I'm trying to use either easyocr or pytesseract to read a crossword puzzle image that I pre-processed. Which can be seen here:
I've been having trouble trying to extract the text successfully, as some letters aren't detected at all. I'm not sure if I need to use better bounding boxes or if vertical text is something that is the main issue at hand. I'm not looking for any way of specific formatting, just a string that has all the letters in the crossword.
Источник: https://stackoverflow.com/questions/781 ... crosswords
