How to recognize text of a certain color?

Question

Python

There is a picture:
You need to get only text from it. The text is black, gray or dark gray, my idea is that I want to process the image using opencv in such a way as to "remove" those parts that do not fall into the "gray-black" range, and then run the converted image through the text recognition algorithm . I want to ask two questions: 1) I know that cv2 has an inRange method that can be passed a range of colors, but I don't know how to correctly specify the colors (gray, dark gray) that I need. 2) Tell me, what is generally better to use the preprocessing approach? I'm sure there are better options than mine.

Answer 1

You can also binarize and then remove elements that are too large in area.
In the same imagemagick, this is done elementarily.