为什么使用PP-OCRv4检测、识别模型,检测识别出来的单词是连在一起的,不能区分每个单词。 #13203
Unanswered
1424153694
asked this question in
Q&A
Replies: 2 comments
-
同样的问题,别问,问就是百度做的东西压根不考虑鲁棒场景。 不过你这个可能是英文模型,如果是中英文夹杂,好像padle严格不支持中英文合在一起的时候英文识别空格 |
Beta Was this translation helpful? Give feedback.
0 replies
-
检测是按行检测的 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
问题描述 / Problem Description
为什么使用PP-OCRv4检测、识别模型,检测识别出来的单词是连在一起的,检测模型不是对每个单词进行检测画框,而是把整个短语句子放在一个检测框里,识别模型也无法识别出空格,导致模型识别出的单词内容是连在一起的,不能区分每个单词。
效果图:

Beta Was this translation helpful? Give feedback.
All reactions