Extract floating point number from .png image

Hi all,

I’ve got a .png file (actually lots of them) that contain lots of numbers that are expressed like floating points, e.g. “32.34”. I’d like to get those numbers. I’ve been reading the docs for JuliaImages and I suspect I might be able to hack something together that works for my specific use-case (the numbers are always stored in predictable locations in my images). Having said that, I know next-to-nothing about image manipulation and will probably do it very inefficiently.

So my question: are there any general tools for recognizing numbers (and, out of curiousity, letters) in images in Julia?

Cheers,

Colin

The OCR itself should probably be done with tesseract, for which there is a convenient wrapper package.
https://github.com/leferrad/OCReract.jl

2 Likes

Ha ha I had to google what OCR stood for which about sums up how much I know about this stuff. Anyway, thanks for the link, it looks spot on.

Cheers,

Colin