{"id":872,"date":"2014-08-29T18:06:44","date_gmt":"2014-08-29T18:06:44","guid":{"rendered":"https:\/\/ephesoft.com\/docs\/?p=872"},"modified":"2021-11-17T14:45:10","modified_gmt":"2021-11-17T21:45:10","slug":"recommended-settings-for-better-ocr-results","status":"publish","type":"post","link":"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/","title":{"rendered":"Recommended Settings for Better OCR Results"},"content":{"rendered":"<p><span style=\"color: #333333\"><strong>Applies to: <\/strong>All versions of Ephesoft Transact<\/span><\/p>\n<p><span style=\"color: #333333\">This page lists recommended settings that may improve optical character recognition (OCR) results in Transact. These settings may also resolve common issues with the Recostar_HOCR_Plugin, such as if color images cause:<\/span><\/p>\n<ul>\n<li><span style=\"color: #333333\">Errors or failure when creating HOCR.xml files.<\/span><\/li>\n<li><span style=\"color: #333333\">Transact to crash or hang during RecoStar batch image process.<\/span><\/li>\n<\/ul>\n<p><span style=\"color: #333333\">The following factors can affect OCR quality:<\/span><\/p>\n<ul>\n<li><span style=\"color: #333333\">Image quality<\/span><\/li>\n<li><span style=\"color: #333333\">Compression parameters<\/span><\/li>\n<li><span style=\"color: #333333\">Other plugins<\/span><\/li>\n<\/ul>\n<p><span style=\"color: #333333\">The following settings are optimal when the <strong>PDF to TIFF Conversion Process <\/strong>is set to <strong>Ghostscript <\/strong>and the <strong>Image Conversion Process<\/strong> is set to <strong>ImageMagick<\/strong>.* If you are processing both color and black and white images, use the settings recommended in<\/span> <a href=\"#post-872-_67czvwbvkl99\">Color Images<\/a>. <span style=\"color: #333333\">If your use case is exclusively greyscale, use the settings fo<\/span>r <a href=\"#post-872-_84ohyjr94tsl\">Black and White Images<\/a>.<\/p>\n<p><span style=\"color: #333333\"><strong>Note:<\/strong> Other combinations of engines for <strong>PDF to TIFF Conversion Process <\/strong>and <strong>Image Conversion Process <\/strong>may result in better performance and quality depending on your use case.<\/span><\/p>\n<h2><span style=\"color: #333333\"><a id=\"post-872-_67czvwbvkl99\" style=\"color: #333333\"><\/a>Color Images<\/span><\/h2>\n<p><span style=\"color: #333333\">For color images, Ephesoft recommends the following configurations:<\/span><\/p>\n<ul>\n<li><span style=\"color: #333333\">Documents should have a minimum of 200 DPI.<\/span><\/li>\n<li><span style=\"color: #333333\">In the IMPORT_MULTIPAGE_FILES plugin:<\/span>\n<ul>\n<li><span style=\"color: #333333\">Ensure <code>-limit area 100MB<\/code> is added to the <strong>IM Convert Input Image Parameters<\/strong>.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><span style=\"color: #333333\"><strong>Note: <\/strong>This field is case sensitive, &#8220;MB&#8221; must be capitalized.<\/span><\/p>\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li><span style=\"color: #333333\">Ensure <code>-compress LZW<\/code> is added to the <strong>IM Convert Output Image Parameters<\/strong>.<\/span><\/li>\n<li><span style=\"color: #333333\">Ensure <code>-sCompression=lzw<\/code> is added to the <strong>GhostScript Image Parameters<\/strong>.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><span style=\"color: #333333\"><img decoding=\"async\" width=\"872\" height=\"203\" class=\"wp-image-48329\" src=\"https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-3.png\" srcset=\"https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-3.png 872w, https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-3-300x70.png 300w, https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-3-768x179.png 768w\" sizes=\"(max-width: 872px) 100vw, 872px\" \/><\/span><\/p>\n<p><span style=\"color: #333333\"><em>Figure 1. Import Multipage Files Plugin<\/em><\/span><\/p>\n<ul>\n<li><span style=\"color: #333333\">Ensure the CREATE_OCR_INPUT plugin exists in the Page Process module.<\/span><\/li>\n<li><span style=\"color: #333333\">Turn the <strong>Recostar<\/strong> <strong>color switch <\/strong>to <strong>ON <\/strong>in the RECOSTAR_HOCR plugin, located in the Page Process module.<\/span><\/li>\n<\/ul>\n<p><span style=\"color: #333333\"><img decoding=\"async\" width=\"932\" height=\"172\" class=\"wp-image-48330\" src=\"https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-5.png\" srcset=\"https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-5.png 932w, https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-5-300x55.png 300w, https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-5-768x142.png 768w\" sizes=\"(max-width: 932px) 100vw, 932px\" \/><\/span><\/p>\n<p><span style=\"color: #333333\"><em>Figure 2. RecoStar HOCR Plugin<\/em><\/span><\/p>\n<h2><span style=\"color: #333333\"><a id=\"post-872-_84ohyjr94tsl\" style=\"color: #333333\"><\/a>Black and White Images<\/span><\/h2>\n<p><span style=\"color: #333333\">For black and white images, Ephesoft recommends the following configurations:<\/span><\/p>\n<ul>\n<li><span style=\"color: #333333\">Documents should have a minimum of 200 DPI.<\/span><\/li>\n<li><span style=\"color: #333333\">In the IMPORT_MULTIPAGE_FILES plugin:<\/span>\n<ul>\n<li><span style=\"color: #333333\">Ensure <code>-limit area 100MB<\/code> is added to the <strong>IM Convert Input Image Parameters<\/strong>.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><span style=\"color: #333333\"><strong>Note: <\/strong>This field is case sensitive, &#8220;MB&#8221; must be capitalized.<\/span><\/p>\n<ul>\n<li style=\"list-style-type: none\">\n<ul>\n<li><span style=\"color: #333333\">Ensure <code>-compress LZW<\/code> is added to the <strong>IM Convert Output Image Parameters<\/strong>.<\/span><\/li>\n<li><span style=\"color: #333333\">Ensure <code>-sCompression=lzw<\/code> is added to the <strong>GhostScript Image Parameters<\/strong>.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><span style=\"color: #333333\"><img decoding=\"async\" width=\"872\" height=\"203\" class=\"wp-image-48331\" src=\"https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-9.png\" srcset=\"https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-9.png 872w, https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-9-300x70.png 300w, https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-9-768x179.png 768w\" sizes=\"(max-width: 872px) 100vw, 872px\" \/><\/span><\/p>\n<p><span style=\"color: #333333\"><em>FIgure 3. Import Multipage Files Plugin<\/em><\/span><\/p>\n<ul>\n<li><span style=\"color: #333333\">Turn the <strong>Recostar color switch <\/strong>to <strong>OFF <\/strong>in the RECOSTAR_HOCR plugin, located in the Page Process module.<\/span><\/li>\n<\/ul>\n<p><span style=\"color: #333333\"><img decoding=\"async\" width=\"868\" height=\"164\" class=\"wp-image-48332\" src=\"https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-10.png\" srcset=\"https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-10.png 868w, https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-10-300x57.png 300w, https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-10-768x145.png 768w\" sizes=\"(max-width: 868px) 100vw, 868px\" \/><\/span><\/p>\n<p><span style=\"color: #333333\"><em>Figure 4. RecoStar HOCR Plugin<\/em><\/span><\/p>\n<ul>\n<li><span style=\"color: #333333\">Remove the CREATE_OCR_INPUT plugin from the Page Processing module.<\/span><\/li>\n<\/ul>\n<h2><span style=\"color: #333333\"><a id=\"post-872-_u549mqsrw1j6\" style=\"color: #333333\"><\/a>Related Articles<\/span><\/h2>\n<ul>\n<li><a href=\"https:\/\/ephesoft.com\/docs\/products\/transact\/features-and-functions\/administrator\/moduleplugin-configuration\/folder-import-module\/import-multipage-files-plugin-4040\/\">Import Multipage Files Plugin<\/a><\/li>\n<li><a href=\"https:\/\/ephesoft.com\/docs\/imagemagick\/\">Understanding ImageMagick Compression Parameters<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Applies to: All versions of Ephesoft Transact This page lists recommended settings that may improve optical character recognition (OCR) results [&hellip;]<\/p>\n","protected":false},"author":54,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[697,138,698,168,696],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v19.0 (Yoast SEO v22.1) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Recommended Settings for Better OCR Results | Ephesoft Docs<\/title>\n<meta name=\"robots\" content=\"noindex, follow\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Recommended Settings for Better OCR Results\" \/>\n<meta property=\"og:description\" content=\"Applies to: All versions of Ephesoft Transact This page lists recommended settings that may improve optical character recognition (OCR) results [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/\" \/>\n<meta property=\"og:site_name\" content=\"Ephesoft Docs\" \/>\n<meta property=\"article:published_time\" content=\"2014-08-29T18:06:44+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2021-11-17T21:45:10+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-3.png\" \/>\n<meta name=\"author\" content=\"lydiaxie\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"lydiaxie\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/\",\"url\":\"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/\",\"name\":\"Recommended Settings for Better OCR Results | Ephesoft Docs\",\"isPartOf\":{\"@id\":\"https:\/\/ephesoft.com\/docs\/#website\"},\"datePublished\":\"2014-08-29T18:06:44+00:00\",\"dateModified\":\"2021-11-17T21:45:10+00:00\",\"author\":{\"@id\":\"https:\/\/ephesoft.com\/docs\/#\/schema\/person\/bca3e75d8d08163c3b26d530db9013d1\"},\"breadcrumb\":{\"@id\":\"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/ephesoft.com\/docs\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Recommended Settings for Better OCR Results\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/ephesoft.com\/docs\/#website\",\"url\":\"https:\/\/ephesoft.com\/docs\/\",\"name\":\"Ephesoft Docs\",\"description\":\"Intelligent Document Processing Made Easy\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/ephesoft.com\/docs\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/ephesoft.com\/docs\/#\/schema\/person\/bca3e75d8d08163c3b26d530db9013d1\",\"name\":\"lydiaxie\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/ephesoft.com\/docs\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/b98869ec848ba0d1f0d43297973b9cd7?s=96&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/b98869ec848ba0d1f0d43297973b9cd7?s=96&r=g\",\"caption\":\"lydiaxie\"}}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Recommended Settings for Better OCR Results | Ephesoft Docs","robots":{"index":"noindex","follow":"follow"},"og_locale":"en_US","og_type":"article","og_title":"Recommended Settings for Better OCR Results","og_description":"Applies to: All versions of Ephesoft Transact This page lists recommended settings that may improve optical character recognition (OCR) results [&hellip;]","og_url":"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/","og_site_name":"Ephesoft Docs","article_published_time":"2014-08-29T18:06:44+00:00","article_modified_time":"2021-11-17T21:45:10+00:00","og_image":[{"url":"https:\/\/ephesoft.com\/docs\/wp-content\/uploads\/2014\/08\/word-image-3.png"}],"author":"lydiaxie","twitter_card":"summary_large_image","twitter_misc":{"Written by":"lydiaxie","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/","url":"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/","name":"Recommended Settings for Better OCR Results | Ephesoft Docs","isPartOf":{"@id":"https:\/\/ephesoft.com\/docs\/#website"},"datePublished":"2014-08-29T18:06:44+00:00","dateModified":"2021-11-17T21:45:10+00:00","author":{"@id":"https:\/\/ephesoft.com\/docs\/#\/schema\/person\/bca3e75d8d08163c3b26d530db9013d1"},"breadcrumb":{"@id":"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/ephesoft.com\/docs\/recommended-settings-for-better-ocr-results\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/ephesoft.com\/docs\/"},{"@type":"ListItem","position":2,"name":"Recommended Settings for Better OCR Results"}]},{"@type":"WebSite","@id":"https:\/\/ephesoft.com\/docs\/#website","url":"https:\/\/ephesoft.com\/docs\/","name":"Ephesoft Docs","description":"Intelligent Document Processing Made Easy","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/ephesoft.com\/docs\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/ephesoft.com\/docs\/#\/schema\/person\/bca3e75d8d08163c3b26d530db9013d1","name":"lydiaxie","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/ephesoft.com\/docs\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/b98869ec848ba0d1f0d43297973b9cd7?s=96&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/b98869ec848ba0d1f0d43297973b9cd7?s=96&r=g","caption":"lydiaxie"}}]}},"_links":{"self":[{"href":"https:\/\/ephesoft.com\/docs\/wp-json\/wp\/v2\/posts\/872"}],"collection":[{"href":"https:\/\/ephesoft.com\/docs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ephesoft.com\/docs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ephesoft.com\/docs\/wp-json\/wp\/v2\/users\/54"}],"replies":[{"embeddable":true,"href":"https:\/\/ephesoft.com\/docs\/wp-json\/wp\/v2\/comments?post=872"}],"version-history":[{"count":2,"href":"https:\/\/ephesoft.com\/docs\/wp-json\/wp\/v2\/posts\/872\/revisions"}],"predecessor-version":[{"id":49900,"href":"https:\/\/ephesoft.com\/docs\/wp-json\/wp\/v2\/posts\/872\/revisions\/49900"}],"wp:attachment":[{"href":"https:\/\/ephesoft.com\/docs\/wp-json\/wp\/v2\/media?parent=872"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ephesoft.com\/docs\/wp-json\/wp\/v2\/categories?post=872"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ephesoft.com\/docs\/wp-json\/wp\/v2\/tags?post=872"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}