microsoft / table-transformer

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.
MIT License
2.01k stars 231 forks source link

"Urgent"-Issue in null cell- null cell value getting overlapped by next cell value #168

Open VisakhRKrishnan opened 4 months ago

VisakhRKrishnan commented 4 months ago

I used this table transform code but there is an issue like cell value are overlapped with next cell value can please give me a solution for that and which is urgent

image image

After detection the values are getting overlapped (Date field value getting overlapped by Description ) image

could you please give me a solution

VisakhRKrishnan commented 4 months ago

I fixed this issue, like identified the null cell and replace the value with "Null"

tzktz commented 4 months ago

I fixed this issue, like identified the null cell and replace the value with "Null"

what ocr used for this ? In easy ocr extraction of words get worst https://github.com/NielsRogge/Transformers-Tutorials/issues/372