10872
Comments (4284)
sorted by:
You're viewing a single comment thread. View all comments, or full comment thread.
2
ConTexYankee 2 points ago +2 / -0

This is not a perfect explanation of what happens with OCR, but read the second point in the article. Basically states that OCR is far from perfect and if someone doesn’t correct the OCR scan once done then it’s gonna be riddled with errors.

https://www.forbes.com/sites/timworstall/2012/10/27/why-are-ebooks-riddled-with-typos/?sh=6ee7e321677c

I think there are probably people more qualified than I am to speak on it, though.