search

DevashishPrasad / CascadeTabNet

This repository contains the code and implementation details of the CascadeTabNet paper "CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents"
MIT License
1.46k stars 422 forks source link

Explain the coordinates in Table Structure Recognition #135

Closed ZafarShadman09 closed 3 years ago

ZafarShadman09 commented 3 years ago

This really is an amazing work thank you. But I am having trouble understanding the coordinates in the table structure recognition.

I am unable to interpret which is x0,x1, y0,y1.

These value seem to be repeating 1299 1750.

ZafarShadman09 commented 3 years ago

Got it.

x,y is actually the point and its separated and its all four corner coordinates

MahimaBarot commented 2 years ago

Got it.

x,y is actually the point and its separated and its all four corner coordinates

I am still unclear about this coordinate system. In what format are they returning the values? also in pixels or point?