Will Google's recognition system see tough mobile phones?
Google keeps doing interesting things. From testing self-driving cars, to providing workers with a great way to procrastinate by making its search engine logo into some sort of game for the day – the company is rarely out of the news.
In case anyone has forgotten about the internet giant, it's now received a patent for the first ‘automatic large scale video object recognition' system.
This technology would allow people to upload photos or videos to the internet without tagging a location or subject, and have Google do it for them instead.
For example, a video of someone walking along a canal-side path in Venice might end up being tagged ‘water', ‘gondola', ‘Venice' and ‘Italy'… in theory.
Google states, "Conventional systems rely on direct human input to provide object exemplars explicitly labelled as representing the object, such as a set of images known to include, for example, dogs, based on prior human examination.
"However, such human input is expensive, time-consuming, and cannot scale up to handle very large data sets comprising hundreds of thousands of objects and millions of images."
Tough mobile phones and their more breakable cousins might look similar, but they are in fact quite different when it comes to durability. So, will every mobile just be a ‘mobile phone', or will this recognition system be able to tell what type of handset it's looking at?