I have a paper with boxes that contain fields in which I want to extract data from. Currently I am using the quickstart found here https://pypi.org/project/pytesseract/
In particular, I use the image_to_boxes to extract the data, however the program reads lines top to bottom and left to right and not boxes themselves top to bottom left to right. So I was wondering if I could parse the data within the boxes themselves of a certain region of my data sheet.
The results read 'Part Operation:150 Number: RG45X12-G' instead of 'Part Number: RG45X12-G Operation: 150'
