Esp32 cam embedded 7-seg ocr

I’m not coming up with a lot of results for embedded OCR on the esp32. It seems like a lot of compute power that should be capable of this in a reasonable amount of time with some edge filters and the like. Possibly available RAM could be an issue?

Just curious if anyone had tried anything like this yet and if I would be wasting my time or at least be able to discuss some lessons learned. Anyone out there seen any attempts at doing this locally?

Regards,
Devan

You can use the built in home assistant integration https://www.home-assistant.io/integrations/seven_segments/

But I agree an esp should be able to do it.