{"id":102437,"date":"2021-12-01T15:37:06","date_gmt":"2021-12-01T13:37:06","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/reliz-sistemy-raspoznavaniya-teksta-tesseract-5-0"},"modified":"2021-12-01T15:37:06","modified_gmt":"2021-12-01T13:37:06","slug":"reliz-sistemy-raspoznavaniya-teksta-tesseract-5-0","status":"publish","type":"post","link":"https:\/\/prohoster.info\/fr\/blog\/news\/reliz-sistemy-raspoznavaniya-teksta-tesseract-5-0","title":{"rendered":"Publication du syst\u00e8me de reconnaissance de texte Tesseract 5.0","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>La version du syst\u00e8me de reconnaissance optique de caract\u00e8res Tesseract 4.1 a \u00e9t\u00e9 publi\u00e9e, prenant en charge la reconnaissance de caract\u00e8res UTF-8 et de textes en plus de 100 langues, y compris le russe, le kazakh, le bi\u00e9lorusse et l'ukrainien. Les r\u00e9sultats peuvent \u00eatre enregistr\u00e9s sous forme de texte brut, ainsi que dans les formats HTML (hOCR), ALTO (XML), PDF et TSV. \u00c0 l'origine, le syst\u00e8me a \u00e9t\u00e9 cr\u00e9\u00e9 entre 1985 et 1995 dans un laboratoire de la soci\u00e9t\u00e9 Hewlett Packard, le code a \u00e9t\u00e9 ouvert en 2005 sous la licence Apache et a depuis \u00e9t\u00e9 d\u00e9velopp\u00e9 avec l'aide des employ\u00e9s de Google. Les textes sources du projet sont distribu\u00e9s sous la licence Apache 2.0.      <\/p>\n<p> Tesseract comprend une utilitaire en console et une biblioth\u00e8que libtesseract pour int\u00e9grer des fonctionnalit\u00e9s de reconnaissance de texte dans d'autres applications. Parmi les interfaces GUI tierces supportant Tesseract, on peut noter gImageReader, VietOCR et YAGF. Deux moteurs de reconnaissance sont propos\u00e9s : l'un classique, qui reconna\u00eet le texte au niveau des mod\u00e8les de caract\u00e8res individuels, et l'autre, bas\u00e9 sur l'application d'un syst\u00e8me d'apprentissage machine utilisant un r\u00e9seau de neurones r\u00e9currents LSTM, optimis\u00e9 pour reconna\u00eetre des lignes enti\u00e8res et permettant d'atteindre une pr\u00e9cision significativement am\u00e9lior\u00e9e. Des mod\u00e8les pr\u00e9-entra\u00een\u00e9s sont publi\u00e9s pour 123 langues. Pour optimiser les performances, des modules utilisant OpenMP et des instructions SIMD AVX2, AVX, NEON ou SSE4.1 sont propos\u00e9s.     <\/p>\n<p>Am\u00e9liorations principales dans Tesseract 5.0 :  <\/p>\n<ul>\n<li class=\"l\"> Le changement significatif de version est d\u00fb aux modifications de l'API qui rompent la compatibilit\u00e9. En particulier, l'API publique libtesseract n'est plus li\u00e9e aux types de donn\u00e9es propri\u00e9taires GenericVector et STRING, ceux-ci \u00e9tant remplac\u00e9s dans le code par std::string et std::vector.\n<li class=\"l\"> La structure de l'arbre des sources a \u00e9t\u00e9 r\u00e9organis\u00e9e. Les fichiers d'en-t\u00eate publics ont \u00e9t\u00e9 d\u00e9plac\u00e9s dans le r\u00e9pertoire include\/tesseract.\n<li class=\"l\"> La gestion de la m\u00e9moire a \u00e9t\u00e9 remani\u00e9e, tous les appels \u00e0 malloc et free ont \u00e9t\u00e9 remplac\u00e9s par du code C++. Le code a subi une modernisation g\u00e9n\u00e9rale.\n<li class=\"l\"> Des optimisations ont \u00e9t\u00e9 ajout\u00e9es pour les architectures ARM et ARM64, utilisant des instructions ARM NEON pour acc\u00e9l\u00e9rer les calculs. Une optimisation de performance g\u00e9n\u00e9rale a \u00e9t\u00e9 r\u00e9alis\u00e9e pour toutes les architectures.\n<li class=\"l\"> De nouveaux modes d'entra\u00eenement des mod\u00e8les et de reconnaissance du texte ont \u00e9t\u00e9 mis en \u0153uvre, bas\u00e9s sur l'utilisation de calculs en virgule flottante. Ces nouveaux modes se distinguent par une performance accrue et une r\u00e9duction de la consommation de m\u00e9moire. Dans le moteur LSTM, le mode rapide float32 est activ\u00e9 par d\u00e9faut.\n<li class=\"l\"> La transition vers l'utilisation de la normalisation Unicode avec la forme NFC (Normalization Form Canonical) a \u00e9t\u00e9 r\u00e9alis\u00e9e.\n<li class=\"l\"> Une option pour configurer le niveau de d\u00e9tail des logs (\u2014loglevel) a \u00e9t\u00e9 ajout\u00e9e.\n<li class=\"l\"> Le syst\u00e8me de construction bas\u00e9 sur Autotools a \u00e9t\u00e9 repens\u00e9 et est maintenant configur\u00e9 pour une construction en mode non r\u00e9cursif.\n<li class=\"l\"> La branche \u00abmaster\u00bb dans Git a \u00e9t\u00e9 renomm\u00e9e en \u00abmain\u00bb.\n<li class=\"l\"> Ajout de la prise en charge des nouvelles versions de macOS et des syst\u00e8mes Apple bas\u00e9s sur la puce M1.<br \/>\n<br \/>Source : <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/www.opennet.ru\/opennews\/art.shtml?num=56259\">opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u041e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043d \u0440\u0435\u043b\u0438\u0437 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043e\u043f\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0442\u0435\u043a\u0441\u0442\u0430 Tesseract 4.1, \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u044e\u0449\u0435\u0439 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u0435 \u0441\u0438\u043c\u0432\u043e\u043b\u043e\u0432 UTF-8 \u0438 \u0442\u0435\u043a\u0441\u0442\u043e\u0432 \u043d\u0430 \u0431\u043e\u043b\u0435\u0435 \u0447\u0435\u043c 100 \u044f\u0437\u044b\u043a\u0430\u0445, \u0432\u043a\u043b\u044e\u0447\u0430\u044f \u0440\u0443\u0441\u0441\u043a\u0438\u0439, \u043a\u0430\u0437\u0430\u0445\u0441\u043a\u0438\u0439, \u0431\u0435\u043b\u043e\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u0438 \u0443\u043a\u0440\u0430\u0438\u043d\u0441\u043a\u0438\u0439. \u0420\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442 \u043c\u043e\u0436\u0435\u0442 \u0441\u043e\u0445\u0440\u0430\u043d\u044f\u0442\u044c\u0441\u044f \u043a\u0430\u043a \u043e\u0442\u043a\u0440\u044b\u0442\u044b\u043c \u0442\u0435\u043a\u0441\u0442\u043e\u043c, \u0442\u0430\u043a \u0438 \u0432 \u0444\u043e\u0440\u043c\u0430\u0442\u0430\u0445 HTML (hOCR), ALTO (XML), PDF \u0438 TSV. \u0418\u0437\u043d\u0430\u0447\u0430\u043b\u044c\u043d\u043e \u0441\u0438\u0441\u0442\u0435\u043c\u0430 \u0431\u044b\u043b\u0430 \u0441\u043e\u0437\u0434\u0430\u043d\u0430 \u0432 1985-1995 \u0433\u043e\u0434\u0430\u0445 \u0432 \u043b\u0430\u0431\u043e\u0440\u0430\u0442\u043e\u0440\u0438\u0438 \u043a\u043e\u043c\u043f\u0430\u043d\u0438\u0438 Hewlett Packard, \u0432 [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-102437","post","type-post","status-publish","format-standard","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.2 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u041e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043d \u0440\u0435\u043b\u0438\u0437 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043e\u043f\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0442\u0435\u043a\u0441\u0442\u0430 Tesseract 4.1, \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u044e\u0449\u0435\u0439 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u0435 \u0441\u0438\u043c\u0432\u043e\u043b\u043e\u0432 UTF-8 \u0438 \u0442\u0435\u043a\u0441\u0442\u043e\u0432 \u043d\u0430 \u0431\u043e\u043b\u0435\u0435 \u0447\u0435\u043c 100 \u044f\u0437\u044b\u043a\u0430\u0445, \u0432\u043a\u043b\u044e\u0447\u0430\u044f \u0440\u0443\u0441\u0441\u043a\u0438\u0439, \u043a\u0430\u0437\u0430\u0445\u0441\u043a\u0438\u0439, \u0431\u0435\u043b\u043e\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u0438 \u0443\u043a\u0440\u0430\u0438\u043d\u0441\u043a\u0438\u0439.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/fr\/blog\/news\/reliz-sistemy-raspoznavaniya-teksta-tesseract-5-0\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.2\" \/>\n\t\t<meta property=\"og:locale\" content=\"fr_FR\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47\u0420\u0435\u043b\u0438\u0437 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0442\u0435\u043a\u0441\u0442\u0430 Tesseract 5.0 | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u041e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043d \u0440\u0435\u043b\u0438\u0437 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043e\u043f\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0442\u0435\u043a\u0441\u0442\u0430 Tesseract 4.1, \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u044e\u0449\u0435\u0439 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u0435 \u0441\u0438\u043c\u0432\u043e\u043b\u043e\u0432 UTF-8 \u0438 \u0442\u0435\u043a\u0441\u0442\u043e\u0432 \u043d\u0430 \u0431\u043e\u043b\u0435\u0435 \u0447\u0435\u043c 100 \u044f\u0437\u044b\u043a\u0430\u0445, \u0432\u043a\u043b\u044e\u0447\u0430\u044f \u0440\u0443\u0441\u0441\u043a\u0438\u0439, \u043a\u0430\u0437\u0430\u0445\u0441\u043a\u0438\u0439, \u0431\u0435\u043b\u043e\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u0438 \u0443\u043a\u0440\u0430\u0438\u043d\u0441\u043a\u0438\u0439.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/fr\/blog\/news\/reliz-sistemy-raspoznavaniya-teksta-tesseract-5-0\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2021-12-01T13:37:06+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2021-12-01T13:37:06+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47Version du syst\u00e8me de reconnaissance de texte Tesseract 5.0 | ProHoster","description":"La version du syst\u00e8me de reconnaissance optique de caract\u00e8res Tesseract 4.1 a \u00e9t\u00e9 publi\u00e9e, prenant en charge la reconnaissance des caract\u00e8res UTF-8 et des textes en plus de 100 langues, y compris le russe, le kazakh, le bi\u00e9lorusse et l'uukrainien.","canonical_url":"https:\/\/prohoster.info\/fr\/blog\/news\/reliz-sistemy-raspoznavaniya-teksta-tesseract-5-0","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"fr_FR","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u0420\u0435\u043b\u0438\u0437 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0442\u0435\u043a\u0441\u0442\u0430 Tesseract 5.0 | ProHoster","og:description":"\u041e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043d \u0440\u0435\u043b\u0438\u0437 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043e\u043f\u0442\u0438\u0447\u0435\u0441\u043a\u043e\u0433\u043e \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u044f \u0442\u0435\u043a\u0441\u0442\u0430 Tesseract 4.1, \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u044e\u0449\u0435\u0439 \u0440\u0430\u0441\u043f\u043e\u0437\u043d\u0430\u0432\u0430\u043d\u0438\u0435 \u0441\u0438\u043c\u0432\u043e\u043b\u043e\u0432 UTF-8 \u0438 \u0442\u0435\u043a\u0441\u0442\u043e\u0432 \u043d\u0430 \u0431\u043e\u043b\u0435\u0435 \u0447\u0435\u043c 100 \u044f\u0437\u044b\u043a\u0430\u0445, \u0432\u043a\u043b\u044e\u0447\u0430\u044f \u0440\u0443\u0441\u0441\u043a\u0438\u0439, \u043a\u0430\u0437\u0430\u0445\u0441\u043a\u0438\u0439, \u0431\u0435\u043b\u043e\u0440\u0443\u0441\u0441\u043a\u0438\u0439 \u0438 \u0443\u043a\u0440\u0430\u0438\u043d\u0441\u043a\u0438\u0439.","og:url":"https:\/\/prohoster.info\/fr\/blog\/news\/reliz-sistemy-raspoznavaniya-teksta-tesseract-5-0","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2021-12-01T13:37:06+00:00","article:modified_time":"2021-12-01T13:37:06+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"102437","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":null,"breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-12-01 13:37:56","updated":"2022-09-30 15:52:33","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/posts\/102437","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/comments?post=102437"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/posts\/102437\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/media?parent=102437"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/categories?post=102437"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/fr\/wp-json\/wp\/v2\/tags?post=102437"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}