Treating OCR Output as a Language (TOOL): A Pipeline for OCR Post-Correction
Year: 2026
Type: article
Abstract: Optical Character Recognition (OCR) enables the digitisation and analysis of large document collections, but recognition errors remain a challenge, particularly for historical documents. This paper presents TOOL (Treating OCR Output as a Language), a modular approach that formulates OCR post-correction as a sequence-to-sequence translation task. A fine-tuned MarianMT encoder–decoder model transforms noisy OCR output into corrected text without modifying the underlying recognition engine. We evaluate TOOL on a collection of historical German vocational education and training documents spanning the period from 1871 to the present day. On 139 held-out test documents, TOOL reduces mean word error rate from 0.792 for Tesseract alone to 0.600, corresponding to a relative reduction of approximately 24.3%. Improvements are also observed in Jaccard bigram similarity, BLEU-4, METEOR, and ROUGE-2, whereas mean normalised Levenshtein distance increases. Comparisons with Hunspell, Phi-4, and Qwen2.5-VL show that the larger language and vision-language models achieve higher accuracy on several metrics. However, TOOL offers a competitive quality–runtime trade-off, with an average end-to-end processing time of 30.12 s per document, compared with 96.57 s for Qwen Transcribed. The results support the feasibility of translation-based OCR post-correction as an additional processing stage in existing OCR workflows, while generalisation to other document collections, OCR engines, and languages remains to be investigated.
Source: Electronics
Authors: Thomas Asselborn(Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Resources, Software, Validation, Visualization, Writing – original draft, Writing – review & editing), Magnus Bender(Conceptualization, Funding acquisition, Investigation, Methodology, Project administration, Resources, Supervision, Validation, Writing – original draft, Writing – review & editing), Ralf Möller(Funding acquisition, Supervision), Sylvia Melzer(Conceptualization, Funding acquisition, Project administration, Supervision, Writing – original draft, Writing – review & editing)
Institutions: University of Lübeck, Aarhus University, Universität Hamburg
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,896
Funder: Deutsche Forschungsgemeinschaft
Award: G8763060997
OpenAlex ID: W7236283453
