February 26, 2016

Google Unveils Neural Network with “Superhuman” Ability to Determine the Location of Almost Any Image

Knowing the specific location cue an extact image is taken is significantly hard  and as to whether the image was taken indoors or shows a pet or food or some other detail is much harder.
 
Thnak to, the  computer vision specialist at Google, and a couple of pals through their work of Tobias Weyand, .  have trained a deep-learning machine to work out the location of almost any photo using only the pixels it contains.
 
Their new machine significantly outperforms humans and can even use a clever trick to determine the location of indoor images and pictures of specific things such as pets, food, and so on that have no location cues.
 
Their approach is straightforward, at least in the world of machine learning. Weyand and co begin by dividing the world into a grid consisting of over 26,000 squares of varying size that depend on the number of images taken in that location.
 
So big cities, which are the subjects of many images, have a more fine-grained grid structure than more remote regions where photographs are less common. Indeed, the Google team ignored areas like oceans and the polar regions, where few photographs have been taken.
 

No comments: