Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

PaddleOCR对于纯文本的识别比PPStructure更准确 #11665

Closed
jyyang621 opened this issue Mar 4, 2024 · 5 comments
Closed

PaddleOCR对于纯文本的识别比PPStructure更准确 #11665

jyyang621 opened this issue Mar 4, 2024 · 5 comments
Assignees

Comments

@jyyang621
Copy link

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem

  • 系统环境/System Environment: Linux
  • 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Related components: PaddleOCR 2.7
  • 运行指令/Command Code:
  • 完整报错/Complete Error Message:
  • 我在测试PaddleOCR和PPStructure的时候,发现对于纯文本来说,前者比后者解析的更准确,但是我看两个对于文本的识别模型用的好像是一样的?为什么会有这样的差异呢?PPStructure能解析出表格和其他版面结构,但是会有一部分文本识别的不准确。两者我用的都是最新版。

请尽量不要包含图片在问题中/Please try to not include the image in the issue.

@RussellLuo
Copy link
Contributor

@jyyang621 当前 PPStructure 版面分析的 OCR 精度存在问题,具体可以参考这里的讨论:#10270

@tink2123
Copy link
Collaborator

tink2123 commented Mar 5, 2024

由于版面分析不够准确,因此会影响OCR的识别结果。模型我们在下一个版本会升级,优化这个问题~ 感谢关注

@jyyang621
Copy link
Author

@jyyang621 当前 PPStructure 版面分析的 OCR 精度存在问题,具体可以参考这里的讨论:#10270

好的,感谢大佬!

@jyyang621
Copy link
Author

由于版面分析不够准确,因此会影响OCR的识别结果。模型我们在下一个版本会升级,优化这个问题~ 感谢关注

好的,感谢大佬,期待!

@GreatV
Copy link
Collaborator

GreatV commented Apr 24, 2024

这个问题应该已经在 #11916 修复了,可以试试main分支的效果。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

5 participants