• Home
  • Search
  • Automatic Assessment of OCR Quality in Historical Documents
  • Cite Icon34
  • https://doi.org/10.1609/aaai.v29i1.9487Copy DOI Icon

Automatic Assessment of OCR Quality in Historical Documents

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Mass digitization of historical documents is a challenging problem for optical character recognition (OCR) tools. Issues include noisy backgrounds and faded text due to aging, border/marginal noise, bleed-through, skewing, warping, as well as irregular fonts and page layouts. As a result, OCR tools often produce a large number of spurious bounding boxes (BBs) in addition to those that correspond to words in the document. This paper presents an iterative classification algorithm to automatically label BBs (i.e., as text or noise) based on their spatial distribution and geometry. The approach uses a rule-base classifier to generate initial text/noise labels for each BB, followed by an iterative classifier that refines the initial labels by incorporating local information to each BB, its spatial location, shape and size. When evaluated on a dataset containing over 72,000 manually-labeled BBs from 159 historical documents, the algorithm can classify BBs with 0.95 precision and 0.96 recall. Further evaluation on a collection of 6,775 documents with ground-truth transcriptions shows that the algorithm can also be used to predict document quality (0.7 correlation) and improve OCR transcriptions in 85% of the cases.

Similar Papers
  • Research Article

Transforming images into words: optical character recognition solutions for image text extraction

  • Aug 01, 2025
  • IAES International Journal of Artificial Intelligence (IJ-AI)
  • Jyoti Wadmare +5
  • Supplementary Content
  • Citations5

Development and customization of in-house developed OCR and its evaluation

  • Oct 16, 2018
  • The Electronic Library
  • Rajeswari S +1
  • Research Article

281: TELE-ICU + OCR VITALS CAPTURE IMPROVES PRESSOR TIMELINESS WHILE CONTRIBUTING TO MORTALITY REDUCTION

  • Mar 01, 2026
  • Critical Care Medicine
  • Dileep Unnikrishnan +7
  • Research Article
  • Citations3

THE COMPARISONS OF OCR TOOLS: A CONVERSION CASE IN THE MALAYSIAN HANSARD CORPUS DEVELOPMENT

  • Dec 20, 2019
  • MALAYSIAN JOURNAL OF COMPUTING
  • Anis Nadiah Che Abdul Rahman +3
  • Research Article
  • Citations2

An Accuracy Examination of OCR Tools

  • Oct 01, 2019
  • International Journal of Innovative Technology and Exploring Engineering
  • Jayesh Majumdar +15
  • Research Article
  • Citations300

Optical Character Recognition by Open source OCR Tool Tesseract: A Case Study

  • Oct 20, 2012
  • International Journal of Computer Applications
  • Chirag Patel +2
  • Conference Article
  • Citations3

Comprehensive Assessment of OCR Tools for Gene Name Recognition in Biological Pathway Figures

  • Dec 06, 2022
  • Stuart Aldrich +4
  • Conference Article
  • Citations5

Comparative Study of Different Optical Character Recognition Models on Handwritten and Printed Medical Reports

  • Mar 14, 2023
  • Anand Kumar +2
  • Research Article

초등 학생들의 필기 능력 개선을 위한 딥러닝 기반 광학 문자인식 도구 개발

  • Feb 15, 2024
  • Korean Association For Learner-Centered Curriculum And Instruction
  • Jun-Gu Han +1
  • Book Chapter
  • Citations1

Post OCR Correction of Swedish Patent Text

  • Jan 01, 2014
  • Linda Andersson +2
  • Conference Article
  • Citations1

The Efficacy of Tesseract OCR: Insights from a Practical Application Study

  • May 23, 2024
  • Conference Article
  • Citations8

Extracting table data from images using optical character recognition text

  • May 01, 2018
  • Mehmet Yasin Akpinar +2
  • Conference Article
  • Citations1

Complete OCR Solution for Image Analysis of World War 2 Documents

  • Sep 15, 2022
  • Mihai Gradinaru +5
  • Research Article

Clustering and Retrieval of Tele -Lecture Content

  • Apr 27, 2015
  • International Journal of Scientific Engineering and Research
  • Ashwini Y Kothawade +1
  • Book Chapter
  • Citations3

Retrieving Instructional Video Content from Speech and Text Information

  • Jan 01, 2016
  • Ashwini Y Kothawade +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.