A food diary can help you keep track of calories, helping you to feel in control and prevent over-eating. Now Americans have taken it a step further with PlateMate, which estimates calories of a meal from a mere snapshot of the food on the plate.
Developed by computer scientists at the Harvard School of Engineering and Applied Sciences (SEAS), PlateMate asks people to distinguish between foods in the photo, identify what they are, and estimate quantities. The nutritional value for the meal are then automatically calculated.
The researchers insist PlateMate's calorie estimates have proved, in tests, to be just as accurate as those of trained nutritionists.
The researchers did encounter some common-sense problems with sending photographs to strangers without any context. A latte made with whole milk looks no different than one made with skim milk, a fast-food burger might pack in more calories than one cooked at home.
They say vetting the people assessing calories improved the accuracy of the tool.
“A lot of prior crowdsourcing research has been about making crowds do things that we wish computers could do, like shorten an 800-word essay to 500 words and have it still make sense,” said Jon Noronha, who co-developed PlateMate as an undergraduate at Harvard and now works at Microsoft. “That’s something computers can almost do, but it’s just beyond their reach.”
“What makes the nutrition application so interesting as a problem in crowdsourcing is that computers are so very far away from doing it on their own because food is such a human thing.”