How does the PDF OCR process compare to images? I uploaded a sample PDF with ver... | Hacker News

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

pc86 on June 25, 2015 | parent | context | favorite | on: Ask HN: Open source OCR library?

How does the PDF OCR process compare to images? I uploaded a sample PDF with very clear sans-serif text (printed to PDF from a webpage) and there seems to be some odd substitutions. "prohibitecL" instead of "prohibited", "ac" instead of "QC" (as part of an address), random clipping of the first letter in a few lines and random use of a capital i instead of 1.

Overall very good, I'm just wondering if the library is better with image files than PDFs?

kargo on June 25, 2015 [–]

Interesting... I see it now. I assume some issue during the PDF to image conversion in the web app. PDF support is just a few days old.

The OCR library itself supports only image formats as input and is "innocent" with regards to this issue ;)

Consider applying for YC's Winter 2027 batch! Applications are open till November 2.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact