- Our logo includes team logo and official logo for PaddleOCR
PaddleOCR is an open-source OCR tool based on PaddlePaddle algorithm developed by company Baidu from China. It aims to create multilingual, awesome, leading, and practical OCR tools that help users train better models and apply them into practice. Compared with other OCR tools, PaddleOCR has the feature of ultra-lightweight and pre-trained models, which is suitable for local offline deployment and being embedded in IoT devices. It is also the reason that triggers we four Embedded Master students to study about it.
fix the incompatibility of gif saving #2351
This contribution fixes the incompatibility of git saving. The original file saves the output result with cv2.imwrite() while this API cannot correct saves ‘.gif’ file. So we add a judgement to check the type of image file. If the original image file is ‘.gif’ type, it will be saved as ‘.png’ file.
Fix two grammatical mistakes in StyleText/README.md file #2312
This contribution fixes two grammatical mistakes in file StyleText/README.md.