I am using pytesseract for image to text extraction, i want to extract the menu items and their respective prices. The problem that I am facing right now is that the menu items are easily getting extracted but the ocr is not able to extract the prices.

P.S. What i found out is that due to substantial whitespaces between the items and the prices the ocr may not be able to detect the price and moves on to the next menu item.

Please suggest me any preprocessing technique that might be useful in this case.

I tried some preprocessing techniques, like greyscaling and dpi setting but it didn’t provide the result that i was expecting. The result it provided was mostly the same as previous.