Google's tries out CAPTCHAs using rotated images

gallery

Google has come up with a new form of CAPTCHA technology, which is based on identifying images rather than letters.

The CAPTCHA requires analysis of the content of an image rather than text, which is believed to be a task that humans perform well in and machines generally do not.

"Unfortunately, there is a war going on between humans and 'bots. Software 'bots are attempting to generate massive numbers of computer accounts which are then sold in bulk to spammers,"Google's researchers wrote in a blog post.

"Spammers use these accounts to inundate emails and discussion boards. Meanwhile humans are trying to simply create an account and don't want to spend a lot of time proving that they are not a program."

Users have to adjust randomly rotated images to their upright orientation - a familiar task carried out by those working with photography.

CAPTCHA (Completely Automated Public Turing Test to tell Computers and Humans Apart) is a test used in computing, which tries to ensure a response is not generated automatically by a computer.

With three images the system had a sufficiently high human success rate of 84 per cent, and a sufficiently low bot-success rate of only 0.09 per cent, according to Google's researchers.

They said that computers were capable of reading some images such as faces, skies and text, but that they could work through their image database to get rid of them.

Last year, IT PRO reported on traditional CAPTCHA techniques being beaten by certain types of spam, while spammers recently started beating reworked Microsoft CAPTCHAs.

Email to a friend

Print this page