{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:37:24Z","timestamp":1772908644457,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T00:00:00Z","timestamp":1739750400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T00:00:00Z","timestamp":1739750400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100008332","name":"Graz University of Technology","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100008332","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Digit Libr"],"published-print":{"date-parts":[[2025,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>This paper explores the challenge of processing and extracting information from large quantities of printed serial sources from the 19th century, which have been largely untapped due to the inadequacies of existing extraction techniques. We focus on the Habsburg Central Europe\u2019s <jats:italic>Hof- und Staatsschematismus<\/jats:italic>, a comprehensive record published between 1702 and 1918 that documents the Habsburg civil service\u2019s hierarchy and the evolution of its central administration over two centuries. Our approach sees the significant investment into machine learning-driven layout detection prior to the OCR-process. We generated synthetic data mimicking the <jats:italic>Hof- und Staatsschematismus<\/jats:italic> style for initial training of a Faster R-CNN model, followed by fine-tuning the model with a smaller dataset of manually annotated historical documents. Subsequently, we optimised Tesseract-OCR for our document style to enhance the combined structure extraction and OCR process. Our evaluation demonstrates significant improvements in OCR performance metrics (WER and CER), with the combined structure detection and fine-tuned OCR process showing a decrease in error rates of 15.68 percentage points for CER and 19.95 percentage points for WER. These findings underscore the potential of ML techniques in facilitating the extraction and analysis of historical documents.<\/jats:p>","DOI":"10.1007\/s00799-025-00413-z","type":"journal-article","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T07:17:36Z","timestamp":1739776656000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Enhancing OCR in historical documents with complex layouts through machine learning"],"prefix":"10.1007","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4787-9091","authenticated-orcid":false,"given":"David","family":"Fleischhacker","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roman","family":"Kern","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfgang","family":"G\u00f6derle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,17]]},"reference":[{"key":"413_CR1","doi-asserted-by":"crossref","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: (2019), pp. 32\u201339","DOI":"10.1042\/BSR20181785"},{"key":"413_CR2","doi-asserted-by":"crossref","unstructured":"Noflatscher, H.: (B\u00f6hlau, 2004), pp. 59\u201375","DOI":"10.7767\/boehlau.9783205160199.59"},{"key":"413_CR3","unstructured":"Bauer, V.: Repertorium territorialer Amtskalender und Amtshandb\u00fccher im Alten Reich: Adre\u00df- , Hof- , Staatskalender und Staatshandb\u00fccher des 18. Jahrhunderts., vol. vol. 2 (Klostermann, 1999)"},{"key":"413_CR4","unstructured":"ALEX. Staatshandbuch 1910: Schematismus staat (1910). https:\/\/alex.onb.ac.at\/cgi-content\/alex?aid=shb&datum=1910 &page=597 &size=45. Accessed on: 2022-10-21"},{"key":"413_CR5","unstructured":"Raphael, L.: Die Erben von Bloch und Febvre. Annales-Geschichtsschreibung und nouvelle histoire in Frankreich 1945-1980 (Klett-Cotta, Stuttgart, 1994)"},{"key":"413_CR6","doi-asserted-by":"publisher","unstructured":"Jannidis, F., Kohle, H., Rehbein, M.: Digital Humanities Eine Einf\u00fchrung. J. B. Metzler, Stuttgart (2017). https:\/\/doi.org\/10.1007\/978-3-476-05446-3","DOI":"10.1007\/978-3-476-05446-3"},{"key":"413_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-022-00325-2","author":"E Boros","year":"2022","unstructured":"Boros, E., Nguyen, N.K., Lejeune, G., Doucet, A.: Assessing the impact of ocr noise on multilingual event detection over digitised documents. Int. J. Digit. Libr. (2022). https:\/\/doi.org\/10.1007\/s00799-022-00325-2","journal-title":"Int. J. Digit. Libr."},{"key":"413_CR8","unstructured":"Wajer, M.B.W.: Internet Archive OCR Stack in 2021. Switching to Open Source Software (2021). https:\/\/ia601807.us.archive.org\/35\/items\/merlijn-wajer-presentation\/merlijn-wajer-presentation-ocr.pdf"},{"key":"413_CR9","unstructured":"Austrian National Library. Austrian Books Online (2023). https:\/\/www.onb.ac.at\/en\/digital-offers\/austrian-books-online"},{"issue":"1","key":"413_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18352\/lq.10322","volume":"30","author":"K Kettunen","year":"2020","unstructured":"Kettunen, K., Koistinen, M., Kervinen, J.: Ground truth ocr sample data of finnish historical newspapers and journals in data improvement validation of a re-ocring process. LIBER Quarterly 30(1), 1\u201320 (2020). https:\/\/doi.org\/10.18352\/lq.10322","journal-title":"LIBER Quarterly"},{"key":"413_CR11","unstructured":"Staatsbibliothek, B.: Technologien & Softwareentwicklung (2023). https:\/\/www.digitale-sammlungen.de\/de\/technologien-und-softwareentwicklung"},{"key":"413_CR12","unstructured":"G.\u00a0Markus. Issue 13: OCR. EuropeanaTech Insight is a multimedia publication about R &D developments by the EuropeanaTech Community (2019). https:\/\/pro.europeana.eu\/page\/issue-13-ocr"},{"key":"413_CR13","unstructured":"Ehmer, J., Mitterauer, M., Thaller, M.: Wiener Datenbank zur Europ\u00e4ischen Familiengeschichte (2023)"},{"key":"413_CR14","unstructured":"Becker, P., Osterkamp, J.: The Emperor\u2019s Desk (2018\u20132021)"},{"key":"413_CR15","unstructured":"Romberg, M.: The Viennese Court (2020\u20132023)"},{"key":"413_CR16","unstructured":"Popovici, V., Velkov\u00e1, A.: Social Mobility of Elites (2022)"},{"issue":"2","key":"413_CR17","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1515\/bfp-2020-0024","volume":"44","author":"E Engl","year":"2020","unstructured":"Engl, E.: OCR-D kompakt: Ergebnisse und Stand der Forschung in der F\u00f6rderinitiative. Bibliothek Forschung und Praxis 44(2), 218\u2013230 (2020). https:\/\/doi.org\/10.1515\/bfp-2020-0024","journal-title":"Bibliothek Forschung und Praxis"},{"issue":"23","key":"413_CR18","doi-asserted-by":"publisher","first-page":"17209","DOI":"10.1007\/s00521-020-04910-x","volume":"32","author":"J Mart\u00ednek","year":"2020","unstructured":"Mart\u00ednek, J., Lenc, L., Kr\u00e1l, P.: Building an efficient OCR system for historical documents with little training data. Neural Comput. Appl. 32(23), 17209\u201317227 (2020). https:\/\/doi.org\/10.1007\/s00521-020-04910-x","journal-title":"Neural Comput. Appl."},{"key":"413_CR19","doi-asserted-by":"publisher","unstructured":"Reul, C., Christ, D., Hartelt, A., Balbach, N., Wehner, M., Springmann, U., Wick, C., Grundig, C., B\u00fcttner, A., Puppe, F.: Ocr4all\u2013an open-source tool providing a (semi-)automatic ocr workflow for historical printings (2019). https:\/\/doi.org\/10.3390\/app9224853. http:\/\/arxiv.org\/abs\/1909.04032","DOI":"10.3390\/app9224853"},{"key":"413_CR20","unstructured":"Cordell, R.: Machine Learning + Libraries. A Report on the State of the Field (2020). https:\/\/labs.loc.gov\/static\/labs\/work\/reports\/Cordell-LOC-ML-report.pdf?loclr=blogsig"},{"key":"413_CR21","doi-asserted-by":"publisher","DOI":"10.53377\/lq.10934","author":"A Gasparini","year":"2022","unstructured":"Gasparini, A., Kautonen, H.: Understanding artificial intelligence in research libraries-extensive literature review. LIBER Quart. J. Assoc. Eur. Res. Libr. (2022). https:\/\/doi.org\/10.53377\/lq.10934","journal-title":"LIBER Quart. J. Assoc. Eur. Res. Libr."},{"key":"413_CR22","unstructured":"Teibenbacher, P., Kramer, D., G\u00f6derle, W.: An Inventory of Austrian Census Materials , 1857-1910. Final Report. Mosaic Working Paper 190, 25 (2012)"},{"issue":"4","key":"413_CR23","doi-asserted-by":"publisher","first-page":"263","DOI":"10.25162\/VSWG-2021-0016","volume":"108","author":"A Zechner","year":"2021","unstructured":"Zechner, A., Knapp, E., Adelsberger, M.: Prices and Wages in Salzburg and Vienna, c. 1450\u20131850 An Introduction to the Data. Vierteljahresschrift fur Sozial und Wirtschaftsgeschichte 108(4), 263\u2013270 (2021). https:\/\/doi.org\/10.25162\/VSWG-2021-0016","journal-title":"Vierteljahresschrift fur Sozial und Wirtschaftsgeschichte"},{"key":"413_CR24","doi-asserted-by":"publisher","unstructured":"Bavouzet, J.: in The Habsburg Civli Service and Beyond: Bureaucracy and Civil Servants from the Vorm\u00e4rz to the Inter-War Years, ed. by F.\u00a0Adlgasser, F.\u00a0Lindstr\u00f6m (Verlag der \u00d6sterreichischen Akademie der Wissenschaften, Vienna, 2019), pp. 167\u2013186. https:\/\/doi.org\/10.2307\/j.ctvggx26b.11","DOI":"10.2307\/j.ctvggx26b.11"},{"key":"413_CR25","doi-asserted-by":"crossref","unstructured":"Wang, J., Liu, C., Jin, L., Tang, G., Zhang, J., Zhang, S., Wang, Q., Wu, Y., Cai, M.: Towards robust visual information extraction in real world: New dataset and novel solution (2021). www.aaai.org","DOI":"10.1609\/aaai.v35i4.16378"},{"key":"413_CR26","doi-asserted-by":"publisher","unstructured":"Douzon, T., Duffner, S., Garcia, C., Espinas, J.: Improving information extraction on business documents with specific pre-training tasks. In International Workshop on Document Analysis Systems. (Springer Science and Business Media Deutschland GmbH, 2022), pp. 111\u2013125. https:\/\/doi.org\/10.1007\/978-3-031-06555-2_8","DOI":"10.1007\/978-3-031-06555-2_8"},{"key":"413_CR27","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.patrec.2020.05.001","volume":"136","author":"M Carbonell","year":"2020","unstructured":"Carbonell, M., Forn\u00e9s, A., Villegas, M., Llad\u00f3s, J.: A neural model for text localization, transcription and named entity recognition in full pages. Pattern Recogn. Lett. 136, 219\u2013227 (2020). https:\/\/doi.org\/10.1016\/j.patrec.2020.05.001","journal-title":"Pattern Recogn. Lett."},{"issue":"3","key":"413_CR28","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s10032-023-00427-w","volume":"26","author":"S Tarride","year":"2023","unstructured":"Tarride, S., Maarand, M., Boillet, M., McGrath, J., Capel, E., V\u2019ezina, H., Kermorvant, C.: Large-scale genealogical information extraction from handwritten Quebec parish records. Int. J. Doc. Anal. Recogn. (IJDAR) 26(3), 255\u2013272 (2023). https:\/\/doi.org\/10.1007\/s10032-023-00427-w","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"413_CR29","unstructured":"Monnier, T., Aubry, M.: in 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 91\u201396. (IEEE, 2020)"},{"key":"413_CR30","doi-asserted-by":"crossref","unstructured":"Gruber, I., Ircing, P., Neduchal,P., Hr\u00faz, M., Hlav\u00e1\u010d, M., Zaj\u00edc, Z., \u0160vec, J., Bul\u00edn, M.: in International Conference on Speech and Computer, pp. 166\u2013175, (Springer, 2020)","DOI":"10.1007\/978-3-030-60276-5_17"},{"key":"413_CR31","unstructured":"M.\u00a0Shen, H.\u00a0Lei, in 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), pp. 1566\u20131570, (IEEE, 2015)"},{"key":"413_CR32","doi-asserted-by":"crossref","unstructured":"Lat, A., Jawahar, C.: in 2018 24th International Conference on Pattern Recognition (ICPR), pp. 3162\u20133167 (IEEE, 2018)","DOI":"10.1109\/ICPR.2018.8545609"},{"issue":"3","key":"413_CR33","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s10032-019-00332-1","volume":"22","author":"T Gr\u00fcning","year":"2019","unstructured":"Gr\u00fcning, T., Leifert, G., Strau\u00df, T., Michael, J., Labahn, R.: A two-stage method for text line detection in historical documents. Int. J. Doc. Anal. Recogn. 22(3), 285\u2013302 (2019). https:\/\/doi.org\/10.1007\/s10032-019-00332-1. arXiv:1802.03345","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"413_CR34","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8100285","author":"J B\u00fcttner","year":"2022","unstructured":"B\u00fcttner, J., Martinetz, J., El-Hajj, H., Valleriani, M.: Cordeep and the sacrobosco dataset: detection of visual elements in historical documents. J. Imaging (2022). https:\/\/doi.org\/10.3390\/jimaging8100285","journal-title":"J. Imaging"},{"key":"413_CR35","doi-asserted-by":"publisher","DOI":"10.1145\/3355610","author":"GM Binmakhashen","year":"2019","unstructured":"Binmakhashen, G.M., Mahmoud, S.A.: Document layout analysis: a comprehensive survey. ACM Comput. Surv. (2019). https:\/\/doi.org\/10.1145\/3355610","journal-title":"ACM Comput. Surv."},{"key":"413_CR36","doi-asserted-by":"publisher","unstructured":"Boillet, M., Kermorvant, C., Paquet, T.: Multiple document datasets pre-training improves text line detection with deep neural networks. Proceedings-International Conference on Pattern Recognition pp. 2134\u20132141 (2020). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412447. arXiv:2012.14163","DOI":"10.1109\/ICPR48806.2021.9412447"},{"key":"413_CR37","doi-asserted-by":"publisher","unstructured":"Xu, Y., Li, M., Cui, L., Huang,S., Wei, F., Zhou,M.: Layoutlm: Pre-training of text and layout for document image understanding. In: Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp. 1192\u20131200 (2020). https:\/\/doi.org\/10.1145\/3394486.3403172. http:\/\/arxiv.org\/abs\/1912.13318","DOI":"10.1145\/3394486.3403172"},{"issue":"3","key":"413_CR38","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s10032-021-00380-6","volume":"24","author":"S Biswas","year":"2021","unstructured":"Biswas, S., Riba, P., Llad\u00f3s, J., Pal, U.: Beyond document object detection: instance-level segmentation of complex layouts. Int. J. Doc. Anal. Recogn. 24(3), 269\u2013281 (2021). https:\/\/doi.org\/10.1007\/s10032-021-00380-6","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"413_CR39","unstructured":"LuaTex. Luatex (2023). https:\/\/www.luatex.org\/"},{"key":"413_CR40","unstructured":"Remy, P.: Name dataset. https:\/\/github.com\/philipperemy\/name-dataset (2021)"},{"key":"413_CR41","unstructured":"FontForge. Fontforge. https:\/\/fontforge.org\/en-US\/ (2023). [Accessed 09-Mar-2023]"},{"key":"413_CR42","unstructured":"Wikipedia. Liste der \u00f6sterreichischen Orden und Ehrenzeichen \u2014 Wikipedia, the free encyclopedia. http:\/\/de.wikipedia.org\/w\/index.php?title=Liste%20der%20%C3%B6sterreichischen%20Orden%20und%20Ehrenzeichen&oldid=231609032 (2023). [Online; accessed 09-March-2023]"},{"key":"413_CR43","unstructured":"A.\u00a0Paszke, S.\u00a0Gross, F.\u00a0Massa, A.\u00a0Lerer, J.\u00a0Bradbury, G.\u00a0Chanan, T.\u00a0Killeen, Z.\u00a0Lin, N.\u00a0Gimelshein, L.\u00a0Antiga, A.\u00a0Desmaison, A.\u00a0Kopf, E.\u00a0Yang, Z.\u00a0DeVito, M.\u00a0Raison, A.\u00a0Tejani, S.\u00a0Chilamkurthy, B.\u00a0Steiner, L.\u00a0Fang, J.\u00a0Bai, S.\u00a0Chintala, in Advances in Neural Information Processing Systems, vol.\u00a032, ed. by H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0\u2019 Alch\u00e9-Buc, E.\u00a0Fox, R.\u00a0Garnett (Curran Associates, Inc., 2019). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf"},{"key":"413_CR44","doi-asserted-by":"publisher","unstructured":"Li, Y., Xie, S., Chen, X., Dollar, P., He, K., Girshick, R.: Benchmarking detection transfer learning with vision transformers (2021). https:\/\/doi.org\/10.48550\/ARXIV.2111.11429","DOI":"10.48550\/ARXIV.2111.11429"},{"key":"413_CR45","unstructured":"Keskar, N.S., Mudigere,D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: Generalization gap and sharp minima. CoRR abs\/1609.04836. arXiv:1609.04836. (2016)"},{"key":"413_CR46","doi-asserted-by":"publisher","unstructured":"Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks (2014). https:\/\/doi.org\/10.48550\/ARXIV.1404.5997","DOI":"10.48550\/ARXIV.1404.5997"},{"key":"413_CR47","unstructured":"PyTorch. Torchserve (2023). https:\/\/pytorch.org\/serve\/index.html"},{"key":"413_CR48","unstructured":"Fleischhacker, M.: Boundingboxeditor. https:\/\/github.com\/mfl28\/BoundingBoxEditor (2023)"},{"key":"413_CR49","unstructured":"Tesseract. Tesseract (2023). https:\/\/github.com\/tesseract-ocr\/tesseract"},{"key":"413_CR50","unstructured":"Tesseract. Improving the quality of the output (2022). https:\/\/tesseract-ocr.github.io\/tessdoc\/ImproveQuality.html. Accessed on: 2022-10-21"}],"container-title":["International Journal on Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-025-00413-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00799-025-00413-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-025-00413-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T06:21:05Z","timestamp":1742797265000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00799-025-00413-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,17]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["413"],"URL":"https:\/\/doi.org\/10.1007\/s00799-025-00413-z","relation":{},"ISSN":["1432-5012","1432-1300"],"issn-type":[{"value":"1432-5012","type":"print"},{"value":"1432-1300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,17]]},"assertion":[{"value":"5 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"3"}}