Feeds

Google boffins beat own Captchas

The StreetView numbers game

The Power of One eBook: Top reasons to choose HP BladeSystem

A group of Google scientists working on extracting numbers from StreetView images has discovered that their technology can also match humans at solving captchas.

The aim, according to their research paper (at Arxiv, here), was to automatically extract accurate street number data from StreetView images so as to improve Google Maps location information.

Prior work, the researchers write, had worked on extracting individual numbers from an image, identifying each number, and then reassembling the whole street number. This, however, is inefficient, so the group let by Ian Goodfellow focussed on taking an entire image and identifying all the numbers in it.

Testing their model on Google's StreetView House Numbers dataset (which contains 200,000 numbers), the researchers found they were able to match human accuracy of 98 per cent with “95.64 per cent coverage”.

To achieve that accuracy, the researchers spent six days training Google's DistBelief neural network modelling framework. That training was then applied to all the house numbers Google holds – well into the tens of millions. The less constrained dataset reduced coverage down to 89 per cent while holding accuracy at the 98 per cent “equal to a human” threshold.

Google's Street View number recognition

Getting numbers out of images is easy, says Google

The same model was then tested against Google's reCAPTCHA puzzle, achieving 99.8 per cent accuracy. The researchers write that while this doesn't render Captchas useless, “the utility of distorted text as a reverse turing test by itself is significantly diminished”.

As Google's Vinay Shet writes in this blog post, “the act of typing in the answer to a distorted image should not be the only factor when it comes to determining a human versus a machine”, and Google itself is reducing its “dependence on text distortions as the main differentiator between human and machine,” using Captchas instead to “perform advanced risk analysis”. ®

Designing a Defense for Mobile Applications

More from The Register

next story
DARPA-derived secure microkernel goes open source tomorrow
Hacker-repelling, drone-protecting code will soon be yours to tweak as you see fit
How long is too long to wait for a security fix?
Synology finally patches OpenSSL bugs in Trevor's NAS
Roll out the welcome mat to hackers and crackers
Security chap pens guide to bug bounty programs that won't fail like Yahoo!'s
HIDDEN packet sniffer spy tech in MILLIONS of iPhones, iPads – expert
Don't panic though – Apple's backdoor is not wide open to all, guru tells us
Researcher sat on critical IE bugs for THREE YEARS
VUPEN waited for Pwn2Own cash while IE's sandbox leaked
Four fake Google haxbots hit YOUR WEBSITE every day
Goog the perfect ruse to slip into SEO orfice
Putin: Crack Tor for me and I'll make you a MILLIONAIRE
Russian Interior Ministry offers big pile o' roubles for busting pro-privacy browser
prev story

Whitepapers

Designing a Defense for Mobile Applications
Learn about the various considerations for defending mobile applications - from the application architecture itself to the myriad testing technologies.
Implementing global e-invoicing with guaranteed legal certainty
Explaining the role local tax compliance plays in successful supply chain management and e-business and how leading global brands are addressing this.
Top 8 considerations to enable and simplify mobility
In this whitepaper learn how to successfully add mobile capabilities simply and cost effectively.
Seven Steps to Software Security
Seven practical steps you can begin to take today to secure your applications and prevent the damages a successful cyber-attack can cause.
Boost IT visibility and business value
How building a great service catalog relieves pressure points and demonstrates the value of IT service management.