Thanks to the power of artificial intelligence, the Internet and the future, you’ll soon be able to Google how many calories are in that brunch you just took down…simply by taking a photo. That Instagram of yours just got a whole lot more interesting.
Google is working on a technology, called Im2Calories, that will estimate the number of calories in a photo by assessing the size of each food iteam. The proposed program isn’t quite foolproof just yet. It’s possible, for example, that Im2Calories could mistaken a fried egg for a poached egg. There is room for users to correct the calorie-counting app, however, according to Google research scientist Kevin P. Murphy, who spoke at last week’s Rework Deep Learning Summit in Boston.
A picture may be worth a thousand words, but how do we figure out how many calories are in it? Popular Science explains the technology: “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.” Essentially, it uses existing information and photographs to gauge the amount of calories in that cronut you just posted to Instagram.
According to Murphy, the technology is aimed at helping people keep food diaries. Snapping a photo eliminates the need to manually input each food item into a system and guess the calorie count. A date has not been announced for the release of Im2Calories, though Murphy points out that this technology can eventually work on completing other favors for humankind, such as finding parking spaces. Now that’s something we can all get behind!
More food-tech stories on Food Republic: