This window to the future is none other than a piece of glass. University of Wisconsin-Madison engineers has devised a method to create pieces of “smart” glass that can recognize images without requiring any sensors or circuits or power sources.
The advanced technology that is behind the face recognition system in many of the smartphones could get a high-tech upgrade that is, honestly, low-tech.
The team is using optics in order to condense the standard setup of the cameras, the sensors, and the deep neural networks. All of them, into a piece of thin glass. They published their findings in the journal Photonics Research.
Putting artificial intelligence into inert objects is quite a concept. It seems that it is more like something science fiction. But it could open a new door for low-power electronics.
Artificial intelligence comes with substantial computational resources and, of course, a battery life, every time you glance at your phone in order to unlock it with your face. However, in the future, just a piece of glass could recognize your face, without using any power whatsoever. It’s quite different than the typical route to the machine vision.
There would be pieces of glass that look like translucent squares. Imagine some strategically placed bubbles and some impurities put within the glass. It would bend the light in some specific ways in order to make the difference between the images. This is how artificial intelligence work.
How did they prove it?
In order to give us some proof, engineers have found a method to make glass pieces that can identify handwritten numbers. The light that came from an image of a number goes to one end of the glass, and then it focuses on one of the nine specific spots on the other side.
Meagan Kozlovs is a reporter for Debate Report. She’s worked and interned at Global News Toronto and CHECX. Megan is based in Toronto and covers issues affecting her city. In addition to her severe milk shake addiction, she’s a Netflix enthusiast, a red wine drinker, and a voracious reader.