The DOI matches its Crossref record.
A survey of OCR evaluation tools and metrics
Abstract
The millions of pages of historical documents that are digitized in libraries are increasingly used in contexts that have more specific requirements for OCR quality than keyword search. How to comprehensively, efficiently and reliably assess the quality of OCR results against the background of mass digitization, when ground truth can only ever be produced for very small numbers? Due to gaps in specifications, results from OCR evaluation tools can return different results, and due to differences in implementation, even commonly used error rates are often not directly comparable. OCR evaluation metrics and sampling methods are also not sufficient where they do not take into account the accuracy of layout analysis, since for advanced use cases like Natural Language Processing or the Digital Humanities, accurate layout analysis and detection of the reading order are crucial. We provide an overview of OCR evaluation metrics and tools, describe two advanced use cases for OCR results, and perform an OCR evaluation experiment with multiple evaluation tools and different metrics for two distinct datasets. We analyze the differences and commonalities in light of the presented use cases and suggest areas for future work.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This metric closely aligns with the Character Recognition Rate (1 minus Character Error Rate) commonly used in OCR studies (Neudecker et al., 2021;Karpinski et al., 2018;Liebl and Burghardt, 2020), but is bounded within [0,1], enabling comparison across varying text lengths.”
From CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition (2025) · cites this paper as Neudecker et al., 2021
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
No references could be resolved yet.
Research works printed but not linked: 38
- 10.1145/2595188.2595214 · doi:10.1145/2595188.2595214
- 10.1145/2037342.2037369 · doi:10.1145/2037342.2037369
- 10.1145/3322905.3322916 · doi:10.1145/3322905.3322916
- 10.1109/ICDAR.2015.7333898 · DOI
- 10.1109/ICDAR.2011.282 · doi:10.1109/icdar.2011.282
- 10.1109/ICDAR.2013.141 · doi:10.1109/icdar.2013.141
- 10.1109/DAS.2016.82 · doi:10.1109/das.2016.82
- 10.1016/j.patrec.2020.02.003 · DOI
- 10.1145/1141753.1141759 · doi:10.1145/1141753.1141759
- Maud Ehrmann , Matteo Romanello , Alex Flückiger , and Simon Clematide . 2020 . Extended overview of CLEF HIPE 2020: named entity processing on historical newspapers . In CLEF 2020 Working Notes. Conference and Labs of the Evaluation Forum, Vol. 2696 . CEUR, Aachen, Germany, 1–38. Maud Ehrmann, Matteo Romanello, Alex Flückiger, and Simon Clematide. 2020. Extended overview of CLEF HIPE 2020: named entity processing on historical newspapers. In CLEF 2020 Working Notes. Conference and Labs of the Evaluation Forum, Vol. 2696. CEUR, Aachen, Germany, 1–38.
- 10.1109/JCDL.2019.00057 · DOI
- 10.1093/llc/fqz024 · DOI
- Rose Holley . 2009 . How good can it get? Analysing and improving OCR accuracy in large scale historic newspaper digitisation programs . D-Lib Magazine 15 , 3/4 (2009), Unpaginated. Rose Holley. 2009. How good can it get? Analysing and improving OCR accuracy in large scale historic newspaper digitisation programs. D-Lib Magazine 15, 3/4 (2009), Unpaginated.
- Kimmo Kettunen , Eetu Mäkelä , Teemu Ruokolainen , Juha Kuokkala , and Laura Löfberg . 2017 . Old content and modern tools-searching named entities in a Finnish OCRed historical newspaper collection 1771-1910 . Digital Humanities Quarterly 11 (2017), 24 . Issue 3. Kimmo Kettunen, Eetu Mäkelä, Teemu Ruokolainen, Juha Kuokkala, and Laura Löfberg. 2017. Old content and modern tools-searching named entities in a Finnish OCRed historical newspaper collection 1771-1910. Digital Humanities Quarterly 11 (2017), 24. Issue 3.
- 10.1109/ICDAR.2009.133 · doi:10.1109/icdar.2009.133
- Gundram Leifert , Roger Labahn , Tobias Grüning , and Svenja Leifert . 2019 . End-To-End Measure for Text Recognition. In 2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE, NY, USA, 1424–1431 . Gundram Leifert, Roger Labahn, Tobias Grüning, and Svenja Leifert. 2019. End-To-End Measure for Text Recognition. In 2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE, NY, USA, 1424–1431.
- Vladimir I Levenshtein . 1966. Binary codes capable of correcting deletions, insertions, and reversals. Soviet physics doklady 10, 8 ( 1966 ), 707–710. Vladimir I Levenshtein. 1966. Binary codes capable of correcting deletions, insertions, and reversals. Soviet physics doklady 10, 8 (1966), 707–710.
- 10.1007/s10032-009-0094-8 · DOI
- Margot Mieskes and Stefan Schmunk . 2019 . OCR Quality and NLP Preprocessing . In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics , Florence, Italy. ACL, Stroudsburg PA, USA, 102–105. Margot Mieskes and Stefan Schmunk. 2019. OCR Quality and NLP Preprocessing. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, Florence, Italy. ACL, Stroudsburg PA, USA, 102–105.
- 10.1145/2501115.2501130 · doi:10.1145/2501115.2501130
- 10.1109/ICPR.2010.72 · doi:10.1109/icpr.2010.72
- Elvys Linhares Pontes , Ahmed Hamdi , Nicolas Sidere , and Antoine Doucet . 2019 . Impact of OCR quality on named entity linking . In International Conference on Asian Digital Libraries . Springer, NY, USA, 102–115. Elvys Linhares Pontes, Ahmed Hamdi, Nicolas Sidere, and Antoine Doucet. 2019. Impact of OCR quality on named entity linking. In International Conference on Asian Digital Libraries. Springer, NY, USA, 102–115.
- 10.1016/j.patcog.2012.10.002 · DOI
- Georg Rehm , Peter Bourgonje , Stefanie Hegele , Florian Kintzel , Julián Moreno Schneider , Malte Ostendorff , Karolina Zaczynska , Armin Berger , Stefan Grill , and Sören et al . Räuchle. 2020 . QURATOR: Innovative Technologies for Content and Data Curation . CEUR-WS 2535 , 1 (2020), 15 . Georg Rehm, Peter Bourgonje, Stefanie Hegele, Florian Kintzel, Julián Moreno Schneider, Malte Ostendorff, Karolina Zaczynska, Armin Berger, Stefan Grill, and Sören et al. Räuchle. 2020. QURATOR: Innovative Technologies for Content and Data Curation. CEUR-WS 2535, 1 (2020), 15.
- Stephen Vincent Rice . 1996. Measuring the accuracy of page-reading systems . UNLV , Las Vega, NV . Stephen Vincent Rice. 1996. Measuring the accuracy of page-reading systems. UNLV, Las Vega, NV.
- Stephen V Rice and Thomas A Nartker . 1996. The ISRI analytic tools for OCR evaluation . UNLV/Information Science Research Institute , TR-96 2 ( 1996 ), 45. Stephen V Rice and Thomas A Nartker. 1996. The ISRI analytic tools for OCR evaluation. UNLV/Information Science Research Institute, TR-96 2 (1996), 45.
- 10.1109/ICDAR.2015.7333823 · doi:10.1109/icdar.2015.7333823
- 10.33011/computel.v1i.345 · doi:10.33011/computel.v1i.345
- 10.1109/DAS.2018.14 · DOI
- David A Smith and Ryan Cordell . 2018. A research agenda for historical and multilingual optical character recognition . Northeastern University , Boston, MA . David A Smith and Ryan Cordell. 2018. A research agenda for historical and multilingual optical character recognition. Northeastern University, Boston, MA.
- 10.1109/ICDAR.2011.114 · DOI
- Uwe Springmann , Florian Fink , and Klaus U Schulz . 2016. Automatic quality evaluation and (semi-) automatic improvement of OCR models for historical printings. arXiv preprint arXiv:1606.05157 ( 2016 ), 8. Uwe Springmann, Florian Fink, and Klaus U Schulz. 2016. Automatic quality evaluation and (semi-) automatic improvement of OCR models for historical printings. arXiv preprint arXiv:1606.05157 (2016), 8. · arXiv
- Uwe Springmann , Christian Reul , Stefanie Dipper , and Johannes Baiter . 2018. Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin. arXiv preprint arXiv:1809.05501 ( 2018 ), 8. Uwe Springmann, Christian Reul, Stefanie Dipper, and Johannes Baiter. 2018. Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin. arXiv preprint arXiv:1809.05501 (2018), 8. · arXiv
- 10.1045/july2009-munoz · doi:10.1045/july2009-munoz
- 10.1007/978-3-319-24592-8_19 · doi:10.1007/978-3-319-24592-8_19
- 10.1007/BF01206331 · DOI · Paper page
- Daniel van Strien Kaspar Beelen Mariona Coll Ardanuy Kasra Hosseini Barbara McGillivray and Giovanni Colavizza. 2020. Assessing the Impact of OCR Quality on Downstream NLP Tasks. In ICAART (1). SCITEPRESS Setúbal Portugal 484–496. Daniel van Strien Kaspar Beelen Mariona Coll Ardanuy Kasra Hosseini Barbara McGillivray and Giovanni Colavizza. 2020. Assessing the Impact of OCR Quality on Downstream NLP Tasks. In ICAART (1). SCITEPRESS Setúbal Portugal 484–496. · DOI
- 10.1515/abitech-2015-0014 · doi:10.1515/abitech-2015-0014
Cited by
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
Benchmarking large language models for handwritten text recognition
Crosilla, G., Klic, L., & Colavizza, G. (2025) · Journal of Documentation · doi:10.1108/jd-03-2025-0082 · Cited by 34
Semnani, S. J., Zhang, H., He, X., Tekgürler, M., & Lam, M. S. (2025) · arXiv · doi:10.48550/arxiv.2509.19768 · Cited by 5
Metadata
- Authors
- Neudecker, C., Baierer, K., Gerber, M., Clausner, C., Antonacopoulos, A., & Pletschacher, S.
- Affiliations
- Berlin State Library, Germany
- University of Salford, United Kingdom
- Venue
- The 6th International Workshop on Historical Document Imaging and Processing
- Publisher
- ACM
- Published
- 2021-09-05
- Pages
- 13-18
- Cited by
- 81
- References
- 0
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: A survey of OCR evaluation tools and metrics. https://app.cochat.ai/papers/10.1145/3476887.3476888
- The paper
- Neudecker, C., Baierer, K., Gerber, M., Clausner, C., Antonacopoulos, A., & Pletschacher, S. (2021). A survey of OCR evaluation tools and metrics. The 6th International Workshop on Historical Document Imaging and Processing. https://doi.org/10.1145/3476887.3476888
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.