Google captures Recaptcha

 

Gallery

By Stuart Turton

Posted on 17 Sep 2009 at 10:39

Google has acquired spam-fighting project Recaptcha, as it looks to bring the firm's technology to its book digitisation plans.

Recaptcha is best known for creating the squiggly words that you have to decipher in order to add comments to blogs and forums. The system works on the principal that machines can't easily read the text, whereas humans can, supposedly reducing spam.

However, behind the system there is a sophisticated optical character recognition technology that scans words from old newspapers and books to create the codes. This the same technology that Google is using in its controversial book digitisation project.

However, unlike the Google method, as people enter Recaptcha codes they teach the system to read more difficult text, improving the efficiency of the scanning process. It is a process that could become invaluable to Google's ambitious digitisation project.

We'll be applying the technology within Google not only to increase fraud and spam protection for Google products but also to improve our books and newspaper scanning process

"We'll be applying the technology within Google not only to increase fraud and spam protection for Google products but also to improve our books and newspaper scanning process," says Luis von Ahn, co-founder of Recaptcha on the Google blog.

"Improving the availability and accessibility of all the information on the internet is really important to us, so we're looking forward to advancing this technology with the Recaptcha team," adds Will Cathcart, Google Product Manager.

Google is currently attempting to fend off criticism over its Books project, which has been described as an "antitrust nightmare" by Amazon. In an attempt to quell criticism, the company's now offered to share its scanned-books repository with rivals.