If you're trying to lose a little weight or simply trying to eat healthier, then Google has a project in the works that could make your life a whole lot easier. It can tell you how many calories are sitting on your plate just by looking at a photo of your food using artificial intelligence.
The project, called Im2Calories, sounds like something straight out of a science fiction movie, but it's not. It can look at the types of food on your plate and calculate a rough calorie estimate based on size and other factors. It might not be perfect, but it would give people a better understanding about what they're putting in their bodies.
“To me it's obvious that people really want this and this is really useful,” [Google research scientist Kevin Murphy] said. “Ok fine, maybe we get the calories off by 20 percent. It doesn't matter. We're going to average over a week or a month or a year. And now we can start to potentially join information from multiple people and start to do population level statistics. I have colleagues in epidemiology and public health, and they really want this stuff.”
The technology behind Im2Calories works by examining photos of your food and comparing them to what it knows about existing photos that look similar. So, it should get better as more images and data are added to the system.
Like many deep learning applications, it marries visual analysis—in this case, determining the depth of each pixel in an image—with pattern recognition. Im2Calories can draw connections between what a given piece of food looks like, and vast amounts of available caloric data.
Im2Calories isn't completely automated, though. The software has options that let users correct data when the program makes a bad assumption that could affect the calorie count, like confusing a fried egg with a poached egg.