Mr. Somebody
Friend Of A Friend
Google develops computer vision accurate enough to solve its own CAPTCHAs
By Jacob Kastrenakes on April 16, 2014 04:05
Google has cracked the CAPTCHA. In a paper published this week, Google researchers say that they've developed an algorithm that can accurately solve Google's own CAPTCHA puzzles — those obfuscated jumbles of letters and numbers you type in on websites to prove that you're human — with 99.8 percent accuracy, obviously posing something of a problem to the puzzle's intended purpose of weeding out robots. The new system was developed to help Google automatically analyze hard-to-read signs and house numbers photographed by its Street View cameras, allowing it to accurately match images with locations on a map.
"RELYING ON DISTORTED TEXT ALONE ISN’T ENOUGH."
Despite being near perfect when it comes to CAPTCHAs — a feat that plenty of humans can't even manage — the new system's analysis of Street View imagery isn't quite as accurate, correctly identifying the text just over 90 percent of the time. When analyzing house numbers specifically, however, its accuracy jumps up to over 96 percent.
These CAPTCHAs have been correctly solved by the new algorithm.
Google is, of course, specially suited to developing such advanced automated text analysis because of its extensive work with Street View and reCAPTCHA, its own CAPTCHA service. Even so, Google says that it's already found ways to further protect reCAPTCHA from being broken by others' computers. "Thanks to this research, we know that relying on distorted text alone isn’t enough," Vinay Shet, reCAPTCHA's product manager writes in a blog post. Shet explains that part of this is analyzing a user's full interaction with the CAPTCHA puzzle — and not solely whether they can get the answer right.
Google AI that solves reCAPTCHAs is now cracking address numbers in Street View
by Signe Brewster
SUMMARY:
Google found that an algorithm can solve reCAPTCHAS with an accuracy of more than 99 percent.
When Google’s Street View cars drive up and down the streets of a town, they don’t just collect images. They also log addresses, which helps match Street View with Maps. It’s much faster to have a computer do the matching, so Google relies on artificial intelligence to pick out address numbers and decide what they mean.
Street View addresses cracked by the algorithm. Photo courtesy of Google.
Google said today that its address recognition will get a boost from another development–an algorithm that can crack Google’s version of the CAPTCHA, known as reCAPTCHA, with more than 99 percent accuracy. While humans don’t have too much trouble picking out characters that are jumbled, computers have a very hard time deciphering where one letter ends and the next begins. Google’s new algorithm comes much closer to a human level of recognition.
As artificial intelligence and internet bots have improved, the longstanding and very annoying CAPTCHA system has come under strain. Vicarious, an artificial intelligence company that received $40 million in funding in March, built an algorithm last year that was able to crack any type of CAPTCHA with an accuracy of at least 90 percent. Its effectiveness came from its ability to pick out characters even when they were squished together or overlapping.
But Google says not to worry. It used its findings with the algorithm to improve reCAPTCHAS not by making them more difficult, but by incorporating other factors that analyze whether it is a human or a bot on the other end. It has actually made reCAPTCHAS clearer as a result. And the algorithm is now busy crunching address numbers for the Street View team.
By Jacob Kastrenakes on April 16, 2014 04:05
Google has cracked the CAPTCHA. In a paper published this week, Google researchers say that they've developed an algorithm that can accurately solve Google's own CAPTCHA puzzles — those obfuscated jumbles of letters and numbers you type in on websites to prove that you're human — with 99.8 percent accuracy, obviously posing something of a problem to the puzzle's intended purpose of weeding out robots. The new system was developed to help Google automatically analyze hard-to-read signs and house numbers photographed by its Street View cameras, allowing it to accurately match images with locations on a map.
"RELYING ON DISTORTED TEXT ALONE ISN’T ENOUGH."
Despite being near perfect when it comes to CAPTCHAs — a feat that plenty of humans can't even manage — the new system's analysis of Street View imagery isn't quite as accurate, correctly identifying the text just over 90 percent of the time. When analyzing house numbers specifically, however, its accuracy jumps up to over 96 percent.
These CAPTCHAs have been correctly solved by the new algorithm.
Google is, of course, specially suited to developing such advanced automated text analysis because of its extensive work with Street View and reCAPTCHA, its own CAPTCHA service. Even so, Google says that it's already found ways to further protect reCAPTCHA from being broken by others' computers. "Thanks to this research, we know that relying on distorted text alone isn’t enough," Vinay Shet, reCAPTCHA's product manager writes in a blog post. Shet explains that part of this is analyzing a user's full interaction with the CAPTCHA puzzle — and not solely whether they can get the answer right.
Google AI that solves reCAPTCHAs is now cracking address numbers in Street View
by Signe Brewster
SUMMARY:
Google found that an algorithm can solve reCAPTCHAS with an accuracy of more than 99 percent.
When Google’s Street View cars drive up and down the streets of a town, they don’t just collect images. They also log addresses, which helps match Street View with Maps. It’s much faster to have a computer do the matching, so Google relies on artificial intelligence to pick out address numbers and decide what they mean.
Street View addresses cracked by the algorithm. Photo courtesy of Google.
Google said today that its address recognition will get a boost from another development–an algorithm that can crack Google’s version of the CAPTCHA, known as reCAPTCHA, with more than 99 percent accuracy. While humans don’t have too much trouble picking out characters that are jumbled, computers have a very hard time deciphering where one letter ends and the next begins. Google’s new algorithm comes much closer to a human level of recognition.
As artificial intelligence and internet bots have improved, the longstanding and very annoying CAPTCHA system has come under strain. Vicarious, an artificial intelligence company that received $40 million in funding in March, built an algorithm last year that was able to crack any type of CAPTCHA with an accuracy of at least 90 percent. Its effectiveness came from its ability to pick out characters even when they were squished together or overlapping.But Google says not to worry. It used its findings with the algorithm to improve reCAPTCHAS not by making them more difficult, but by incorporating other factors that analyze whether it is a human or a bot on the other end. It has actually made reCAPTCHAS clearer as a result. And the algorithm is now busy crunching address numbers for the Street View team.
who is able to make war with the beast?
"OK?... it's on"
"now, tell me about your mother..."