Hi all! I’m stuck on a problem here. I’m trying to make these two images match closely so I can create masks from them and do OCR. I’ve tried the usual stuff but can’t seem to get to a solution that works for both images and results in reasonable OCR accuracy. No matter what color space I pick, I can’t find a range of values that works for both. I would love some ideas about how to adjust them so i can turn them into reasonable binary images.
I’m willing to recursively adjust the images but I can’t figure out what I would be adjusting and what to measure.
Thanks for the help!