Understanding the application of handwritten text recognition technology in heritage contexts: a systematic review of Transkribus in published research
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
Handwritten Text Recognition (HTR) technology is now a mature machine learning tool, becoming integrated in the digitisation processes of libraries and archives, speeding up the transcription of primary sources and facilitating full text searching and analysis of historic texts at scale. However, research into how HTR is changing our information environment is scant. This paper presents a systematic literature review regarding how researchers are using one particular HTR platform, Transkribus, to indicate the domains where HTR is applied, the approach taken, and how the technology is understood. 381 papers from 2015 to 2020 were gathered from Google Scholar, Scopus, and Web of Science, then grouped and coded into categories using quantitative and qualitative approaches. Published research that mentions Transkribus is international and rapidly growing. Transkribus features primarily in archival and library science publications, while a long tail of broad and eclectic disciplines, including history, computer science, citizen science, law and education, demonstrate the wider applicability of the tool. The most common paper categories were humanities applications (67%), technological (25%), users (5%) and tutorials (3%). This paper presents the first overarching review of HTR as featured in published research, while also elucidating how HTR is affecting the information environment.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Basics of Qualitative Research (3rd ed.): Techniques and Procedures for Developing Grounded Theory
Corbin, J., & Strauss, A. (2008) · SAGE · doi:10.4135/9781452230153 · Cited by 12,136 · cited 1×
“To provide confidence in our coding, labels chosen were checked by multiple researchers to ensure agreement, as is standard practise in content analysis (Krippendorff 2004) and allied grounded theory research (Corbin and Strauss 2008).”
Weber, R. (1990) · doi:10.4135/9781412983488 · Cited by 7,750
The Politics of Mass Digitization
Thylstrup, N. B. (2019) · doi:10.7551/mitpress/11404.001.0001 · Cited by 132
Research works printed but not linked: 47
- Anderson I (2004) Are you being served? Historians and the search for primary sources. Archivaria 58:81–129
- Baker KS, Bergerson AS, Fahnenbruck L, Parker D, Roers B (2017) The ongoing rewards of collaboration, intermediality, and multivocality in the humanities: reflections on the Multimedia Project Trug&Schein. Feminist Germ Stud 36:54–70. https://doi.org/10.5250/femigermstud.36.1.0054 · doi:10.5250/femigermstud.36.1.0054
- Benoit E III, Eveleigh A (2019) Challenges, opportunities and future directions of participatory archives. In: BenoitEveleigh EA (ed) Participatory archives: theory and practice. Facet Publishing, London, pp 205–215 · DOI
- Berelson B (1952) Content analysis in communication research. The Free Press, Glencoe
- Bień JS (2019) The Parkosz Treaty Experimental electronic edition. Linguistics Series, vol 1. Polish Studies, Poznań, pp 27–69
- Blanke T, Bryant M, Hedges M (2012) Open source optical character recognition for historical research. J Doc 68(5):659–683. https://doi.org/10.1108/00220411211256021 · DOI
- Chambers S (2019) Library Labs as experimental incubators for digital humanities research. Paper presented at 23rd International Conference on Theory and Practice of Digital Libraries, University of Oslo, 2019. https://biblio.ugent.be/publication/8645483. Accessed 6 Apr 2022
- Chammas E, Mokbel C, Likforman-Sulem L (2018) Handwriting recognition of historical documents with few labelled data. Paper presented at IAPR International Workshop on Document Analysis Systems (DAS), Vienna, Austria, 2018. https://doi.org/10.1109/DAS.2018.15 · DOI
- Charmaz K (2006) Constructing grounded theory: a practical guide through qualitative analysis. Introducing qualitative methods series. Sage, London
- Chassanoff A (2013) Historians and the use of primary source materials in the digital age. Am Arch 76:458–480. https://doi.org/10.17723/aarc.76.2.lh76217m2m376n28 · DOI
- Chen J, Riba P, Fornés A, Mas J, Lladós J, Pujadas-Mora J M (2018) Word-hunter: a gamesourcing experience to validate the transcription of historical manuscripts. Paper presented at International conference on frontiers in handwriting recognition (ICFHR). IEEE, Niagara Falls, 5–8 Aug 2018. https://doi.org/10.1109/ICFHR-2018.2018.00098 · doi:10.1109/icfhr-2018.2018.00098
- Christlein V, Nicolaou A, Schlauwitz T, Späth S, Herbers K, Maier A (2018) Handwritten text recognition error rate reduction in historical documents using naive transcribers. Paper presented at Gesellschaft für Informatik NF-DH-2018, University of Bonn, Bonn, 2018. https://doi.org/10.18420/infdh2018-13 · DOI · Paper page
- Cordell R (2017) “Q i-jtb the Raven”: taking dirty OCR seriously. Book History John Hopkins University Press 20:188–225. https://doi.org/10.1353/bh.2017.0006 · doi:10.1353/bh.2017.0006
- Drisko JW, Maschi T (2015) Content analysis. Oxford University Press, London · DOI · Paper page
- Duff W, Craig B, Cherry J (2004) Historians’ use of archival sources: promises and pitfalls of the digital age. Public Hist 26:1–10 · doi:10.1525/tph.2004.26.1.1
- Edwards JA (2007) Easily adaptable handwriting recognition in historical manuscripts. PhD Thesis, University of California Berkeley
- Flowerdew J (2013) Some thoughts on English for Research Publication Purposes (ERPP) and related issues. Cambridge University Press, Cambridge
- Franzini S, Terras M, Mahony G (2016) A catalogue of digital editions. In: Pierazzo E, Driscoll M (eds) Digital scholarly editing: theories and practices. Open Book Publishers, Cambridge, pp 161–182 · doi:10.11647/obp.0095.09
- Gooding P (2018) Historical newspapers in the digital age: search all about it! Routledge, London
- Grüning T (2018) READ-BAD: a new dataset and evaluation scheme for baseline detection in archival documents. Paper presented at 13th IAPR international workshop on document analysis systems (DAS), IEEE, Vienna, April, 2018. arXiv:1705.03311 · DOI
- Impedovo S (1993) Introduction. In: Impedovo S (ed) Fundamentals of handwriting recognition. Springer, London, pp 1–10
- Kaden B, Kleineberg M (2019) Scholarly makerspaces—an interim report on the DFG Project FuReSH. LIBREAS Lib Ideas Neutral 35:1–10
- Knoke D, Yang S (2011) Social network analysis. Sage, Thousand Oaks
- Krippendorff K (2004) Content analysis: an introduction to its methodology. Sage, London
- Laroche R, Leong E, Munroe J, Nunn HM, Smith L, Tigner AL (2018) Becoming visible: recipes in the making. Early Mod Women 1:133–143. https://doi.org/10.1353/emw.2018.0056 · doi:10.1353/emw.2018.0056
- Lindemann D, Khemakhem M, Laurent R (2018) Retro-digitizing and automatically structuring a large bibliography collection. https://hal.archives-ouvertes.fr/hal-01941534/document. Accessed 15 Jan 2021
- Malmi E, Gionis A, Solin A (2018) Computationally inferred genealogical networks uncover long-term trends in assortative mating. Paper presented at World Wide Web conference, Lyon, 23 April 2018. https://doi.org/10.1145/3178876.3186136. · DOI
- Massot M-L, Sforzini A, Ventresque V (2018) Transcrire les fiches de lecture de Michel Foucault avec le logiciel Transkribus: compte rendu des tests, pp 10–20. https://hal.archives-ouvertes.fr/hal-01794139v2. Accessed 5 Dec 2020
- Meeks D (2020) The significance of medium in palaeographic study. In: Davis V, Laboury D (eds) The Oxford handbook of Egyptian epigraphy and palaeography. Oxford University Press, Oxford, pp 1–12
- Miloni N (2020) Automatic transcription of historical documents: Transkribus as a tool for libraries, archives and scholars. PhD Thesis, Uppsala University
- Muehlberger G et al (2019) Transforming scholarship in the archives through handwriting text recognition, Transkribus as a case study. J Doc 75:954–976. https://doi.org/10.1108/JD-07-2018-0114 · DOI · Paper page
- Prell M (2018) Early modern letters as a challenge automated handwriting recognition. Experience and Results Report on the Transkribus Project. Universitat Jena, Jena
- Ramirez-Castaneda V (2020) Disadvantages in preparing and publishing scientific papers caused by the dominance of the English language in Science: the case of Colombian researchers in biological sciences. Paper presented at PLoS One, Kyoto, 16 Sept 2020. https://doi.org/10.1371/journal.pone.0238372 · DOI · Paper page
- Ridge M (2020) Crowdsourcing in cultural heritage; a practical guide to designing and running successful projects. In: Schuster K, Dunn S (eds) Routledge international handbook of research methods in digital humanities. Routledge, Abingdon, pp 461–480
- Robinson L (2009) Information science: communication chain and domain analysis. J Doc 65:578–591. https://doi.org/10.1108/00220410910970267 · doi:10.1108/00220410910970267
- Romein AC, Kemman M, Birkholz JM, Baker J, de Gruijter M, Meroño PA, Ries T, Ros R, Scagliola S (2020a) State of the field: digital history. J Hist Assoc 105:291–312
- Romein AC, Veldhoen S, de Gruijter M (2020b) The datafication of early modern ordinances. DH Benelux, Leiden
- Sagar B (2019) Character recognition on palm-leaf manuscripts—a survey. In: Sridhar V, Padma M, Radhakrishna RK (eds) Emerging research in electronics, computer science and technology. Springer, Singapore, pp 669–685 · doi:10.1007/978-981-13-5802-9_59
- Sanchez JA, Romero V, Toselli AH, Villegas M, Vidal E (2016) A set of benchmarks for HTR on historical documents. Pattern Recognit 94:122–134. https://doi.org/10.1016/j.patcog.2019.05.025 · doi:10.1016/j.patcog.2019.05.025
- Sanchez JA, Romero V, Toselli AH, Vidal E (2018) Handwritten text recognition competitions with the tranScriptorium dataset. In: Magner V, Pal U, Antonacopoulos A (eds) Document analysis and text recognition: benchmarking state-of-the-art systems. World Scientific, Singapore, pp 1–10
- Schomaker L (2020) Lifelong learning for text retrieval and recognition in historical handwritten document collections. In: Fischer A, Liwicki M, Ingold R (eds) Handwritten historical document analysis, recognition and retrieval—state of the art and future trends. World Scientific, London, pp 221–248
- Semantic Scholar (2005). https://www.semanticscholar.org. Accessed 1 Oct 2021
- Seefeldt D, Thomas WG III (2009) What is digital history? A look at some exemplar projects. Perspect Hist 98:1–7
- van Lit LWC (2019) Among digitized manuscripts. Philology, codicology, palaeography in a digital world. Brill, Leiden
- van Weijen D (2013) Publication languages in the arts & humanities. Res Trends 32:1–10
- Wenger E (1999) Communities of practice: learning, meaning, and identity. Cambridge University Press, Cambridge
- Williams SA, Terras M, Warwick C (2013) What people study when they study Twitter: classifying Twitter related academic papers. J Doc 69:10–12. https://doi.org/10.1108/JD-03-2012-0027 · DOI · Paper page
Cited by
Unlocking the archives: Using large language models to transcribe handwritten historical documents
Humphries, M., Leddy, L. C., Downton, Q., Legace, M., McConnell, J., Murray, I., & Spence, E. (2025) · Historical Methods: A Journal of Quantitative and Interdisciplinary History · doi:10.1080/01615440.2025.2500309 · Cited by 72
Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents
Greif, G., Griesshaber, N., & Greif, R. (2025) · arXiv · doi:10.48550/arxiv.2504.00414 · Cited by 49
Arias Hernández, R., & Rockembach, M. (2025) · AI & SOCIETY · doi:10.1007/s00146-025-02194-0 · Cited by 22
Murrieta-Flores, P., Vega-Sánchez, R., Sánchez-Diaz, A., & Cruz-Ríos, H. F. (2025) · STAR: Science & Technology of Archaeological Research · doi:10.1080/20548923.2025.2484828 · Cited by 7
Human-in-the-loop tabular data extraction methods for historical climate data rescue
Vercruysse, B., Birkholz, J. M., Chandrasekar, K. K. T., Muheki, D., Thiery, W., Verbeeck, H., Hufkens, K., Jacobsen, K., & Verbruggen, C. (2026) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-025-00524-y · Cited by 5
Metadata
- Authors
- Nockels, J., Gooding, P., Ames, S., & Terras, M.
- Venue
- Archival Science
- Published
- 2022-06-17
- Volume
- 22
- Issue
- 3
- Pages
- 367-392
- ISSN
- 1389-0166 (ISSN-L)
- 1573-7500
- OpenAlex
- W4283065708
- Cited by
- 72
- References
- 3
- FWCI
- 30.08
- Type
- journal article
- Language
- en
- Open access
- hybrid
- Licence
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Funders
- scottish graduate school for arts and humanities (AH/R012717/1)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Understanding the application of handwritten text recognition technology in heritage contexts: a systematic review of Transkribus in published research. https://app.cochat.ai/papers/10.1007/s10502-022-09397-0
- The paper
- Nockels, J., Gooding, P., Ames, S., & Terras, M. (2022). Understanding the application of handwritten text recognition technology in heritage contexts: a systematic review of Transkribus in published research. Archival Science. https://doi.org/10.1007/s10502-022-09397-0
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.