Treating OCR Output as a Language (TOOL): A Pipeline for OCR Post-Correction
Open Access
- 18 November 2026
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 15 (22) , 5378
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digitisation and analysis of large document collections, but recognition errors remain a challenge, particularly for historical documents.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.Keywords
Funding Information
- Deutsche Forschungsgemeinschaft (90893796)
This publication has 22 references indexed in Scilit:
- Treating OCR Output as a Language (TOOL) – Improving OCR Output with Seq2Seq TranslationAnnals of Computer Science and Information Systems, 2025
- Exploring Intelligent Document Processing Technology for Discovering Requirements Debt in Systems Engineering Management PlansProcedia Computer Science, 2025
- Post-ocr text correction for Bulgarian historical documentsInternational Journal on Digital Libraries, 2025
- Enhancing Text Recognition of Damaged Documents through Synergistic OCR and Large Language ModelsAnnals of Computer Science and Information Systems, 2024
- Survey of Post-OCR Processing ApproachesACM Computing Surveys, 2021
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- The Political Economy of Collective Skill Formation2011
- An Overview of the Tesseract OCR EngineNinth International Conference on Document Analysis and Recognition (ICDAR 2007), 2007
- Multicriteria Optimization2005
- The Indexing and Retrieval of Document Images: A SurveyComputer Vision and Image Understanding, 1998