i want to make my ocr while preserving the text layout. i am using python. is there a quick way in api to get text output while preserving text layout in terms of spaces and line numbers for each word?
Hello, the OCR API returns the x/y coordinates of the bounding box of every word.
thank you, i believe that there is no ready method to obtain the output whose text layout is preserved using the coordinates. i believe i should prepare that method myself right?
Yes. You have the words and their coordinates from the API. But to reconstruct the layout/overlay, that needs to be done in your code.
1 Like