What's the easiest solution to get digitalized representation of the text on an image?

Question

Assume the image is only in black and white.

Is there a software that can generate a matrix representation for the text on the image?

Answer 1

你应该看看OCR -软件。

Answer 2

If you're referring to an image like the one below, then it's pretty straight forward.

You just do the following:

• Read the image into a 2D byte array so you can access the pixels
• Loop through the array and look for every black pixel (0)
• Store these in a matrix however you need to

This assumes that lettering is pure black on white, you might have to allow values upto a certain value (5 or 10) if this isn't the case.