Skip to content
New issue

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

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

Already on GitHub? # to your account

有的单个字符,比如 -, 识别出来可能是nan,这种怎么识别比较好 #10459

Closed
nissansz opened this issue Jul 24, 2023 · 6 comments
Assignees
Labels
expneeded need extra experiment to fix issue good first issue Good for newcomers status/close

Comments

@nissansz
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:win10
  • 版本号/Version:Paddle: PaddleOCR:2.6 问题相关组件/Related components:
  • 运行指令/Command Code:
  • 完整报错/Complete Error Message:

有的单个字符,比如 -, 识别出来可能是nan,这种怎么识别比较好

@ToddBear
Copy link
Collaborator

可以提供一下具体的输入图片以及对应的识别结果吗?

@ToddBear ToddBear added question Further information is requested good first issue Good for newcomers labels Jul 25, 2023
@nissansz
Copy link
Author

image
识别结果就是空,没结果。

@ToddBear ToddBear added expneeded need extra experiment to fix issue and removed question Further information is requested labels Jul 25, 2023
@ToddBear
Copy link
Collaborator

我尝试了一下,发现一行文本中只有单个 '_', '-', '/', '.' 的字符就容易出现识别不出的情况,猜测原因是默认的SVRT_LCNet识别方法在特征提取时会进行上下文信息的融合,导致文字区域的特征被空白区域的特征"污染",进而使其被识别为空白区域。

当我尝试将空白区域的范围缩小,该字符就能正确识别出来了

可以先进行文字的检测,只保留图片文字区域,再进行识别

@nissansz
Copy link
Author

缩小范围可以识别正确,但是acc显示只有0.2,不知道这个准确率还能不能改善,有没有影响

@UserWangZz
Copy link
Collaborator

该issue长时间未更新,暂将此issue关闭,如有需要可重新开启。

@failable
Copy link

failable commented Oct 21, 2024

单个数字也无法识别。

image
Screenshot 2024-10-21 at 12 58 16

都不行

# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
expneeded need extra experiment to fix issue good first issue Good for newcomers status/close
Projects
None yet
Development

No branches or pull requests

5 participants