Scientists at Google and Stanford University, have created artificial intelligence software that has the most advanced image recognition skills in the world. The artificial intelligence software is capable of recognizing and describing the content of photographs and videos with far greater accuracy than ever before and its descriptions are similar to what would be given by a human.
"This kind of system could eventually help visually impaired people understand pictures, provide alternate text for images in parts of the world where mobile connections are slow, and make it easier for everyone to search on Google for images," said Google in a statement.
Computer vision has largely been limited to recognizing individual objects, with the new software teaches itself to identify entire scenes. For e.g., a group of young men playing Frisbee or "two pizzas sitting on top of a stove top oven."
"A picture may be worth a thousands words," says the Google Research blog. "But sometimes it's the words that are the most useful - so it's important we figure out ways to translate from images to words automatically and accurately."
Google says that the technology could lead to enabling the blind and robots to better comfortably navigate their environments. It could also be used in surveillance in both public and private places. The software would eventually be able to recognize individual faces and certain types of behavior.
Google Researchers have been working on object recognition technology and has developed an advanced image classification and detection algorithm called GoogLeNet, that recognizes a wide range of objects. Apart from Google, Microsoft has also announced a breakthrough in Object recognition technology under Project Adam. Microsoft's voice assistant Cortana will be able to identify a wide range of objects with the new object recognition tech.