Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Blurb: "Unlike traditional PDF text extraction, this approach actually "reads" your PDF like a human would, preserving formatting, tables, and document structure with high accuracy.

Input text in their example:

QUENE ELI-

sabet, Quene of England

Their output text from their example:

QUEENE ELIZABETH

Elizabeth, Queene of England

Try harder.



Classic HN snark. It’s an example that is supposed to show the edge of its capabilities. You won’t find another word processor that can even come close.


No this is clearly fair criticism that shows them failing at what they say they do well.

"Come close" ? Nonsense - a free online OCR got me a much better result:

QVENE ELI-

fabet, Quene of England,




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: