Hacker News new | ask | show | jobs
by fmbb 760 days ago
OCR has been a solved problem for years. Long before LLMs started being hyped.

At least from typewritten documents that you did not torch or shred etc.
1 comments
ryanjshaw 760 days ago
No it hasn't. Just 1.5 years ago I tried all the latest OCR tools, including AWS, GCP and Azure services, and none of them could consistently and reliably read a receipt printed at a store.
link
FredPret 760 days ago
Receipts are hard.

- cheap paper

- cheap ink

- misprints

- abbreviations

- every store does it differently

link
tiagod 756 days ago
Yes. Which makes OCR not a solved problem.
link
FredPret 756 days ago
OCR is merely step one.

Interpreting recognized characters is another matter.

link