Luis von Ahn — Using CAPTCHA to decode scanned books
John Murrell writes about a novel twist on CAPTCHA: “completely automated public Turing tests to tell computers and humans apart.”
[tease]
Researchers estimate Web browsers worldwide roll over 60 million of these [CAPTCHA ]speed bumps a day, and all those seconds add up. “Humanity is wasting 150,000 hours every day on these,” said Luis von Ahn, an assistant professor of computer science at Carnegie Mellon who helped develop CAPTCHAs about seven years ago. “Is there any way in which we can use this human time for something good for humanity, do 10 seconds of useful work for humanity?”
Turns out there is. Von Ahn is working with the Internet Archive to use CAPTCHAs to help digitize books that are too old or faded to be accurately scanned by machine. Sites that use reCAPTCHA will present users with the image of a word or two from such a book and have them type that in, with all the entries compared and compiled on the back end into the digital translation. “It’s definitely a barn-raising to try to build the great library,” said Brewster Kahle, co-founder of the archive.