Quote:
Originally Posted by sic
I lost you Natch...
|
What I was getting at is that Google is basically scanning every book they can get their hands on, they could provide Hadrien's notional "HUGE database of books" for plagiarism checks.
Quote:
Originally Posted by Hadrien
Well what you need is to ocr these images and get the text. Finding similarities between 2 texts is something really easy for a company such as google (that's part of how they can search the web).
|
About that: since the Google
book search page advertises that you can "Search the full text of books and discover new ones" -- doesn't that suggest that Google might
be OCRing those scanned holdings?