{"id":15702,"date":"2026-08-23T11:54:08","date_gmt":"2026-08-23T09:54:08","guid":{"rendered":"https:\/\/wp.jochen.hayek.name\/blog-de\/?p=15702"},"modified":"2026-08-23T11:54:08","modified_gmt":"2026-08-23T09:54:08","slug":"ocr-postprocessing","status":"publish","type":"post","link":"https:\/\/wp.jochen.hayek.name\/blog-de\/2026\/08\/23\/ocr-postprocessing\/","title":{"rendered":"sicher eines meiner nerdigsten Hobbys \u00fcberhaupt: OCR-Postprocessing \u2013 quasi digitale Arch\u00e4ologie der besonderen Art"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Also vorher nehme ich ein &#8220;Bild&#8221; und lasse z.B. durch diesen Web-Service ein PDF mit &#8220;selektierbarem Text&#8221; daraus machen:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/tools.pdf24.org\/en\/ocr-pdf\">https:\/\/tools.pdf24.org\/en\/ocr-pdf<\/a><\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">Danach erzeuge ich mit &#8220;pdftohtml -xml&#8221; editierbaren XML-Text daraus.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Dann bem\u00fche ich, den Text zu restaurieren.<\/p>\n\n\n","protected":false},"excerpt":{"rendered":"<p>Also vorher nehme ich ein &#8220;Bild&#8221; und lasse z.B. durch diesen Web-Service ein PDF mit &#8220;selektierbarem Text&#8221; daraus machen: Danach erzeuge ich mit &#8220;pdftohtml -xml&#8221; editierbaren XML-Text daraus. Dann bem\u00fche ich, den Text zu restaurieren.<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"advanced_seo_description":"","jetpack_seo_html_title":"","jetpack_seo_noindex":false,"jetpack_seo_schema_type":"","_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_post_was_ever_published":false,"_share_on_mastodon":"0"},"categories":[360,383,384],"tags":[],"class_list":["post-15702","post","type-post","status-publish","format-standard","hentry","category-ocr","category-pdf","category-pdf-scraping"],"share_on_mastodon":{"url":"","error":""},"jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/paO0l8-45g","jetpack_likes_enabled":true,"amp_enabled":true,"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/wp.jochen.hayek.name\/blog-de\/wp-json\/wp\/v2\/posts\/15702","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wp.jochen.hayek.name\/blog-de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wp.jochen.hayek.name\/blog-de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wp.jochen.hayek.name\/blog-de\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/wp.jochen.hayek.name\/blog-de\/wp-json\/wp\/v2\/comments?post=15702"}],"version-history":[{"count":1,"href":"https:\/\/wp.jochen.hayek.name\/blog-de\/wp-json\/wp\/v2\/posts\/15702\/revisions"}],"predecessor-version":[{"id":15703,"href":"https:\/\/wp.jochen.hayek.name\/blog-de\/wp-json\/wp\/v2\/posts\/15702\/revisions\/15703"}],"wp:attachment":[{"href":"https:\/\/wp.jochen.hayek.name\/blog-de\/wp-json\/wp\/v2\/media?parent=15702"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wp.jochen.hayek.name\/blog-de\/wp-json\/wp\/v2\/categories?post=15702"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wp.jochen.hayek.name\/blog-de\/wp-json\/wp\/v2\/tags?post=15702"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}