{"id":6958,"date":"2026-03-01T23:19:36","date_gmt":"2026-03-01T14:19:36","guid":{"rendered":"https:\/\/jfs.or.jp\/jfs-cs\/?p=6958"},"modified":"2026-04-07T22:14:48","modified_gmt":"2026-04-07T13:14:48","slug":"web-ocr-ndl-01","status":"publish","type":"post","link":"https:\/\/jfs.or.jp\/jfs-cs\/web-ocr-ndl-01\/","title":{"rendered":"\u56fd\u7acb\u56fd\u4f1a\u56f3\u66f8\u9928\u304cWeb\u3067\u52d5\u304fPDF\u7528OCR\u3092\u63d0\u4f9b\u958b\u59cb"},"content":{"rendered":"<h3><span class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc\">NDLOCR-Lite \u3092Web\u30d6\u30e9\u30a6\u30b6\u306b\u79fb\u690d\u3057\u305f\u300cNDLOCR-Lite Web\u300d\u3092\u516c\u958b<\/span><\/h3>\n<p><span class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc\">\u00a0<\/span><a class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-poiln3 r-1wvb978 r-1loqt21\" dir=\"ltr\" role=\"link\" href=\"https:\/\/t.co\/IJIIAewqUO\" target=\"_blank\" rel=\"noopener noreferrer nofollow\"><span class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc r-qlhcfr r-19qo34d r-qvk6io r-orgf3d r-u8s1d\" aria-hidden=\"true\">https:\/\/<\/span>ndlocr-liteweb.netlify.app<\/a><\/p>\n<h3>\u5229\u7528\u65b9\u6cd5<\/h3>\n<p><span style=\"color: #ff0000;\"><strong>\u4e0a\u8a18\u30b5\u30a4\u30c8\u8868\u793a\u3000\u2192\u3000PDF\u30fbJPEG\u306a\u3069\u753b\u50cf\u30d5\u30a1\u30a4\u30eb\u30fbTIFF\u3092\u30c9\u30ed\u30c3\u30d7\u304bCtrl\uff0bV\u3067\u8cbc\u308a\u4ed8\u3051\u3000\u2192\u3000\u5909\u63db<\/strong><\/span><\/p>\n<p>OCR\u7d50\u679c\u306f\u3001\u53f3\u6b04\u306b\u8868\u793a\u3055\u308c\u308b\u3002\u30b3\u30d4\u30fc\u304bDownload\u3059\u308b\u3002<br \/>\n\u30da\u30fc\u30b8\u3054\u3068\u306bOCR\u3055\u308c\u308b\u3088\u3046\u3067\u3001<strong>\u300c\u5168\u3066\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u300d\u3092\u9078\u629e\u30af\u30ea\u30c3\u30af\u3059\u308b\u3068\u3001\u5168\u90e8\u306e\u30c6\u30ad\u30b9\u30c8\u304c\u4e00\u3064\u306e\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u306b\u307e\u3068\u3081\u3089\u308c\u3066\u3044\u308b\u3002<\/strong><\/p>\n<p>\u30c6\u30b9\u30c8\u3057\u3066\u307f\u305f\u3089\u3001\u30a8\u30af\u30bb\u30eb\u5f62\u5f0f\u306e\u5834\u5408\u306b\u306f\u3001\u8868\u306e\u884c\u306e\u30bb\u30eb\u304c\u9806\u306b\u306a\u3063\u3066\u3044\u308b\u5834\u5408\u3068\u3001\u7e26\u30bb\u30eb\u304c\u307e\u3068\u3081\u3089\u308c\u3066\u3044\u308b\u5834\u5408\u3068\u304c\u6df7\u5728\u3057\u3066\u3044\u308b\u306a\u3069\u3001\u305d\u306e\u5f8c\u306e\u7de8\u96c6\u304c\u5fc5\u8981\u306a\u5834\u5408\u304c\u3042\u308b\u3088\u3046\u3060\u3002<br \/>\n\u8868\u5f62\u5f0f\u3067\u306a\u3044\u5834\u5408\u306f\u3001\u4f7f\u3044\u3084\u3059\u3044\u3002<br \/>\n\u3000<\/p>\n<p><span style=\"font-size: 16px;\"><strong>\u56fd\u7acb\u56fd\u4f1a\u56f3\u66f8\u9928\u304c\u3001\u6240\u8535\u3059\u308b\u5927\u91cf\u306ePDF\u6587\u66f8\u304b\u3089\u6587\u5b57\u62bd\u51fa\u3067\u304d\u308b<span style=\"color: #ff0000;\">Web\u30a2\u30d7\u30ea<\/span>\u3092\u63d0\u4f9b\u958b\u59cb<\/strong><\/span>\u3002<br \/>\n\u30c6\u30b9\u30c8\u3057\u305f\u7d50\u679c\u3001\u9023\u7d9a\u3057\u305f\u6570\u5b570\u306a\u3069\u3092\u53d6\u308a\u3053\u307c\u3059\u3053\u3068\u304c\u3042\u308a\u307e\u3059\u3002<br \/>\n\u5229\u7528\u306b\u306f\u3001\u7d50\u679c\u306e\u78ba\u8a8d\u304c\u5fc5\u8981\u3067\u3059\u304c\u3001\u591a\u304f\u306e\u30da\u30fc\u30b8\u3092\u3082\u3064PDF\u304b\u3089OCR\u3057\u3066\u304f\u308c\u308b\u30d5\u30ea\u30fc\u30a2\u30d7\u30ea\u304c\u5c11\u306a\u3044\u4e2d\u3067\u306f\u8cb4\u91cd\u3067\u3059\u3002<\/p>\n<p><span class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc\"><span style=\"color: #ff0000;\"><strong>\u30d6\u30e9\u30a6\u30b6\u4e0a\u3067\u753b\u50cf\u3084PDF\u306eOCR\u51e6\u7406<\/strong><\/span>\u304c\u3067\u304d\u307e\u3059\u3002 <br \/>\nWeb\u30a2\u30d7\u30ea\u3067\u306f\u3042\u308a\u307e\u3059\u304c\u30ed\u30fc\u30ab\u30eb\u3067\u51e6\u7406\u304c\u5b8c\u7d50\u3059\u308b\u306e\u3067\u3001\u753b\u50cf\u3084\u8a8d\u8b58\u30c6\u30ad\u30b9\u30c8\u304c\u5916\u90e8\u306b\u9001\u4fe1\u3055\u308c\u308b\u3053\u3068\u306f\u3042\u308a\u307e\u305b\u3093<\/span><\/p>\n<p>Windows\u6a19\u6e96\u6dfb\u4ed8\u306eSnipping Tool\u3000\u3068\u540c\u69d8\u306eOCR\u3067\u3059\u304c\u3001PDF\u306a\u3069\u591a\u30da\u30fc\u30b8\u306e\u3082\u306e\u3067\u3082\u3001\u4e00\u62ec\u3057\u3066OCR\u3067\u6587\u5b57\u62bd\u51fa\u304c\u3067\u304d\u307e\u3059\u3002<br \/>\n\u306a\u304a\u3001\u30d1\u30bd\u30b3\u30f3\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u7248\u3067\u306f\u3000PDF\u306e\u30da\u30fc\u30b8\u3054\u3068\u306b\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u3092\u9023\u756a\u540d\u3067\u4f5c\u6210\u3059\u308b\u306e\u3067\u3001\u6587\u66f8\u5316\u306b\u306f\u96c6\u7d04\u3059\u308b\u6a5f\u80fd\u304c\u5fc5\u8981\u3068\u306a\u308a\u307e\u3059\u3002<br \/>\n\u8907\u6570\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u3092\u4e00\u3064\u306b\u307e\u3068\u3081\u308b\u65b9\u6cd5\u306b\u306f\u3001<br \/>\n\u30fb\u30a2\u30d7\u30ea\u3092\u4f7f\u3046\u3001<br \/>\n\u30fb\u30a8\u30af\u30bb\u30eb\u306a\u3069\u306e\u30de\u30af\u30ed\u306a\u3069\u3092\u5229\u7528<br \/>\n\u30fbPython\u306e\u30d7\u30ed\u30b0\u30e9\u30e0\u3067\u884c\u3046\uff08\u4e0b\u306b\u30d7\u30ed\u30b0\u30e9\u30e0\u4f8b\u3042\u308a\uff09<br \/>\n\u30fbWindows\u3000\u30b3\u30de\u30f3\u30c9\u3000Dos\u3067\u30d5\u30a9\u30eb\u30c0\u30fc\u5185\u306e\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u3092\u7d50\u5408\u3057\u305f\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u308b<br \/>\n\u3000\u3000<span class=\"hljs-built_in\">copy<\/span> *.txt combined.txt<br \/>\n\u30fbGemini\u306b\u547d\u4ee4\u3059\u308b\uff08\u6570\u30d5\u30a1\u30a4\u30eb\u306a\u3089\u7c21\u5358\uff09<br \/>\n\u305d\u306e\u4ed6\u3044\u308d\u3044\u308d\u3042\u308a\u3002<\/p>\n<h3>\u30a2\u30d7\u30ea\u306e\u7d39\u4ecb\u8a18\u4e8b\u7d39\u4ecb\uff08X\u6295\u7a3f\uff09<\/h3>\n<div class=\"css-175oi2r r-18u37iz r-136ojw6\">\n<div class=\"css-175oi2r r-1iusvr4 r-16y2uox r-1777fci\">\n<div class=\"css-175oi2r r-zl2h9q\">\n<div class=\"css-175oi2r r-k4xj1c r-18u37iz r-1wtj0ep\">\n<div class=\"css-175oi2r r-1d09ksm r-18u37iz r-1wbh5a2\">\n<div class=\"css-175oi2r r-1wbh5a2 r-dnmrzs r-1ny4l3l\">\n<div id=\"id__2u1866svxcb\" class=\"css-175oi2r r-1wbh5a2 r-dnmrzs r-1ny4l3l\" data-testid=\"User-Name\">\n<div class=\"css-175oi2r r-1awozwy r-18u37iz r-1wbh5a2 r-dnmrzs\">\n<div class=\"css-175oi2r r-1wbh5a2 r-dnmrzs\">\n<div class=\"css-175oi2r r-1awozwy r-18u37iz r-1wbh5a2 r-dnmrzs\">\n<div class=\"css-146c3p1 r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc r-a023e6 r-rjixqe r-b88u0q r-1awozwy r-6koalj r-1udh08x r-3s2u2q\" dir=\"ltr\"><span class=\"css-1jxf684 r-dnmrzs r-1udh08x r-1udbk01 r-3s2u2q r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc\"><span class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc\">Yuta Hashimoto\u3000<\/span><\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"css-175oi2r r-18u37iz r-1wbh5a2\">\n<div class=\"css-175oi2r r-1d09ksm r-18u37iz r-1wbh5a2\">\n<div class=\"css-175oi2r r-1wbh5a2 r-dnmrzs\">\n<div class=\"css-146c3p1 r-dnmrzs r-1udh08x r-1udbk01 r-3s2u2q r-bcqeeo r-1ttztb7 r-qvutc0 r-37j5jr r-a023e6 r-rjixqe r-16dba41 r-18u37iz r-1wvb978\" dir=\"ltr\"><span class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc\">@yuta1984<\/span><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"css-175oi2r r-1kkk96v\">\n<div class=\"css-175oi2r r-1awozwy r-18u37iz r-1cmwbt1 r-1wtj0ep\">\n<div class=\"css-175oi2r r-18u37iz r-1h0z5md\"><a href=\"https:\/\/x.com\/yuta1984\/status\/2026953635519938832\">https:\/\/x.com\/yuta1984\/status\/2026953635519938832<\/a><\/div>\n<div class=\"css-175oi2r r-1awozwy r-6koalj r-18u37iz\">\n<div class=\"css-175oi2r\">\n<div class=\"css-175oi2r r-18u37iz r-1h0z5md\">\u00a0<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"css-175oi2r\">\n<div class=\"css-175oi2r\">\n<div class=\"css-175oi2r r-1s2bzr4\">\n<div id=\"id__ghtxa131nuh\" class=\"css-146c3p1 r-bcqeeo r-1ttztb7 r-qvutc0 r-37j5jr r-1inkyih r-16dba41 r-bnwqim r-135wba7\" dir=\"auto\" lang=\"ja\" data-testid=\"tweetText\"><span class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc\">NDLOCR-Lite \u3092Web\u30d6\u30e9\u30a6\u30b6\u306b\u79fb\u690d\u3057\u305f\u300cNDLOCR-Lite Web\u300d\u3092\u516c\u958b\u3057\u307e\u3057\u305f\u3002 <\/span><a class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-poiln3 r-1wvb978 r-1loqt21\" dir=\"ltr\" role=\"link\" href=\"https:\/\/t.co\/IJIIAewqUO\" target=\"_blank\" rel=\"noopener noreferrer nofollow\"><span class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc r-qlhcfr r-19qo34d r-qvk6io r-orgf3d r-u8s1d\" aria-hidden=\"true\">https:\/\/<\/span>ndlocr-liteweb.netlify.app<\/a><span class=\"css-1jxf684 r-bcqeeo r-1ttztb7 r-qvutc0 r-1tl8opc\"> \u30d6\u30e9\u30a6\u30b6\u4e0a\u3067\u624b\u8efd\u306b\u753b\u50cf\u3084PDF\u306eOCR\u51e6\u7406\u3092\u8a66\u3059\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002 Web\u30a2\u30d7\u30ea\u3067\u306f\u3042\u308a\u307e\u3059\u304c\u30ed\u30fc\u30ab\u30eb\u3067\u51e6\u7406\u304c\u5b8c\u7d50\u3059\u308b\u306e\u3067\u3001\u753b\u50cf\u3084\u8a8d\u8b58\u30c6\u30ad\u30b9\u30c8\u304c\u5916\u90e8\u306b\u9001\u4fe1\u3055\u308c\u308b\u3053\u3068\u306f\u3042\u308a\u307e\u305b\u3093\uff08\u672c\u5bb6\u3068\u540c\u69d8\uff09\u3002<\/span><\/div>\n<\/div>\n<\/div>\n<div dir=\"auto\" lang=\"ja\" data-testid=\"tweetText\">\u00a0<\/div>\n<\/div>\n<p>&nbsp;<\/p>\n<h3>\u30a2\u30d7\u30ea\u306e\u7d39\u4ecb\u8a18\u4e8b\u3000\u56fd\u7acb\u56fd\u4f1a\u56f3\u66f8\u9928\u30b5\u30a4\u30c8<\/h3>\n<p><a href=\"https:\/\/lab.ndl.go.jp\/news\/2025\/2026-02-24\/\">https:\/\/lab.ndl.go.jp\/news\/2025\/2026-02-24\/<\/a><\/p>\n<p>2026\u5e7402\u670824\u65e5<\/p>\n<h2 id=\"ndlocr-lite\u306e\u516c\u958b\u306b\u3064\u3044\u3066\">NDLOCR-Lite\u306e\u516c\u958b\uff08\u30d1\u30bd\u30b3\u30f3\u7b49\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u5229\u7528\uff09<\/h2>\n<p><a href=\"https:\/\/github.com\/ndl-lab\">NDL\u30e9\u30dc\u516c\u5f0fGitHub<\/a>\uff08\u5916\u90e8\u30b5\u30a4\u30c8\uff09\u304b\u3089\u3001NDLOCR-Lite\u3092\u516c\u958b\u3057\u307e\u3057\u305f\u3002<\/p>\n<p>NDLOCR-Lite\u306f\u3001NDLOCR\u306e\u8efd\u91cf\u7248\u3092\u76ee\u6307\u3057\u3066\u958b\u767a\u3057\u305fOCR\u3067\u3042\u308a\u3001\u30ce\u30fc\u30c8\u30d1\u30bd\u30b3\u30f3\u7b49\u306e\u4e00\u822c\u7684\u306a\u5bb6\u5ead\u7528\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u3084OS\u74b0\u5883\u3067\u3001<span style=\"color: #0000ff;\"><strong>\u56f3\u66f8\u3084\u96d1\u8a8c\u3068\u3044\u3063\u305f\u8cc7\u6599\u306e\u30c7\u30b8\u30bf\u30eb\u5316\u753b\u50cf\u304b\u3089\u30c6\u30ad\u30b9\u30c8\u30c7\u30fc\u30bf\u304c\u4f5c\u6210\u3067\u304d\u308bOCR<\/strong><\/span>\u3067\u3059\u3002<\/p>\n<p>GPU\uff08Graphics Processing Unit\u3002\u753b\u50cf\u63cf\u753b\u7b49\u306e\u9ad8\u5ea6\u306a\u4e26\u5217\u8a08\u7b97\u3092\u51e6\u7406\u3059\u308b\u88c5\u7f6e\u3002\uff09\u3092<span style=\"color: #0000ff;\"><strong>\u5fc5\u8981\u3068\u305b\u305a\u3001\u8efd\u91cf\u306aOCR\u51e6\u7406\u304c\u53ef\u80fd<\/strong><\/span>\u3067\u3059\u3002<\/p>\n<p>\u307e\u305f\u3001NDLOCR\u304c\u4e0d\u5f97\u610f\u3068\u3057\u3066\u3044\u305f\u82f1\u6587\u3084\u624b\u66f8\u304d\u6587\u5b57\u7b49\u306b\u3064\u3044\u3066\u3082\u5b9f\u9a13\u7684\u306b\u5bfe\u5fdc\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>\u5229\u7528\u5b9f\u4f8b\u6620\u50cf\u304c\u4e0b\u8a18<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/lab.ndl.go.jp\/news\/2025\/0224\/image0.png\" alt=\"OCR\u7d50\u679c\u3092\u793a\u3057\u305f\u753b\u50cf\" width=\"60%\" \/><\/p>\n<p>\u753b\u50cf\u306e\u51fa\u5178\uff1a\u82a5\u5ddd\u7adc\u4e4b\u4ecb \u8457\u300e\u5080\u5121\u5e2b\u300f,\u65b0\u6f6e\u793e,1919. \u56fd\u7acb\u56fd\u4f1a\u56f3\u66f8\u9928\u30c7\u30b8\u30bf\u30eb\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u00a0<a href=\"https:\/\/dl.ndl.go.jp\/pid\/1904835\/1\/53\">https:\/\/dl.ndl.go.jp\/pid\/1904835\/1\/53<\/a>\u00a0(\u53c2\u7167 2026-02-18)<\/p>\n<p><img decoding=\"async\" src=\"https:\/\/lab.ndl.go.jp\/news\/2025\/0224\/image1.png\" alt=\"OCR\u7d50\u679c\u3092\u793a\u3057\u305f\u753b\u50cf\" width=\"60%\" \/><\/p>\n<p>\u753b\u50cf\u306e\u51fa\u5178\uff1a\u56fd\u7acb\u56fd\u4f1a\u56f3\u66f8\u9928\u7dcf\u52d9\u90e8\u7dcf\u52d9\u8ab2 \u7de8\u300e\u56fd\u7acb\u56fd\u4f1a\u56f3\u66f8\u9928\u5e74\u5831\u300f\u662d\u548c29\u5e74\u5ea6,\u56fd\u7acb\u56fd\u4f1a\u56f3\u66f8\u9928,1955. \u56fd\u7acb\u56fd\u4f1a\u56f3\u66f8\u9928\u30c7\u30b8\u30bf\u30eb\u30b3\u30ec\u30af\u30b7\u30e7\u30f3\u00a0<a href=\"https:\/\/dl.ndl.go.jp\/pid\/3048009\/1\/16\">https:\/\/dl.ndl.go.jp\/pid\/3048009\/1\/16<\/a>\u00a0(\u53c2\u7167 2026-02-18)<\/p>\n<h3 id=\"ndlocr-lite\">NDLOCR-Lite<\/h3>\n<ul>\n<li>GitHub\u30ea\u30dd\u30b8\u30c8\u30ea\uff08<a href=\"https:\/\/github.com\/ndl-lab\/ndlocr-lite\">https:\/\/github.com\/ndl-lab\/ndlocr-lite<\/a>\u00a0\uff09<\/li>\n<\/ul>\n<p>\u3053\u308c\u307e\u3067\u56fd\u7acb\u56fd\u4f1a\u56f3\u66f8\u9928\u304c\u516c\u958b\u3057\u3066\u3044\u305fNDLOCR(\u5916\u90e8\u30b5\u30a4\u30c8)\u3067\u306f\u3001\u5b9f\u884c\u74b0\u5883\u306bGPU\u3092\u5fc5\u9808\u3068\u3057\u3066\u3044\u307e\u3057\u305f\u304c\u3001\u300cNDLOCR-Lite\u300d\u3067\u306fGPU\u306f\u4e0d\u8981\u3068\u306a\u3063\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>\u3042\u308f\u305b\u3066\u3001\u30c7\u30b9\u30af\u30c8\u30c3\u30d7\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u3092\u7528\u610f\u3057\u3066\u3044\u308b\u305f\u3081\u3001\u30de\u30a6\u30b9\u64cd\u4f5c\u306e\u307f\u3067\u7c21\u5358\u306b\u304a\u4f7f\u3044\u3044\u305f\u3060\u3051\u307e\u3059\u3002<\/p>\n<p>Windows\uff08Windows 11\uff09\u3001Mac\uff08macOS Sequoia\uff09\u53ca\u3073Linux\uff08Ubuntu 22.04\uff09\u306e\u5404OS\u74b0\u5883\u306b\u304a\u3044\u3066\u52d5\u4f5c\u3092\u78ba\u8a8d\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n<p>\u6b21\u306eURL\u304b\u3089\u3054\u5229\u7528\u306eOS\u306b\u5408\u308f\u305b\u305f\u6700\u65b0\u7248\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u3066\u304a\u4f7f\u3044\u304f\u3060\u3055\u3044\u3002<\/p>\n<p><a href=\"https:\/\/github.com\/ndl-lab\/ndlocr-lite\/releases\">https:\/\/github.com\/ndl-lab\/ndlocr-lite\/releases<\/a><\/p>\n<p>\u4f7f\u3044\u65b9\u306b\u3064\u3044\u3066\u306f\u6b21\u306e\u30da\u30fc\u30b8\u3092\u3054\u89a7\u304f\u3060\u3055\u3044\u3002<\/p>\n<p><a href=\"https:\/\/lab.ndl.go.jp\/data_set\/ndlocrlite-usage\/\">NDLOCR-Lite\u306e\u4f7f\u3044\u65b9<\/a><\/p>\n<p>NDLOCR-Lite\u306f\u3001\u56fd\u7acb\u56fd\u4f1a\u56f3\u66f8\u9928\u304cCC BY 4.0\u30e9\u30a4\u30bb\u30f3\u30b9\u3067\u516c\u958b\u3057\u3066\u3044\u307e\u3059\u3002\u8a73\u7d30\u306fGitHub\u306eREADME\u3092\u3054\u53c2\u7167\u304f\u3060\u3055\u3044\u3002<\/p>\n<p>\u306a\u304a\u3001\u3053\u308c\u307e\u3067\u63d0\u4f9b\u3057\u3066\u3044\u305fGPU\u3092\u5fc5\u8981\u3068\u3059\u308bNDLOCR\u306b\u3064\u3044\u3066\u3082\u3001\u5f15\u304d\u7d9a\u304d\u540c\u30ea\u30dd\u30b8\u30c8\u30ea\uff08<a href=\"https:\/\/github.com\/ndl-lab\/ndlocr_cli\">https:\/\/github.com\/ndl-lab\/ndlocr_cli<\/a>\u00a0\uff09\u304b\u3089\u3054\u5229\u7528\u3044\u305f\u3060\u3051\u307e\u3059\u3002<\/p>\n<p>&nbsp;<\/p>\n<p>Web\u4e0a\u3067\u5b8c\u7d50\u3057\u3001\u8cc7\u6599\u306fPC\u5185\u3067\u5b8c\u7d50\u3059\u308b\u305d\u3046\u3067\u3001PDF\u306a\u3089\u4f55\u3067\u3082\u51e6\u7406\u3067\u304d\u308b\u305d\u3046\u3067\u3059\u3002<br \/>\n\u753b\u9762\u306e\u6587\u5b57\u3092OCR\u51e6\u7406\u3059\u308bWindows11\u306e\u6a19\u6e96\u30a2\u30d7\u30ea\u3082\u3042\u308a\u307e\u3059\u304c\u3001PDF\u6587\u66f8\u5168\u4f53\u3092\u51e6\u7406\u3059\u308b\u306e\u306f\u5927\u5909\u3067\u3059\u3002<br \/>\n\u3053\u306e\u30a2\u30d7\u30ea\u306a\u3089\u3001\u6587\u66f8\u5168\u4f53\u306e\u30c6\u30ad\u30b9\u30c8\u3092\u62bd\u51fa\u3067\u304d\u308b\u306e\u3067\u3001\u30c6\u30b9\u30c8\u3059\u308b\u610f\u5473\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n<p>\u7d39\u4ecb\u3059\u308bX\u306e\u6295\u7a3f\u3092\u3054\u7d39\u4ecb\u3057\u307e\u3059\u3002<br \/>\n\u307e\u305f\u3001Python\u5229\u7528\u3057\u305f\u30a2\u30d7\u30ea\u3082\u63d0\u4f9b\u3055\u308c\u3066\u3044\u307e\u3059\u3002\u3053\u308c\u306f\uff11G\u7a0b\u5ea6\u306e\u30e1\u30e2\u30ea\u30fc\u304c\u3042\u308c\u3070\u8efd\u304f\u52d5\u4f5c\u3059\u308b\u305d\u3046\u3067\u3059\u3002<br \/>\n\u30c6\u30b9\u30c8\u3057\u305f\u3068\u3053\u308d\u3001\u30da\u30fc\u30b8\u3054\u3068\u306e\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210\u3057\u3066\u304f\u308c\u307e\u3059\u3002<br \/>\nPython \u3067\u3001\u5168\u3066\u306e\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u3092\u8aad\u307f\u8fbc\u3093\u3067\u3001\u4e00\u3064\u306e\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u306b\u3057\u3066\u304f\u308c\u308b\u30a2\u30d7\u30ea\u3092Gemini\u304c\u4f5c\u3063\u3066\u304f\u308c\u307e\u3057\u305f\u3002<br \/>\n\u4e00\u3064\u306e\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u306b\u5165\u308c\u305f\u3082\u306e\u3092\u307e\u3068\u3081\u3066\u305d\u306e\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u306b\u4f5c\u3063\u3066\u304f\u308c\u308b\u3002<\/p>\n<p>Python program\u3000PDF\u306e\u30da\u30fc\u30b8\u5358\u4f4d\u3067\u4f5c\u6210\u3055\u308c\u305f\u30c6\u30ad\u30b9\u30c8\u30d5\u30a1\u30a4\u30eb\u3092\u7d50\u5408\u3057\u3066\u4e00\u3064\u306b\u3059\u308bPython\u3000\u30d7\u30ed\u30b0\u30e9\u30e0\u4f8b\u3067\u3059\uff08Gemini\u4f5c\u6210\u3001\u52d5\u4f5c\u78ba\u8a8d\u6e08\u307f\uff09<br \/>\n\u3000\u5bfe\u8c61\u30d5\u30a1\u30a4\u30eb\u3092\u5165\u308c\u3066\u4f5c\u696d\u3059\u308b\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u3092\u6307\u5b9a\u3059\u308b\u3053\u3068\u3082\u3067\u304d\u307e\u3059\u3002<\/p>\n<blockquote>\n<div>import glob<\/div>\n<div>\u00a0<\/div>\n<div>files = glob.glob(&#8220;*.txt&#8221;) # \u30d5\u30a9\u30eb\u30c0\u5185\u306e\u5168txt\u30d5\u30a1\u30a4\u30eb\u3092\u53d6\u5f97<\/div>\n<div>with open(&#8220;combined.txt&#8221;, &#8220;w&#8221;, encoding=&#8221;utf-8&#8243;) as outfile:<\/div>\n<div>\u00a0 \u00a0 for f in files:<\/div>\n<div>\u00a0 \u00a0 \u00a0 \u00a0 with open(f, &#8220;r&#8221;, encoding=&#8221;utf-8&#8243;) as infile:<\/div>\n<div>\u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 outfile.write(infile.read() + &#8220;\\n\\n&#8221;) # \u30d5\u30a1\u30a4\u30eb\u9593\u306b\u6539\u884c\u3092\u5165\u308c\u3066\u7d50\u5408<\/div>\n<p>&nbsp;<\/p>\n<\/blockquote>\n<div class=\"css-175oi2r r-18u37iz r-136ojw6\">\n<div class=\"css-175oi2r r-1iusvr4 r-16y2uox r-1777fci\">\n<div class=\"css-175oi2r r-zl2h9q\">\n<div class=\"css-175oi2r r-k4xj1c r-18u37iz r-1wtj0ep\">\n<div class=\"css-175oi2r r-1d09ksm r-18u37iz r-1wbh5a2\">\n<div class=\"css-175oi2r r-1wbh5a2 r-dnmrzs r-1ny4l3l\">\n<div id=\"id__2u1866svxcb\" class=\"css-175oi2r r-1wbh5a2 r-dnmrzs r-1ny4l3l\" data-testid=\"User-Name\">\n<div class=\"css-175oi2r r-1awozwy r-18u37iz r-1wbh5a2 r-dnmrzs\">\n<div class=\"css-175oi2r r-1wbh5a2 r-dnmrzs\">\n<div class=\"css-175oi2r r-1awozwy r-18u37iz r-1wbh5a2 r-dnmrzs\">\u00a0<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"css-175oi2r\">\n<div class=\"css-175oi2r\">\n<div class=\"css-175oi2r r-1s2bzr4\">\n<div id=\"id__ghtxa131nuh\" class=\"css-146c3p1 r-bcqeeo r-1ttztb7 r-qvutc0 r-37j5jr r-1inkyih r-16dba41 r-bnwqim r-135wba7\" dir=\"auto\" lang=\"ja\" data-testid=\"tweetText\">\u00a0<\/div>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"NDLOCR-Lite \u3092Web\u30d6\u30e9\u30a6\u30b6\u306b\u79fb\u690d\u3057\u305f\u300cNDLOCR-Lite Web\u300d\u3092\u516c\u958b \u00a0https:\/\/ndlocr-liteweb.netlify.app \u5229\u7528\u65b9\u6cd5 \u4e0a\u8a18\u30b5\u30a4\u30c8\u8868\u793a\u3000\u2192\u3000PDF\u30fbJPEG\u306a\u3069\u753b\u50cf\u30d5 &#8230;","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"vk-ltc-link":"","vk-ltc-target":"0","footnotes":""},"categories":[24],"tags":[],"class_list":["post-6958","post","type-post","status-publish","format-standard","hentry","category-iot-it"],"_links":{"self":[{"href":"https:\/\/jfs.or.jp\/jfs-cs\/wp-json\/wp\/v2\/posts\/6958","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jfs.or.jp\/jfs-cs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jfs.or.jp\/jfs-cs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jfs.or.jp\/jfs-cs\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/jfs.or.jp\/jfs-cs\/wp-json\/wp\/v2\/comments?post=6958"}],"version-history":[{"count":7,"href":"https:\/\/jfs.or.jp\/jfs-cs\/wp-json\/wp\/v2\/posts\/6958\/revisions"}],"predecessor-version":[{"id":7217,"href":"https:\/\/jfs.or.jp\/jfs-cs\/wp-json\/wp\/v2\/posts\/6958\/revisions\/7217"}],"wp:attachment":[{"href":"https:\/\/jfs.or.jp\/jfs-cs\/wp-json\/wp\/v2\/media?parent=6958"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jfs.or.jp\/jfs-cs\/wp-json\/wp\/v2\/categories?post=6958"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jfs.or.jp\/jfs-cs\/wp-json\/wp\/v2\/tags?post=6958"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}