Google neural net can figure out where photos are taken

A deep-learning machine at Google can determine the location of almost any image.

By - February 29, 2016 Share on LinkedIn
Google Photos

Google computer vision specialist Tobias Weyand and his team have trained a deep-learning machine to work out the location of where almost any photo was taken, the MIT Technology Review reported.

The machine outperforms humans, and can also determine the location of indoor images and pictures of specific things such as pets and food.

The team began by dividing the world into a grid consisting of over 26,000 squares of varying sizes, depending on the number of images taken in a location.

Places where more images are available, like big cities, have a more fine-grained grid, while areas like the oceans and polar regions were ignored completely.

After this, the team built a database of geo-located images from the web and used the location data to determine the grid square in which each image was taken.

This data set is huge, containing around 126 million images and their location data.

Roughly 91 million images were used to train the neural network, while the remaining images were used to validate the system.

Called PlaNet, the idea is that you input an image into the neural net and get a grid location or a set of likely candidates.

PlaNet

PlaNet

Here’s what powers Google and Facebook’s AI

Google has open sourced its artificial intelligence engine

Why you need a deep-learning antivirus

The superintelligence revolution

Google buys artificial intelligence company DeepMind

Share your thoughts

Join the conversation

Connect with Us

androidappletwitterfacebookgoogleplusfeednewsletter

Poll

Do you use Yahoo as your primary search engine?

View Results

Loading ... Loading ...

More News

HyperDrive USB adapter adds everything Apple removed from the new MacBook Pro

HyperDrive

The HyperDrive Compact USB-C hub for the Macbook Pro aims to overcome the notebook’s “limited connection” options.

How an online shopping package gets from a warehouse to you

parcelninja

A behind-the-scenes video of Parcelninja shows how an online shopping product arrives at its warehouse, gets stored and picked, and is then sent to a client.

Most-watched videos on YouTube in 2016

YouTube

YouTube has released its annual Rewind, detailing the most-watched videos for the year globally and in South Africa.

SABC inquiry to continue, despite Maguvhe appeal

SABC logo on paper

Parliament’s inquiry into the SABC board will continue its work, despite members of the broadcaster walking out of the inquiry in protest on Wednesday.

Free MyBroadband Newsletter
×