Open Source Historical OCR: The OCRopodium Project

Research output: Chapter in Book/Report/Conference proceedingConference paper

6 Citations (Scopus)

Abstract

In this paper we present some initial results of OCRopodium project to build a scalable workflow for OCR of historical collections. Large-scale digitisation projects dealing with text-based historical material face challenges that are not well-catered-to by commercial software. Open source tools allow for better customisation to match these requirements, particularly with regard to character model training and per-project language modelling.
Original languageEnglish
Title of host publicationResearch and Advanced Technology for Digital Libraries
Subtitle of host publicationProceedings of the 14th European Conference, ECDL 2010
EditorsMounia Lalmas, Joemon Jose, Andreas Rauber, Fabrizio Sebastiani, Ingo Frommholz
Place of PublicationBerlin and New York
PublisherSpringer
Pages522 - 525
Number of pages4
VolumeN/A
EditionN/A
ISBN (Print)9783642154638
DOIs
Publication statusPublished - 2010
Event14th European Conference on Research and Advanced Technology for Digital Libraries - Glasgow, SCOTLAND
Duration: 6 Sept 201010 Sept 2010

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
Volume6273
ISSN (Print)0302-9743

Conference

Conference14th European Conference on Research and Advanced Technology for Digital Libraries
CityGlasgow, SCOTLAND
Period6/09/201010/09/2010

Fingerprint

Dive into the research topics of 'Open Source Historical OCR: The OCRopodium Project'. Together they form a unique fingerprint.

Cite this