> it's not possible to unambiguously segment the text into distinct letters (which is a necessary first step in any OCR engine that I'm aware of)

This made me realize I never saw such a thing as OWR, i.e. a software that would first try to recognized whole words, then go down to character level if no satisfying match found.

Found out this exists already: https://en.wikipedia.org/wiki/Intelligent_word_recognition