dhlab-epfl / dhSegment

Generic framework for historical document processing
https://dhlab-epfl.github.com/dhSegment
GNU General Public License v3.0
370 stars 116 forks source link

Can this network be used to extract table from a document? #13

Closed jewelc92 closed 5 years ago

jewelc92 commented 5 years ago

Can this network be used to extract table from a document? If it could be, how to do it? Painting the table lines in red and the others in black?

solivr commented 5 years ago

Depending on what you want you have two options:

If you want the content of the table, then you can try to annotate only the text lines inside the table (not sure this would work though), or combine a table extractor (i.e the second option above) with a text line extractor.