Search Box

Friday, February 26, 2016

Google Knows Where You Took Those Photos


Google Knows Where You Took Photos Using Pixels

Photos are broken down to the pixel-level, and Google's systems then try to cross-reference these with its gigantic image library.

Sky News | February 25, 2016



Google is developing technology that can pinpoint the location of any photo using nothing but the image's pixels.
Many services can establish where a photograph was taken using the hidden data which is often attached to most digital photographs.
However, Google wants to go a step further and has developed a system that can determine where an image was taken by scanning the landscape.
Photos are broken down to the pixel-level, and Google's systems then try to cross-reference these with its gigantic image library to see if it can match it.


Deep learning machine PlaNet recognises a range of visual cues, such as vegetation and landmarks, to guess a photo's location with 'superhuman levels of accuracy. The Eiffel Tower (top left) can be easily assigned to Paris, but the model showed the fjord photo (middle left) could have been taken in Norway or New Zealand
Deep learning machine PlaNet recognises a range of visual cues, such as vegetation and landmarks, to guess a photo's location with 'superhuman levels of accuracy. The Eiffel Tower (top left) can be easily assigned to Paris, but the model showed the fjord photo (middle left) could have been taken in Norway or New Zealand. Source: http://www.dailymail.co.uk/sciencetech/article-3463520/Google-knows-took-photos-using-individual-PIXELS-AI-tool-locates-landmarks-superhuman-accuracy.html



<more at http://news.sky.com/story/1648443/google-knows-where-you-took-photos-using-pixels; related articles and links: http://www.dailymail.co.uk/sciencetech/article-3463520/Google-knows-took-photos-using-individual-PIXELS-AI-tool-locates-landmarks-superhuman-accuracy.html (Google knows where you took your photos using individual pixels: AI tool locates landmarks with 'superhuman accuracy'. Deep learning machine PlaNet recognises a variety of visual cues. It uses them to guess a location with 'superhuman levels of accuracy'
The software was trained using 126 million images found online. During trials, it correctly guessed the country of origin 28% of the time and the continent of origin in almost half of cases. February 25, 2016) and https://www.washingtonpost.com/news/the-intersect/wp/2014/11/19/everything-google-knows-about-you-and-how-it-knows-it/ (Everything Google knows about you (and how it knows it). November 19, 2014)>

No comments:

Post a Comment