Ocropodium: open source OCR for small-scale historical archives

Tobias Blanke; Michael Bryant; Mark Hedges

doi:10.1177/0165551511429418

Ocropodium: open source OCR for small-scale historical archives

Tobias Blanke, Michael Bryant, Mark Hedges

Digital Humanities

Research output: Contribution to journal › Article › peer-review

13 Citations (Scopus)

Abstract

Large-scale digitization projects dealing with text-based historical material face challenges that are not well catered for by commercial software. This article discusses the results of a project to build a scalable OCR workflow for historical collections based on open source tools that is particularly tailored towards use in small-scale historical archives. It argues that open source tools allow for better customization to match these requirements, particularly with regard to character model training and per-project language modelling. We offer insights into our accuracy evaluation results of various open source OCR tools, as well as a case study about the challenges and opportunities of open source OCR in historical archives.

Original language	English
Pages (from-to)	76 - 86
Number of pages	11
Journal	JOURNAL OF INFORMATION SCIENCE
Volume	38
Issue number	1
DOIs	https://doi.org/10.1177/0165551511429418
Publication status	Published - Feb 2012

Access to Document

10.1177/0165551511429418

OCROPODIUM
Blanke, T. & Hedges, M.
JISC Joint Information Systems Committee
1/09/2009 → 30/06/2011
Project: Research

Cite this

@article{83b898d3f5484a82aaaafdf6f9bbd552,

title = "Ocropodium: open source OCR for small-scale historical archives",

abstract = "Large-scale digitization projects dealing with text-based historical material face challenges that are not well catered for by commercial software. This article discusses the results of a project to build a scalable OCR workflow for historical collections based on open source tools that is particularly tailored towards use in small-scale historical archives. It argues that open source tools allow for better customization to match these requirements, particularly with regard to character model training and per-project language modelling. We offer insights into our accuracy evaluation results of various open source OCR tools, as well as a case study about the challenges and opportunities of open source OCR in historical archives.",

author = "Tobias Blanke and Michael Bryant and Mark Hedges",

year = "2012",

month = feb,

doi = "10.1177/0165551511429418",

language = "English",

volume = "38",

pages = "76 -- 86",

journal = "JOURNAL OF INFORMATION SCIENCE",

publisher = "SAGE Publications Ltd",

number = "1",

}

TY - JOUR

T1 - Ocropodium: open source OCR for small-scale historical archives

AU - Blanke, Tobias

AU - Bryant, Michael

AU - Hedges, Mark

PY - 2012/2

Y1 - 2012/2

N2 - Large-scale digitization projects dealing with text-based historical material face challenges that are not well catered for by commercial software. This article discusses the results of a project to build a scalable OCR workflow for historical collections based on open source tools that is particularly tailored towards use in small-scale historical archives. It argues that open source tools allow for better customization to match these requirements, particularly with regard to character model training and per-project language modelling. We offer insights into our accuracy evaluation results of various open source OCR tools, as well as a case study about the challenges and opportunities of open source OCR in historical archives.

AB - Large-scale digitization projects dealing with text-based historical material face challenges that are not well catered for by commercial software. This article discusses the results of a project to build a scalable OCR workflow for historical collections based on open source tools that is particularly tailored towards use in small-scale historical archives. It argues that open source tools allow for better customization to match these requirements, particularly with regard to character model training and per-project language modelling. We offer insights into our accuracy evaluation results of various open source OCR tools, as well as a case study about the challenges and opportunities of open source OCR in historical archives.

U2 - 10.1177/0165551511429418

DO - 10.1177/0165551511429418

M3 - Article

VL - 38

SP - 76

EP - 86

JO - JOURNAL OF INFORMATION SCIENCE

JF - JOURNAL OF INFORMATION SCIENCE

IS - 1

ER -

Ocropodium: open source OCR for small-scale historical archives

Abstract

Access to Document

Fingerprint

Projects

OCROPODIUM

Cite this