New Computer Vision Project Can Solve reCAPTCHAs With Over 99% Accuracy

From Google Online Security Blog:

Translating a street address to an exact location on a map is harder than it seems. To take on this challenge and make Google Maps even more useful, we’ve been working on a new system to help locate addresses even more accurately, using some of the technology from the Street View and reCAPTCHA teams.

This technology finds and reads street numbers in Street View, and correlates those numbers with existing addresses to pinpoint their exact location on Google Maps.

We show that this system is able to accurately detect and read difficult numbers in Street View with 90% accuracy.

Turns out that this new algorithm can also be used to read CAPTCHA puzzles—we found that it can decipher the hardest distorted text puzzles from reCAPTCHA with over 99% accuracy... (cont'd) (full technical paper)

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

Allied Motion - New MFH170i Housed Brushless Torque Motor Has Integrated Servo Drive and Optical Encoder

Allied Motion - New MFH170i Housed Brushless Torque Motor Has Integrated Servo Drive and Optical Encoder

Allied Motion's Megaflux MFH170i series of 170 mm (6.7 in) diameter housed brushless torque motors consists of a high performance brushless DC torque motor, a digital servo drive, and an optical encoder, all integrated into a rugged machined aluminum housing with robust duplex bearings. The MFH0170i series features a 63.5 mm (2.5 in) large-bore through shaft, and is characterized by a very high torque-to-inertia ratio. There are three stack lengths in the series with peak torque ranging from 8.5 up to 16.9 Nm (75 up to 150 lb-in). The standard winding voltage is 48 V. And to ease the hassle of long leadtimes for prototypes, the new MFH170i is now available through our QuickShip program.