The neat trick with reCAPTCHA is that it provides a two-word code to break, one of which is an unrecognised word from a printed text that’s been scanned in but which OCR software hasn’t confidently recognised. If you get the machine-generated word right, reCAPTCHA assumes you’ve probably also cracked the missing word. Unknown words matched by multiple users can then be added to the scanned text of books or newspapers. That’s a clever way of contributing to scanning efforts (and a logical step for Google given its ongoing Booksscanning efforts), but doesn’t necessarily mean that the resulting CAPTCHA is any easier to read.
Google Makes Shift To reCAPTCHA By Buying It
About the Author
Angus Kidman | Lifehacker Editor
Angus has been writing professionally about technology since 1994 and breaking it for even longer. He is based in Sydney but spends a frankly unhealthy portion of his life on the road, tracking down the latest stories. In 2011, he won the IT Journo Award For Best Consumer Technology Journalist and Consensus IT Writers Award for Best Technical Writer for his work on Lifehacker; about time too.