如何使用 Python 在一行中配置不同字体大小的 tesseract？

Question

I have a problem that I get only the number 2201 from my image. I have tried all configurations for pytesseract but no result. Maybe somebody here has a solution for me? When I cut the image into two pieces and run the OCR it works perfectly.

text = pytesseract.image_to_string(img, lang = 'deu', config='-psm 4')
print(text)

that was my configuration

Image being OCR'd

Answer 1

Problem is that it short text and it IS NOT on one (base)line. So you will need to split image to 2 part and OCR them separately.