Google announced a new tool on Wednesday that makes it possible for apps, robots and drones to “see.” The tool is meant for app developers and can detect various emotions on a face, such as a smile or a frown, the Internet firm said.
Giving more options to developers
Google’s Cloud Vision API is thename of the new technology, which allows app developers to tap into Google’s smart “machine learning” service that has the ability to identify objects, including faces and emotions. “Seeing, a very hard computer problem, is solved with Cloud Vision.
For instance, our computers are capable of scanning and reproducing an image of a mountain or an image of a baby, but they all look the same to the computer – a bunch of pixels. The computers are not capable of sifting through photographs to find baby photos for users until they name or tag them baby. On the other hand, it is possible for Google Photos to find baby photos. And now the Internet firm is offering this technology to developers so that they can add it to their apps.
Developers will be able to apply tons of machine learning smarts to home or work applications with the API. Machine learning, which was once known as artificial intelligence, is when computers make use of the data they view to learn how to recognize people, things, words or anything over time.
Google shows how it works
To demonstrate Cloud Vision, Google used it to build a cute little robot known as GoPiGo. Google also created a video in which one can see a robot following faces and detecting emotions. Further in the video, the robot demonstrates its power of detecting and identifying other objects such as glasses, a banana, money, etc. Google has also hinted at other applications of its Cloud Vision. Aerosense — a drone maker owned by Sony Mobile Communications — has been testing Google Vision.
On Google’s blog, Aerosense’s GM, Tomoaki Kobayakawa, said, “We have drones that take thousands of photos per flight. We find that Google Cloud Vision API as the best way to turn those huge number of photos, automatically produced, into meaningful insights.”
