Genevi\u00e8ve Cron of the Bibliotheque Nationale de France (BnF) begins by discussing the BNF’s digital library: Gallica.\u00a0 A million documents digitised since 1992, with OCR as standard since 2005.\u00a0 OCR accuracy for newspapers is 98% on word level, but results are much more varied – from 60% up. For books, the average accuracy lies at 90%.<\/p>\n
<\/p>\n[slideshare id=4138323&doc=bratislavaws-cron-bnf-usecases-100518090456-phpapp02]\n
http:\/\/vimeo.com\/11833984<\/p>\n
She describes users of digital services: mostly French or Francophone; special access needs (vision impairment).\u00a0 Queries about digital store go up every year; most queries relate to content rather than bibliographic information.\u00a0 Content queries split into thematic, geographic, history, genealogy, newspapers.<\/p>\n
Genevi\u00e8ve goes on to describe the Gallica workflow: a volume is OCR’d; some books sent straight to store; but newspapers are manually corrected by service provider, some other books are manually corrected to reach almost 100% accuracy.\u00a0 As a validation tool for manually corrected text, ABBYY FineReader is used.\u00a0 OCR is useful when words in user queries are not in bibliographic data – hence subject spread of content queries.\u00a0 She outlines the Wikimedia\/BnF Collaborative Correction plan: going for 100% accuracy through user collaboration.\u00a0 Text-to-speech and epub projects in progress.\u00a0 Creation of groundtruthed datasets within IMPACT to aid further research into improving OCR accuracy.<\/p>\n
Niall Anderson, BL + Mark-Oliver Fischer, BSB Genevi\u00e8ve Cron of the Bibliotheque Nationale de France (BnF) begins by discussing the BNF’s digital library: Gallica.\u00a0 A million documents digitised since 1992, with OCR as standard since 2005.\u00a0 OCR accuracy for newspapers is 98% on word level, but results are much more varied – from 60% up. For books, the average accuracy lies at … Continue reading “Use of digitised and OCRed text collections by end\u00a0users”<\/span><\/a><\/p>\n","protected":false},"author":4217,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[154],"tags":[],"class_list":["post-2701","post","type-post","status-publish","format-standard","hentry","category-discussions"],"acf":[],"_links":{"self":[{"href":"https:\/\/digitisation.eu\/index.php?rest_route=\/wp\/v2\/posts\/2701","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/digitisation.eu\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/digitisation.eu\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/digitisation.eu\/index.php?rest_route=\/wp\/v2\/users\/4217"}],"replies":[{"embeddable":true,"href":"https:\/\/digitisation.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2701"}],"version-history":[{"count":0,"href":"https:\/\/digitisation.eu\/index.php?rest_route=\/wp\/v2\/posts\/2701\/revisions"}],"wp:attachment":[{"href":"https:\/\/digitisation.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2701"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/digitisation.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2701"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/digitisation.eu\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2701"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"