Add a legend, gridlines, and other markings.Change a chart from one type to another.Select tables, cells, rows, and columns.Fill shapes and text boxes with color or an image.Format Chinese, Japanese, or Korean text.Make characters superscript or subscript.Populate and create customized documents.Add, change, or delete a source file in Pages on iPad.Select text and place the insertion point.Use VoiceOver to preview comments and track changes.Intro to images, charts, and other objects.
All ideas and questions can be discussed here in English.įor Chinese develops, Scan the QR code below with your Wechat, you can join the official technical discussion group. One line of code quick use: Quick Startįor international developers, we regard PaddleOCR Discussions as our international community platform.
The F-score of PP-OCRv2 is 7% higher than that of PP-OCR mobile. The inference speed of PP-OCRv2 is 220% higher than that of PP-OCR server in CPU device. Release 1 key information extraction algorithm SDMGR and 3 DocVQA algorithms (LayoutLM, LayoutLMv2, LayoutXLM).Release 1 text detection algorithm ( PSENet), 3 text recognition algorithms ( NRTR、 SEED、 SAR).
Release PP-OCRv3: With comparable speed, the effect of Chinese scene is further improved by 5% compared with PP-OCRv2, the effect of English scene is improved by 11%, and the average recognition accuracy of 80 language multilingual models is improved by more than 5%.