{"title":"Digitalkoot: electrifying the finnish cultural heritage","authors":"Ville Miettinen","doi":"10.1145/2064058.2064071","DOIUrl":null,"url":null,"abstract":"In this talk we present Digitalkoot, a system for correcting errors in Optical Character Recognition (OCR) processing of old text materials through the use of crowdsourcing. By turning the labor-intensive part into simple games, we have been able to attract a large crowd of tens of thousands of voluntary workers to donate their time for the cause.\n Digitalkoot was created for the specific purpose of helping to digitize the newspaper archives of the National Library of Finland. We demonstrate how even untrained people can reach very high accuracy in a crowdsourced OCR process, and how we were able to overcome the design challenges related to attracting and managing a large pool of workers.","PeriodicalId":258166,"journal":{"name":"Workshop on Research Advances in Large Digital Book Repositories","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Workshop on Research Advances in Large Digital Book Repositories","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2064058.2064071","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
In this talk we present Digitalkoot, a system for correcting errors in Optical Character Recognition (OCR) processing of old text materials through the use of crowdsourcing. By turning the labor-intensive part into simple games, we have been able to attract a large crowd of tens of thousands of voluntary workers to donate their time for the cause.
Digitalkoot was created for the specific purpose of helping to digitize the newspaper archives of the National Library of Finland. We demonstrate how even untrained people can reach very high accuracy in a crowdsourced OCR process, and how we were able to overcome the design challenges related to attracting and managing a large pool of workers.