user1018 comments

Results 84 comments of


                                            user1018

About the OCR engine that you use, three questions need your help

@fh2019ustc Hi, I'vd installed Tesseract(v5.0.1) from Git, and downloaded the eng model. The performance is similar to the following performance, but there are still some differences. What else could be...

About the OCR engine that you use, three questions need your help

1）How can I install 5.0.1.20220118, not 5.0.1?(My environment is Linux Ubuntu) 2）The performance based on Setting 2： ED：733.58 CER：0.1859

About the OCR engine that you use, three questions need your help

Oh, I can get the same performance in Windows environment. But for Ubuntu，I can't find Tesseract v5.0.1.20220118

About the OCR engine that you use, three questions need your help

Yes, Thanks for your continuous technical support

当使用Python多进程multiprocessing时，抛ERROR ModuleNotFoundError: No module named 'paddleocr.ppstructure'

命名为paddleocr.py，生成whl包，修复前的错误通过修改执行目录试试呢

Windows的环境下，pdf转换出错！paddleocr --image_dir=ppstructure/recovery/UnrealText.pdf --type=structure --recovery=true --use_pdf2docx_api=true

目前paddleocr是不是低版本，可以安装paddleocr==2.6.0.3试试，如果还报错可以试试2.6.0.2

DB文字检测，对其结果区域最小外接矩形裁剪后，输入stvr识别，经stn之后的矫正效果并不好，可视化stn自己找到的上下边界点，并没有拟合到边缘上，矫正效果也很差。请问有什么好的解决方法吗。

有效果图吗

pip3 install "paddleocr>=2.6" 在Windows上安装出错！!

感谢反馈

Markdown file can't found.

Sorry for the inconvenience, could you refer to [this document ](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_ch/finetune.md)

字符间的空格没有识别

改为lang='en'，再看看呢