• Home
  • Search
  • Treating OCR Output as a Language (TOOL) – Improving OCR Output with Seq2Seq Translation
  • https://doi.org/10.15439/2025f1103Copy DOI Icon

Treating OCR Output as a Language (TOOL) – Improving OCR Output with Seq2Seq Translation

  • Oct 15, 2025
  • Thomas Asselborn +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Optical Character Recognition (OCR) systems are frequently used to digitise text, but often produce noisy results, especially with historical, poor-quality or multilingual data.Despite advances in OCR technology, post-processing remains a significant bottleneck.We propose TOOL (Treating OCR Output as a Language), a new approach that understands OCR correction as a machine translation task.By treating noisy OCR text as a language in its own right, TOOL employs sequenceto-sequence models like Marian to translate it into clean, standardised text.This method is scalable, model-independent and language-flexible.We demonstrate this approach by translating "OCR German" to Standard German from around 1871 to the present day, improving accuracy at the token level by using matched training pairs of OCR output and base text.

Similar Papers
  • Research Article
  • Citations5

Robust named entity detection from optical character recognition output

  • Apr 13, 2011
  • International Journal on Document Analysis and Recognition (IJDAR)
  • Krishna Subramanian +2
  • Conference Article
  • Citations7

Improving Optical Character Recognition(OCR) Accuracy using Multi-Layer Perceptron(MLP)

  • Apr 11, 2023
  • M Krishnamoorthi +3
  • PDF
  • Research Article
  • Citations4

Advancing machine learning with OCR2SEQ: an innovative approach to multi-modal data augmentation

  • Jun 13, 2024
  • Journal of Big Data
  • Michael Lowe +3
  • Conference Article
  • Citations63

A Fast Alignment Scheme for Automatic OCR Evaluation of Books

  • Jan 01, 2011
  • Ismet Zeki Yalniz +1
  • Research Article
  • Citations19

OCR error correction using correction patterns and self-organizing migrating algorithm

  • Nov 23, 2020
  • Pattern Analysis and Applications
  • Quoc-Dung Nguyen +3
  • Research Article
  • Citations2

Automatic Hindi OCR Error Correction Using MLM-BERT

  • Apr 25, 2024
  • Ingénierie des systèmes d information
  • Teja Kundaikar +3
  • Research Article
  • Citations16

Integrating natural language processing with image document analysis: what we learned from two real-world applications

  • May 28, 2015
  • International Journal on Document Analysis and Recognition (IJDAR)
  • Jinying Chen +2
  • Conference Article
  • Citations10

Combination of multiple aligned recognition outputs using WFST and LSTM

  • Aug 01, 2015
  • Mayce Al Azawi +2
  • Conference Article
  • Citations45

OmniPage vs. Sakhr: paired model evaluation of two Arabic OCR products

  • Jan 07, 1999
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Tapas Kanungo +2
  • Conference Article

Portuguese post-OCR Resources for Text Optimisation

  • Nov 10, 2025
  • Tomás Freitas Osório +1
  • Conference Article
  • Citations3

An Optical Character Recognition Post-processing Method for technical documents

  • Nov 06, 2023
  • Lucas Viana Da Silva +2
  • Research Article
  • Citations1

APPLICATION OF OPTICAL CHARACTER RECOGNITION AND MACHINE LEARNING TECHNOLOGIES TO CREATE AN INFORMATION SYSTEM FOR AUTOMATIC VERIFICATION OF OFFLINE TESTING

  • Dec 24, 2024
  • Bulletin of National Technical University "KhPI". Series: System Analysis, Control and Information Technologies
  • Vadym Ziuziun +1
  • PDF
  • Research Article
  • Citations14

Business Process Automation: A Workflow Incorporating Optical Character Recognition and Approximate String and Pattern Matching for Solving Practical Industry Problems

  • Oct 24, 2019
  • Applied System Innovation
  • Coenrad De Jager +1
  • Research Article

Possibilities of Using OCR Technologies from Google for Recognition and Digitalization of Archive Documents

  • Jun 26, 2024
  • Visnyk of Kharkiv State Academy of Culture
  • O Krasynskyi +1
  • Book Chapter
  • Citations8

Soft Computing Techniques for Optical Character Recognition Systems

  • Dec 24, 2016
  • Arindam Chaudhuri +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.