{"id":15377,"date":"2024-07-12T08:53:44","date_gmt":"2024-07-12T00:53:44","guid":{"rendered":"https:\/\/www.1ai.net\/?p=15377"},"modified":"2024-07-12T08:53:44","modified_gmt":"2024-07-12T00:53:44","slug":"%e7%99%be%e5%ba%a6%e9%a3%9e%e6%a1%a8paddleocr%e5%8f%91%e5%b8%83v2-8-0%e6%96%b0%e7%89%88%e6%9c%ac-%e5%bc%95%e5%85%a5%e8%a1%a8%e6%a0%bc%e8%af%86%e5%88%ab%e7%ae%97%e6%b3%95%e7%ad%89%e6%96%b9%e6%a1%88","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/15377.html","title":{"rendered":"Baidu PaddleOCR releases new version v2.8.0, introducing table recognition algorithms and other solutions"},"content":{"rendered":"<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/paddleocr\" title=\"_Other Organiser\" target=\"_blank\" >PaddleOCR<\/a> As a text recognition development kit under the PaddlePaddle deep learning open source framework, v2.8.0 has released a milestone update. This version introduces cutting-edge OCR technology, including the champion solution of the PaddleOCR algorithm model challenge, such as the scene text recognition algorithm SVTRv2 and<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%a1%a8%e6%a0%bc%e8%af%86%e5%88%ab%e7%ae%97%e6%b3%95\" title=\"[See articles with [table recognition algorithm] labels]\" target=\"_blank\" >Table recognition algorithm<\/a>SLANet-LCNetV2 sets a new standard in the OCR field.<\/p>\n<p>At the same time, the project structure has been deeply optimized, and non-core modules have been moved to the new warehouse, allowing the project to focus more on OCR core technology. In addition, historical problems such as the model failing to run after updating Backbone, numpy version dependency conflicts, and Mac system running freezes have been solved, improving the user experience.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-15378\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/6385637071664997304742236.jpg\" alt=\"\" width=\"711\" height=\"318\" \/><\/p>\n<p>The new version also includes a fix for the loss of OCR results in layout analysis, the introduction of pyproject.toml to comply with the PEP518 specification, and optimization improvements such as sliding window operations for large-scale image reasoning, which enhances the stability, compatibility, and performance of the software. The support and contribution of the open source community are crucial to every progress of PaddleOCR v2.8.0, and the efforts of PMC members and contributors are particularly appreciated.<\/p>\n<p>PaddleOCR is currently building a dedicated site for document tutorials, which will provide keyword search capabilities and an elegant and comfortable interface.<\/p>\n<p><strong>Project address:<\/strong>https:\/\/github.com\/PaddlePaddle\/PaddleOCR<\/p>","protected":false},"excerpt":{"rendered":"<p>PaddleOCR v2.8.0, the text recognition development kit under the Paddle Deep Learning open source framework, has released a milestone update. This version introduces cutting-edge OCR technologies, including the winning solutions of the PaddleOCR Algorithm Model Challenge, such as the scene text recognition algorithm SVTRv2 and the table recognition algorithm SLANet-LCNetV2, which set a new standard for the OCR field. Meanwhile, the project structure was deeply optimized and non-core modules were migrated to the new repository, making the project more focused on OCR core technology. In addition, historical difficult problems including models not running after updating Backbone, numpy version dependency conflicts, Mac system running lag, etc. have been solved to improve user experience. The new version also includes a new version of layout analysis<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[3453,234,3451,3452],"collection":[],"class_list":["post-15377","post","type-post","status-publish","format-standard","hentry","category-news","tag-paddleocr","tag-234","tag-3451","tag-3452"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/15377","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=15377"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/15377\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=15377"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=15377"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=15377"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=15377"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}