If you’re one of the many Instagram users who can’t resist snapping a picture of each weekend brunch, workday lunch and dinner out at a restaurant, your practice might soon pay off.
At a recent tech conference in Boston, Google revealed their new software that uses “deep learning algorithms” to judge how many calories are on a plate, all from a simple picture. The photo doesn’t have to be a high quality image, even an Instagram shot will do, and the technology should be able to identify the food, pinpoint the serving size and then estimate how many calories are there. Google is calling the new technology Im2Calories and Google’s research scientist Kevin Murphy said the technology could make food journaling a lot easier.
He also said users can correct the technology if it happens to read the photo wrong and, no, it’s not a perfect science yet. According to Popular Science, Murphy has pointed out some flaws.
To me it's obvious that people really want this and this is really useful. 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.
Google has reportedly filed for a patent, but there’s no estimated arrival for public use. Until then it looks like Instagram and your food journal app will have to suffice.