Researchers at Carnegie Mellon University and INRIA/Ecole Normale Supérieure in Paris have developed a visual data mining software that can automatically identify which city it is.
1 Star2 Stars3 Stars4 Stars5 Stars (Rate This)
Loading...

Researchers at Carnegie Mellon University and INRIA/Ecole Normale Supérieure in Paris have developed a visual data mining software that can automatically identify which city it is. The interesting thing is the software can recognize Paris easily, but it faces more trouble identifying geo-informative elements for U.S. cities.


City Identifying Software

To identify a city, the software observes the street signs, streetlamps and balcony railings of the surrounding buildings etc. The software analyzed more than 250 million visual elements gleaned from 40,000 Google Street View images of Paris, London, New York, Barcelona and eight other cities to find those that were both frequent and could be used to discriminate one city from the others. This yielded sets of geo-informative visual elements unique to each city, such as cast-iron balconies in Paris, fire escapes in New York City and bay windows in San Francisco.

“Visual Data is much more difficult, so the field of visual data mining is still in its infancy, but I believe it holds a lot of promise. Our data mining technique was able to go through millions of image patches automatically — something that no human would be patient enough to do,” said Efros, who collaborated with colleagues including Abhinav Gupta, assistant research professor of robotics, and Carl Doersch, a Ph.D. student in CMU’s Machine Learning Department. “In the long run, we wish to automatically build a digital visual atlas of not only architectural but also natural geo-informative features for the entire planet.”

Identifying Cities Via Software

The researchers started with 25,000 randomly selected visual elements from city images that were gathered from Google Street View. The software then analyzed these visual elements to determine which details made them different from similar visual elements in other cities. After several iterations, the software identified the top-scoring patches for identifying a city.

For Paris, those patches corresponded to doors, balconies, windows with railings, street signs (the shape and color of the signs, not the street names on the signs), and special Parisian lampposts. But, the software faced more trouble identifying geo-informative elements for U.S. cities, which the researches attributed to the relative lack of stylistic coherence in American cities with their melting pot of styles and influences.

Alexei Efros, CMU associate professor of robotics and computer said, “Our data mining technique was able to go through millions of image patches automatically; something that no human would be patient enough to do. In the long run, we wish to automatically build a digital visual atlas of not only architectural but also natural geo-informative features for the entire planet.”

If you think, you know Paris better and recognize its places then you should take part in Paris-nonParis test.

Source : CNET

Buy Cheapest Related Product From Amazon.com


Splashtop Remote Desktop For Windows 8 Is Now Available At Windows Store

Microsoft’s BUILD 2012: House Full Within The First Hour
You can also press the left/right arrow key on your keyboard to go to previous/next post
  On August 10, 2012(4 years, 1 month ago.)

You May Also Like:

What Do You Think?

Leave a Reply




Loading Facebook Comments ...

FTC Disclosure: Some of the links of this website are "affiliate links." This means if you click on the link and purchase the item, we will receive an affiliate commission.


Recent Search

Recent Tutorials

There is a high-risk XSS Vulnerability in W3 Total Cache, and we have got the guide to the fix for you.
Check out this tutorial to know how to install Apple watchOS 3 beta certificate on your Apple Watch and start enjoying the new version.
If you are trying to jailbreak iPhone, iPad or iPod on iOS 9.2 - 9.3.3 without using a computer or Apple ID, then check this video tutorial.
Pokemon Go users are complaining about the crashing and server issues. Check out the tutorial to solve error problems and thanks us later.
Turning off Wi-Fi Assist is a great way to save mobile data since it automatically starts using cellular data when Wi-Fi signal is poor .
If you want to secure your SIM card from others using it, then check out this tutorial to know how to set up the SIM Pin code on your iPhone.
CiderTV is a great alternative to control Apple TV from the Notification Center. Check out this tutorial to set up CiderTV on your iPhone.
Are you annoyed by the split screen mode on the iPhone 6 Plus or 6s Plus? Check out this quick tutorial to turn off split screen feature.
If you could not wait to installed the iOS 10 beta version on you iPhone and now struggling for the errors, then this tutorial is for you.
Siri might not understand the question you asked. But you can use Siri by editing the text that you asked & it will give an updated answer.
Close You Have To Login
User:
Pass:
Login With »Login With TwitterLogin With Facebook