Google's New Image Recognition Algorithm Capable of Recognizing CAPTCHA with 99.8% Accuracy

Today, the Google Street View project team posted some interesting news. The fact is that the developers of the service have created a new image recognition algorithm in order to more accurately recognize house numbers and street names photographed by Google cars.



And this algorithm turned out to be very effective in another matter - in the recognition of CAPTCHA. Moreover, Google’s own algorithm of the company recognizes captcha with unprecedented efficiency - 99.8%. This is a significantly better result than even a person shows. You yourself know how many times you sometimes need to type captcha characters before the system recognizes them correctly recognized.

The old image recognition algorithm worked on house numbers with an efficiency of 90%, which is quite small, because the volumes of the analyzed information are simply huge, and some errors turned out to be laid out on Street View. At the moment, the system has already recognized about 100 million numbers worldwide. Neural networks are involved for the new algorithm to work (some technical details, in English, here - deep convolutional neural network ). And here is a combined article by Street View and reCAPTCHA teams about the problem of recognizing house and street numbers.

As for captcha, Google developers are not worried about this. On the contrary, it has now become clear how you can still protect your own CAPTCHA so that it is less recognized by automatic systems of various kinds of intruders / spammers. In general, reCAPTCHA will become even more reliable, and there will be even fewer errors on Street View.

Via techcrunch