Join GitHub today
GitHub is home to over 50 million developers working together to host and review code, manage projects, and build software together.
Sign upGitHub is home to over 50 million developers working together to host and review code, manage projects, and build software together.
Sign up
Is it possible to modify it to work on text +hocr (overlayed on it)
So basically replacing image by image+hocr combo.
And then it can be used to annotate text document without having someone to type things after making box. As watever text comes inside box becomes the value for the key.
So at the end we have
Key, Value, Box-cordinates.
example: DATE, 28-May-2018, (x1,y1,x2,y2)
I will try to do it myself by some guidance from you.