{"id":29882,"date":"2025-04-04T02:43:32","date_gmt":"2025-04-03T18:43:32","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=29882"},"modified":"2025-04-04T02:43:32","modified_gmt":"2025-04-03T18:43:32","slug":"uniocr","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/ja\/uniocr\/","title":{"rendered":"uniOCR\uff1a\u8de8\u5e73\u53f0\u5f00\u6e90\u7684\u6587\u5b57\u8bc6\u522b\u5de5\u5177"},"content":{"rendered":"<p>uniOCR \u662f\u4e00\u4e2a\u5f00\u6e90\u7684\u6587\u5b57\u8bc6\u522b\u5de5\u5177\uff0c\u7531 mediar-ai \u56e2\u961f\u5f00\u53d1\u3002\u5b83\u57fa\u4e8e Rust \u8bed\u8a00\u7f16\u5199\uff0c\u652f\u6301 macOS\u3001Windows \u548c Linux \u7cfb\u7edf\u3002\u7528\u6237\u53ef\u4ee5\u901a\u8fc7\u5b83\u4ece\u56fe\u7247\u4e2d\u63d0\u53d6\u6587\u5b57\uff0c\u64cd\u4f5c\u7b80\u5355\u4e14\u514d\u8d39\u3002uniOCR \u7684\u6838\u5fc3\u7279\u70b9\u662f\u8de8\u5e73\u53f0\u652f\u6301\u548c\u7edf\u4e00\u7684\u63a5\u53e3\u8bbe\u8ba1\u3002\u5b83\u96c6\u6210\u4e86\u591a\u79cd OCR \u5f15\u64ce\uff0c\u5305\u62ec macOS \u7684 Vision Kit\u3001Windows OCR \u548c Tesseract\uff0c\u8fd8\u652f\u6301\u4e91\u7aef OCR\u3002\u65e0\u8bba\u662f\u4e2a\u4eba\u7528\u6237\u8fd8\u662f\u5f00\u53d1\u8005\uff0c\u90fd\u53ef\u4ee5\u7528\u5b83\u5feb\u901f\u5904\u7406\u56fe\u7247\u6587\u5b57\u8bc6\u522b\u4efb\u52a1\u3002\u9879\u76ee\u4ee3\u7801\u5f00\u653e\uff0c\u5141\u8bb8\u7528\u6237\u81ea\u7531\u4fee\u6539\u548c\u6269\u5c55\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"\" title=\"uniOCR\uff1a\u8de8\u5e73\u53f0\u5f00\u6e90\u7684\u6587\u5b57\u8bc6\u522b\u5de5\u5177-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/04\/f0f85555edcdd51.jpg\" alt=\"uniOCR\uff1a\u8de8\u5e73\u53f0\u5f00\u6e90\u7684\u6587\u5b57\u8bc6\u522b\u5de5\u5177-1\" width=\"624\" height=\"312\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li>\u652f\u6301 macOS\u3001Windows \u548c Linux \u7cfb\u7edf\uff0c\u8de8\u5e73\u53f0\u8fd0\u884c\u3002<\/li>\n<li>\u63d0\u4f9b\u591a\u79cd OCR \u5f15\u64ce\u9009\u62e9\uff1amacOS Vision\u3001Windows OCR\u3001Tesseract \u548c\u4e91\u7aef OCR\u3002<\/li>\n<li>\u652f\u6301\u4ece\u5355\u5f20\u56fe\u7247\u6216\u591a\u5f20\u56fe\u7247\u4e2d\u63d0\u53d6\u6587\u5b57\u3002<\/li>\n<li>\u63d0\u4f9b\u7edf\u4e00\u7684 API \u63a5\u53e3\uff0c\u65b9\u4fbf\u5207\u6362\u4e0d\u540c OCR \u5f15\u64ce\u3002<\/li>\n<li>\u652f\u6301\u5f02\u6b65\u64cd\u4f5c\u548c\u6279\u91cf\u5904\u7406\uff0c\u63d0\u5347\u8bc6\u522b\u6548\u7387\u3002<\/li>\n<li>\u5141\u8bb8\u81ea\u5b9a\u4e49\u8bbe\u7f6e\uff0c\u6bd4\u5982\u8bed\u8a00\u3001\u7f6e\u4fe1\u5ea6\u9608\u503c\u548c\u8d85\u65f6\u65f6\u95f4\u3002<\/li>\n<li>\u5f00\u6e90\u9879\u76ee\uff0c\u7528\u6237\u53ef\u4ee5\u67e5\u770b\u548c\u4fee\u6539\u4ee3\u7801\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5b89\u88c5\u6d41\u7a0b<\/h3>\n<p>uniOCR \u9700\u8981\u5b89\u88c5 Rust \u73af\u5883\u548c\u76f8\u5173\u4f9d\u8d56\u624d\u80fd\u8fd0\u884c\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u6b65\u9aa4\uff1a<\/p>\n<ol>\n<li><strong>\u5b89\u88c5 Rust<\/strong>\n<ul>\n<li>\u6253\u5f00\u7ec8\u7aef\uff0c\u8f93\u5165\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5 Rust\uff1a\n<pre><code>curl --proto '=https' --tlsv1.2 -sSf https:\/\/sh.rustup.rs | sh\r\n<\/code><\/pre>\n<\/li>\n<li>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u8fd0\u884c\u00a0<code>rustc --version<\/code>\u00a0\u68c0\u67e5\u7248\u672c\uff0c\u786e\u4fdd\u5b89\u88c5\u6210\u529f\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u4e0b\u8f7d uniOCR \u6e90\u7801<\/strong>\n<ul>\n<li>\u4f7f\u7528 Git \u514b\u9686\u9879\u76ee\u5230\u672c\u5730\uff1a\n<pre><code>git clone https:\/\/github.com\/mediar-ai\/uniOCR.git\r\n<\/code><\/pre>\n<\/li>\n<li>\u8fdb\u5165\u9879\u76ee\u76ee\u5f55\uff1a\n<pre><code>cd uniOCR\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u5b89\u88c5 Tesseract\uff08\u53ef\u9009\uff09<\/strong>\n<ul>\n<li>\u5982\u679c\u60f3\u4f7f\u7528 Tesseract \u5f15\u64ce\uff0c\u9700\u8981\u989d\u5916\u5b89\u88c5\uff1a\n<ul>\n<li>macOS\uff1a\u8fd0\u884c\u00a0<code>brew install tesseract<\/code><\/li>\n<li>Ubuntu\uff1a\u8fd0\u884c\u00a0<code>apt-get install tesseract-ocr<\/code><\/li>\n<li>Windows\uff1a\u8fd0\u884c\u00a0<code>winget install tesseract<\/code>\u00a0\u6216\u624b\u52a8\u4e0b\u8f7d\u5b89\u88c5\u5305\u3002<\/li>\n<\/ul>\n<\/li>\n<li>macOS Vision \u548c Windows OCR \u65e0\u9700\u989d\u5916\u5b89\u88c5\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u7f16\u8bd1\u9879\u76ee<\/strong>\n<ul>\n<li>\u5728\u9879\u76ee\u76ee\u5f55\u8fd0\u884c\uff1a\n<pre><code>cargo build --release\r\n<\/code><\/pre>\n<\/li>\n<li>\u7f16\u8bd1\u5b8c\u6210\u540e\uff0c\u53ef\u6267\u884c\u6587\u4ef6\u4f4d\u4e8e\u00a0<code>&lt;\u9879\u76ee\u76ee\u5f55&gt;\/target\/release\/<\/code>\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u8fd0\u884c\u7a0b\u5e8f<\/strong>\n<ul>\n<li>\u8f93\u5165\u4ee5\u4e0b\u547d\u4ee4\u542f\u52a8\uff1a\n<pre><code>cargo run --release\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h3>\u5982\u4f55\u4f7f\u7528<\/h3>\n<p>uniOCR \u901a\u8fc7\u4ee3\u7801\u8c03\u7528\u5b9e\u73b0\u6587\u5b57\u8bc6\u522b\u3002\u4ee5\u4e0b\u662f\u57fa\u672c\u64cd\u4f5c\uff1a<\/p>\n<ol>\n<li><strong>\u51c6\u5907\u56fe\u7247<\/strong>\n<ul>\n<li>\u5c06\u9700\u8981\u8bc6\u522b\u7684\u56fe\u7247\uff08\u6bd4\u5982\u00a0<code>test.png<\/code>\uff09\u653e\u5165\u9879\u76ee\u76ee\u5f55\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u8fd0\u884c\u57fa\u672c\u793a\u4f8b<\/strong>\n<ul>\n<li>\u7f16\u8f91\u00a0<code>&lt;\u9879\u76ee\u76ee\u5f55&gt;\/examples\/basic.rs<\/code>\uff0c\u4ee3\u7801\u5982\u4e0b\uff1a\n<pre><code>use uniocr::{OcrEngine, OcrProvider};\r\nuse anyhow::Result;\r\n#[tokio::main]\r\nasync fn main() -&gt; Result&lt;()&gt; {\r\nlet engine = OcrEngine::new(OcrProvider::Auto)?;\r\nlet text = engine.recognize_file(\"test.png\").await?;\r\nprintln!(\"\u63d0\u53d6\u7684\u6587\u5b57: {}\", text);\r\nOk(())\r\n}\r\n<\/code><\/pre>\n<\/li>\n<li>\u8fd0\u884c\u793a\u4f8b\uff1a\n<pre><code>cargo run --example basic\r\n<\/code><\/pre>\n<\/li>\n<li>\u7a0b\u5e8f\u4f1a\u8f93\u51fa\u56fe\u7247\u4e2d\u7684\u6587\u5b57\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u9009\u62e9 OCR \u5f15\u64ce<\/strong>\n<ul>\n<li>\u4fee\u6539\u00a0<code>OcrProvider<\/code>\u00a0\u53c2\u6570\u4ee5\u5207\u6362\u5f15\u64ce\uff1a\n<ul>\n<li>macOS Vision\uff1a<code>OcrProvider::MacOS<\/code><\/li>\n<li>Windows OCR\uff1a<code>OcrProvider::Windows<\/code><\/li>\n<li>Tesseract\uff1a<code>OcrProvider::Tesseract<\/code><\/li>\n<\/ul>\n<\/li>\n<li>\u793a\u4f8b\u4ee3\u7801\uff1a\n<pre><code>let engine = OcrEngine::new(OcrProvider::Tesseract)?;\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u6279\u91cf\u5904\u7406<\/strong>\n<ul>\n<li>\u7f16\u8f91\u00a0<code>&lt;\u9879\u76ee\u76ee\u5f55&gt;\/examples\/batch_processing.rs<\/code>\uff1a\n<pre><code>use uniocr::{OcrEngine, OcrProvider};\r\nuse anyhow::Result;\r\n#[tokio::main]\r\nasync fn main() -&gt; Result&lt;()&gt; {\r\nlet engine = OcrEngine::new(OcrProvider::Auto)?;\r\nlet images = vec![\"img1.png\", \"img2.png\", \"img3.png\"];\r\nlet results = engine.recognize_batch(images).await?;\r\nfor (i, text) in results.iter().enumerate() {\r\nprintln!(\"\u56fe\u7247 {} \u63d0\u53d6\u7684\u6587\u5b57: {}\", i + 1, text);\r\n}\r\nOk(())\r\n}\r\n<\/code><\/pre>\n<\/li>\n<li>\u8fd0\u884c\uff1a\n<pre><code>cargo run --example batch_processing\r\n<\/code><\/pre>\n<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h3>\u7279\u8272\u529f\u80fd\u64cd\u4f5c<\/h3>\n<h4>\u81ea\u5b9a\u4e49\u8bbe\u7f6e<\/h4>\n<ul>\n<li>uniOCR \u652f\u6301\u8c03\u6574\u8bc6\u522b\u53c2\u6570\u3002\u793a\u4f8b\u4ee3\u7801\uff1a<\/li>\n<\/ul>\n<pre><code>use uniocr::{OcrEngine, OcrProvider, OcrOptions};\r\nlet options = OcrOptions::default()\r\n.languages(vec![\"eng\", \"chi_sim\"])  \/\/ \u8bbe\u7f6e\u82f1\u6587\u548c\u7b80\u4f53\u4e2d\u6587\r\n.confidence_threshold(0.8)         \/\/ \u7f6e\u4fe1\u5ea6\u9608\u503c\r\n.timeout(std::time::Duration::from_secs(30));  \/\/ \u8d85\u65f6 30 \u79d2\r\nlet engine = OcrEngine::new(OcrProvider::Auto)?.with_options(options);\r\n<\/code><\/pre>\n<ul>\n<li>\u8fd0\u884c\u540e\uff0c\u8bc6\u522b\u4f1a\u6309\u8bbe\u7f6e\u6267\u884c\u3002<\/li>\n<\/ul>\n<h4>\u591a\u8bed\u8a00\u652f\u6301<\/h4>\n<ul>\n<li>\u5982\u679c\u8bc6\u522b\u4e2d\u6587\uff0c\u9700\u5b89\u88c5 Tesseract \u7684\u4e2d\u6587\u8bed\u8a00\u5305\uff1a<\/li>\n<li>macOS\/Ubuntu\uff1a\u8fd0\u884c\u00a0<code>brew install tesseract-lang<\/code>\u00a0\u6216\u00a0<code>apt-get install tesseract-ocr-chi-sim<\/code><\/li>\n<li>Windows\uff1a\u4e0b\u8f7d\u00a0<code>chi_sim.traineddata<\/code>\u00a0\u5e76\u653e\u5165 Tesseract \u5b89\u88c5\u76ee\u5f55\u7684\u00a0<code>tessdata<\/code>\u00a0\u6587\u4ef6\u5939\u3002<\/li>\n<li>\u8bbe\u7f6e\u8bed\u8a00\u53c2\u6570\u4e3a\u00a0<code>vec![\"chi_sim\"]<\/code>\u3002<\/li>\n<\/ul>\n<h4>\u6027\u80fd\u4f18\u5316<\/h4>\n<ul>\n<li>uniOCR \u4f7f\u7528\u5f02\u6b65\u64cd\u4f5c\u548c\u5e76\u884c\u5904\u7406\u3002\u6279\u91cf\u8bc6\u522b\u65f6\uff0c\u7a0b\u5e8f\u4f1a\u540c\u65f6\u5904\u7406\u591a\u5f20\u56fe\u7247\uff0c\u8282\u7701\u65f6\u95f4\u3002<\/li>\n<li>\u5728\u9ad8\u6027\u80fd\u8bbe\u5907\u4e0a\uff08\u5982 M4 MacBook Pro\uff09\uff0cmacOS Vision \u6bcf\u79d2\u53ef\u5904\u7406 3.2 \u5f20\u56fe\u7247\uff0c\u51c6\u786e\u7387\u8fbe 90%\u3002<\/li>\n<\/ul>\n<h3>\u6ce8\u610f\u4e8b\u9879<\/h3>\n<ul>\n<li>\u56fe\u7247\u9700\u6e05\u6670\uff0c\u6a21\u7cca\u6216\u5149\u7ebf\u4e0d\u8db3\u53ef\u80fd\u5f71\u54cd\u8bc6\u522b\u6548\u679c\u3002<\/li>\n<li>Windows \u7cfb\u7edf\u9700\u4e3a Windows 10 \u6216\u4ee5\u4e0a\u7248\u672c\u3002<\/li>\n<li>\u4e91\u7aef OCR\uff08\u5982 Google Cloud Vision\uff09\u9700\u989d\u5916\u914d\u7f6e\u51ed\u8bc1\uff0c\u76ee\u524d\u5b98\u65b9\u672a\u63d0\u4f9b\u5b8c\u6574\u793a\u4f8b\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u5e94\u7528\u573a\u666f<\/h2>\n<ol>\n<li><strong>\u6587\u6863\u626b\u63cf<\/strong><br \/>\n\u7528\u6237\u53ef\u4ee5\u5c06\u7eb8\u8d28\u6587\u4ef6\u62cd\u7167\uff0c\u7528 uniOCR \u63d0\u53d6\u6587\u5b57\uff0c\u4fdd\u5b58\u4e3a\u7535\u5b50\u7248\u3002<\/li>\n<li><strong>\u591a\u8bed\u8a00\u7ffb\u8bd1<\/strong><br \/>\n\u8bc6\u522b\u56fe\u7247\u4e2d\u7684\u5916\u6587\u540e\uff0c\u914d\u5408\u7ffb\u8bd1\u5de5\u5177\u751f\u6210\u591a\u8bed\u8a00\u6587\u672c\u3002<\/li>\n<li><strong>\u81ea\u52a8\u5316\u5de5\u4f5c\u6d41<\/strong><br \/>\n\u5f00\u53d1\u8005\u53ef\u4ee5\u5c06 uniOCR \u96c6\u6210\u5230\u811a\u672c\u4e2d\uff0c\u6279\u91cf\u5904\u7406\u56fe\u7247\u5e76\u63d0\u53d6\u6587\u5b57\u3002<\/li>\n<\/ol>\n<p>&nbsp;<\/p>\n<h2>QA<\/h2>\n<ol>\n<li><strong>\u54ea\u4e9b\u7cfb\u7edf\u652f\u6301 uniOCR\uff1f<\/strong><br \/>\n\u652f\u6301 macOS\u3001Windows 10+ \u548c Linux\uff0c\u65e0\u9700\u989d\u5916\u786c\u4ef6\u3002<\/li>\n<li><strong>\u5982\u4f55\u63d0\u9ad8\u8bc6\u522b\u51c6\u786e\u7387\uff1f<\/strong><br \/>\n\u4f7f\u7528\u9ad8\u8d28\u91cf\u56fe\u7247\uff0c\u8c03\u6574\u7f6e\u4fe1\u5ea6\u9608\u503c\uff0c\u6216\u9009\u62e9\u9002\u5408\u7684 OCR \u5f15\u64ce\u3002<\/li>\n<li><strong>Tesseract \u65e0\u6cd5\u8bc6\u522b\u4e2d\u6587\u600e\u4e48\u529e\uff1f<\/strong><br \/>\n\u9700\u5b89\u88c5\u4e2d\u6587\u8bed\u8a00\u5305\uff0c\u5e76\u8bbe\u7f6e\u00a0<code>languages(vec![\"chi_sim\"])<\/code>\u3002<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>uniOCR \u662f\u4e00\u4e2a\u5f00\u6e90\u7684\u6587\u5b57\u8bc6\u522b\u5de5\u5177\uff0c\u7531 mediar-ai \u56e2\u961f\u5f00\u53d1\u3002\u5b83\u57fa\u4e8e Rust \u8bed\u8a00\u7f16\u5199\uff0c\u652f\u6301 macOS\u3001Windows \u548c Linux \u7cfb\u7edf\u3002\u7528\u6237\u53ef\u4ee5\u901a\u8fc7\u5b83\u4ece\u56fe\u7247\u4e2d\u63d0\u53d6\u6587\u5b57\uff0c\u64cd\u4f5c\u7b80\u5355\u4e14\u514d\u8d39\u3002uniOCR \u7684\u6838\u5fc3\u7279\u70b9\u662f\u8de8\u5e73\u53f0\u652f&#8230;<\/p>\n","protected":false},"author":1,"featured_media":62192,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[230,248],"class_list":["post-29882","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","tag-aikaiyuanxiangmu","tag-ocr"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/posts\/29882","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/comments?post=29882"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/posts\/29882\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/media\/62192"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/media?parent=29882"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/categories?post=29882"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/ja\/wp-json\/wp\/v2\/tags?post=29882"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}