search

lquirosd / P2PaLA

Page to PAGE Layout Analysis Tool
GNU General Public License v3.0
190 stars 42 forks source link

Does P2Pala support reading order? #39

Closed JediKnightChan closed 2 years ago

JediKnightChan commented 3 years ago

I fed data to P2PALA with reading order (custom="readingOrder {index:8;}"), but in the output it's missing, and the order of the XML tags in PAGE format is pretty messed up (it reads from bottom of the text region to the top of it, but from left to the right)

lquirosd commented 3 years ago

Hi, P2PaLA does not support reading order. The order in the output XML is arbitrary. As reading order is an open issue in handwritten document layout analysis we are developing new techniques to handle the issue, please check out repo on the matter: https://github.com/lquirosd/Order_Relation_Operator

Note: the research paper where we explain all the details about the proposed method is not published yet, we hope it will be ready soon.