Replies: 1 comment 5 replies
-
可以先进行版面识别,会将表格区域和文字区域分开,再分别进行表格识别和文字ocr,也可以先版面识别后进行整页ocr识别,可能更快,整页ocr的结果给到表格识别模型,会进行box匹配的 |
Beta Was this translation helpful? Give feedback.
5 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
我测试的例子用的是人行征信报告,其实某种意义上,它算是表格,但在使用ocr识别和html组装的过程中,它会把表头标题给忽略掉了,这种情况求大佬解答下,该怎么解决
Beta Was this translation helpful? Give feedback.
All reactions