1109/ICDAR.2007.4376991.Brandt Skelbye M., Dannйlls D. OCR processing of Swedish historical newspapers using deep hybrid CNN–LSTM networks, Proceedings of the Conference Recent Advances in Natural Language Processing–Deep Learning for Natural Language Processing Methods and Applications, Shoumen, Bulgaria: INCOMA, 2021, pp. 190–198. https://doi.org/10.26615/978-954-452-072-4_023Brandt Skelbye M., Dannélls D. OCR Processing of Swedish Historical Newspapers Using Deep Hybrid CNN–LSTM Networks. Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021). 2021. P. 190–198. https://aclanthology.org/2021.ranlp-1.23/Wick C., Reul C., Puppe F. Improving OCR accuracy on early printed books using deep convolutional networks, arXiv Preprint, 2018. https://doi.org/10.48550/arXiv.1802.10033Wick C., Reul C., Puppe F. Improving OCR Accuracy on Early Printed Books using Deep Convolutional Networks. 2018. arXiv preprint arXiv:1802.10033. https://arxiv.org/abs/1802.10033Lyu L., Koutraki M., Krickl M., Fetahu B. Neural OCR post-hoc correction of historical corpora, Trans. Assoc. Comput. Linguist., 2021, vol. 9, pp. 479–493. https://doi.org/10.1162/tacl_a_00379Lyu L., Koutraki M., Krickl M., Fetahu B. Neural OCR Post-Hoc Correction of Historical Corpora. 2021. arXiv preprint arXiv:2102.00583. https://arxiv.org/abs/2102.00583Shi B., Wang X., Lyu P., Yao C., Bai X. ASTER: An attentional scene text recognizer with flexible rectification, IEEE Trans. Pattern Anal. Mach. Intell., 2018, vol. 41, no. 9, pp. 2035–2048. https://doi.org/10.1109/TPAMI.2018.2848939Shi B., Wang X., Lyu P., Yao C., Bai X. ASTER: An Attentional Scene Text Recognizer with Flexible Rectification. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 2018. № 41(9). Р. 2035–2048. DOI: 10.1109/TPAMI.2018.2848938.Sun Z., Pan W., Luo X. Attention-based handwritten text recognition using CNN-BiLSTM architecture, Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2019.Sun Z., Pan W., Luo X. Attention-based Handwritten Text Recognition Using CNN-BiLSTM Architecture. Proceedings of the International Conference on Document Analysis and Recognition (ICDAR). 2019.Luong T., Pham H., Manning Ch.D. Effective approaches to attention-based neural machine translation, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, 2015, Mаrquez L., Callison-Burch Ch., Su J., Eds., Association for Computational Linguistics, 2015, pp. 1412–1421. https://doi.org/10.18653/v1/d15-1166Luong M.T., Pham H., Manning C.D. Effective Approaches to Attention-based Neural Machine Translation. 2015. arXiv preprint arXiv:1508.04025. https://arxiv.org/abs/1508.04025FromThePage: Collaborative transcription and OCR platform. https://www.fromthepage.com (cited January 15, 2025)FromThePage: Collaborative Transcription and OCR Platform. https://www.fromthepage.com (дата обращения: 15.01.2025)Reports of the governors of the Yenisei province. https://fromthepage.sfu-kras.ru/lib/otchyoty-gubernatorov-eniseyskoy-gubernii (cited January 15, 2025)Отчеты губернаторов Енисейской губернии // FromThePage. https://fromthepage.sfu-kras.ru/lib/otchyoty-gubernatorov-eniseyskoy-gubernii (дата обращения: 15.01.2025)Kozhin K. Image labeling software for optical character recognition (Anno OCR), RF Certificate of State Registration of Software 2024684369, 2024.Кожин К. Программа для разметки изображений под задачи оптического распознавания символов (Anno OCR): Свид. о регистр. ПрЭВМ № 2024684369. Российская Федерация, 2024.Mann H.B., Whitney D.R. On a test of whether one of two random variables is stochastically larger than the other, Ann. Math. Stat., 1947, vol. 18, no. 1, pp. 50–60. https://doi.org/10.1214/aoms/1177730491Mann H.B., Whitney D.R. On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other // Annals of Mathematical Statistics. 1947. V. 18. № 1. P. 50–60.Zhu X. Sample size calculation for Mann–Whitney U test with five methods, International Journal of Clinical Trials, 2021, vol. 8, no. 3, pp. 184–190. https://doi.org/10.18203/2349-3259.ijct20212840Zhu X. Sample size calculation for Mann-Whitney U test with five methods // International Journal of Clinical Trials. 2021. V. 8. № 3. P. 184–190.Mokeyev A., Artemova E., Malkin P. StackMix and Blot augmentations for handwritten recognition using CTCLoss, arXiv Preprint, 2021. https://doi.org/10.48550/arXiv.2108.11667Mokeyev A., Artemova E., Malkin P. StackMix and Blot Augmentations for Handwritten Recognition using CTCLoss. arXiv preprint arXiv:2108.11667. 2021. https://arxiv.org/abs/2108.11667Fogel S., Averbuch-Elor H., Cohen S., Mazor S., Litman R. ScrabbleGAN: Semi-supervised varying length handwritten text generation, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, 2020, IEEE, 2020, pp. 4324–4333. https://doi.org/10.1109/CVPR42600.2020.00438Fogel S., Averbuch-Elor H., Cohen S., Mazor S., Litman R. ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020. P. 4324–4333. DOI: 10.1109/CVPR42600.2020.00430.