{"id":698,"date":"2017-05-29T08:11:38","date_gmt":"2017-05-29T08:11:38","guid":{"rendered":"http:\/\/statutes.org.uk\/site\/?p=698"},"modified":"2017-05-29T08:11:39","modified_gmt":"2017-05-29T08:11:39","slug":"automatic-correction-of-ocr","status":"publish","type":"post","link":"https:\/\/statutes.org.uk\/site\/automatic-correction-of-ocr\/","title":{"rendered":"Automatic correction of OCR"},"content":{"rendered":"<p>A milestone: I have begun automatically correcting the OCR errors in the 46 volumes of Danby Pickering&#8217;s &#8216;Statutes At Large&#8217;, and have uploaded the improved text to <a href=\"https:\/\/github.com\/Anterotesis\/statutes\/tree\/master\/Pickering\">Github<\/a>.<\/p>\n<p>Given the quantity of text I&#8217;m dealing with &#8211; the Pickering series alone amounts to over fifteen million words &#8211; correcting each volume &#8216;by hand&#8217; is obviously impractical. Bulk &#8216;find and replace&#8217; is an improvement, but still not fast enough to be practical.<\/p>\n<p>Such repetitive tasks are grist to the digital mill. So, using <a href=\"https:\/\/dl.dropboxusercontent.com\/u\/4713959\/BestLcOCRRules.txt\">this list of common OCR errors<\/a>, augmented with others I&#8217;ve found, and a one line bash script, automatic improvement of the texts has commenced.<\/p>\n<p>The results are obviously an improvement. Nevertheless, the texts still aren&#8217;t great. There are still many spelling errors. As I used spaces as separators, words with punctuation attached are uncorrected. The many problems arising from layout are still to be faced.<\/p>\n<p>But this is an important step forward.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>A milestone: I have begun automatically correcting the OCR errors in the 46 volumes of Danby Pickering&#8217;s &#8216;Statutes At Large&#8217;, and have uploaded the improved text to Github. Given the quantity of text I&#8217;m dealing with &#8211; the Pickering series alone amounts to over fifteen million words &#8211; correcting each volume &#8216;by hand&#8217; is obviously [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":"","jetpack_post_was_ever_published":false},"categories":[1],"tags":[],"class_list":["post-698","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/statutes.org.uk\/site\/wp-json\/wp\/v2\/posts\/698","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/statutes.org.uk\/site\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/statutes.org.uk\/site\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/statutes.org.uk\/site\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/statutes.org.uk\/site\/wp-json\/wp\/v2\/comments?post=698"}],"version-history":[{"count":0,"href":"https:\/\/statutes.org.uk\/site\/wp-json\/wp\/v2\/posts\/698\/revisions"}],"wp:attachment":[{"href":"https:\/\/statutes.org.uk\/site\/wp-json\/wp\/v2\/media?parent=698"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/statutes.org.uk\/site\/wp-json\/wp\/v2\/categories?post=698"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/statutes.org.uk\/site\/wp-json\/wp\/v2\/tags?post=698"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}