11.27.07
Approve Blog Comments to Save Our Literary Heritage?
I’m sure nearly everyone who reads blogs knows about the strategy for filtering spam from blog comments by asking users to type the text in a picture.
I’m not sure everyone knows about Project Gutenberg – the project to digitize all of our world’s classical literature… basically old books are fed into computers who digitize the text and then try to convert it to words. The problem is that much of the text is old, and the computer can’t always figure it out:
image credit: reCAPTCHA (see below)
So… I don’t remember where I read it first… but there are organizations that are working to help decipher the text. I’m sure everyone who can read English can reasonably decipher the text above – so why not have people help decipher the scans?
I’ve just installed a WordPress plugin called reCAPTCHA – whenever you comment on this blog, you’ll be asked to verify someone’s interpretation of the scanned text. Pretty cool, huh?
Learn more about reCAPTCHA and the OCR/literature movement here.
Permalink Comments off
