I got Abobe Acrobat 1 with an OCR app in a scanner bundle in ‘96. The scanner was new but the software by that time was already a few years old. What a PITA that stuff was to use, and the results were horrible.
You are right, the process has come a very long way. Think about all those hand written checks running down the line at the federal reserve.
I ran the AP version of the BC through a little freeware app called PDF OCR X, for intel chipped Macs. It came out nearly completely converted. Each layer was labeled with corresponding text. Pretty impressive considering the resolution of that doc.
IIRC HDOH converted their documents in 2001? So we aren’t exactly talking about a stone tablet here.
USPS had a process called Remote Video Encoding where the letters rejected for "read" were run under a TV camera and the image transmitted to personnel elsewhere who would read the letter's address and provide the right coding to send it on its way.
As I was retiring this was being phased out totally since OCR systems, plus normal mail address hygiene had improved such that the few pieces that couldn't be read could be dealt with manually by one guy 10 minutes a day (or some such). The engineers are all rather dismissive of the need to keep RVE even on pretense.