Doesn't extract the table correctly. #1603
linkstatic12
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
So I am a dev who is a table detection and table structure enthusiast and I am on a Journey to find the best implementation which can help me extract any type of table from a PDF. I have gone through a couple of different implementations available on net and even trained a model on financial reports which are available on IBM site. What I have taken from this unstructured IO is that it is not accurate when it comes to different types of tables. What I have found is that the Microsoft Table Transformer implementation is much better as compared to this when it comes to table structures.
Beta Was this translation helpful? Give feedback.
All reactions