Header

UZH-Logo

Maintenance Infos

Crowdsourcing the OCR Ground Truth of a German and French Cultural Heritage Corpus


Clematide, Simon; Furrer, Lenz; Volk, Martin (2018). Crowdsourcing the OCR Ground Truth of a German and French Cultural Heritage Corpus. Journal for Language Technology and Computational Linguistics (JLCL), 33(1):25-47.

Abstract

Crowdsourcing approaches for post-correction of OCR output (Optical Character Recognition) have been successfully applied to several historical text collections. We report on our crowd-correction platform Kokos, which we built to improve the OCR quality of the digitized yearbooks of the Swiss Alpine Club (SAC) from the 19th century. This multilingual heritage corpus consists of Alpine texts mainly written in German and French, all typeset in Antiqua font. Finding and engaging volunteers for correcting large amounts of pages into high quality text requires a carefully designed user interface, an easy-to-use workflow, and continuous efforts for keeping the participants motivated. More than 180,000 characters on about 21,000 pages were corrected by volunteers in about 7 months, achieving an OCR ground truth with a systematically evaluated accuracy of 99.7 on the word level. The crowdsourced OCR ground truth and the corresponding original OCR recognition results from Abbyy FineReader for each page are available as a resource for machine learning and evaluation. Additionally, the scanned images (300 dpi) of all pages are included to enable tests with other OCR software.

Abstract

Crowdsourcing approaches for post-correction of OCR output (Optical Character Recognition) have been successfully applied to several historical text collections. We report on our crowd-correction platform Kokos, which we built to improve the OCR quality of the digitized yearbooks of the Swiss Alpine Club (SAC) from the 19th century. This multilingual heritage corpus consists of Alpine texts mainly written in German and French, all typeset in Antiqua font. Finding and engaging volunteers for correcting large amounts of pages into high quality text requires a carefully designed user interface, an easy-to-use workflow, and continuous efforts for keeping the participants motivated. More than 180,000 characters on about 21,000 pages were corrected by volunteers in about 7 months, achieving an OCR ground truth with a systematically evaluated accuracy of 99.7 on the word level. The crowdsourced OCR ground truth and the corresponding original OCR recognition results from Abbyy FineReader for each page are available as a resource for machine learning and evaluation. Additionally, the scanned images (300 dpi) of all pages are included to enable tests with other OCR software.

Statistics

Downloads

95 downloads since deposited on 01 Feb 2019
19 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Uncontrolled Keywords:ocr; crowdsourcing
Language:English
Date:2018
Deposited On:01 Feb 2019 15:45
Last Modified:25 Sep 2019 00:07
Publisher:Gesellschaft für Sprachtechnologie und Computerlinguistik (GSCL)
ISSN:0175-1336
Additional Information:URL for Volume: https://jlcl.org/content/2-allissues/1-heft1-2018/jlcl-2018-1.pdf ISSN 2190-6858
OA Status:Green
Official URL:https://jlcl.org/content/2-allissues/1-heft1-2018/jlcl_2018-1_2.pdf
Project Information:
  • Content: Published Version
  • Language: English
  • Licence: Creative Commons: Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)