Computer scientists at the Harvard School of Engineering and Applied Sciences (SEAS) have developed a tool that uses crowdsourcing to estimate the nutritional value of a plate of food. With PlateMate, users simply snap a photo of their meal and everyday people assess what’s on the plate and the quantity. Then, the tool automatically calculates the amount of calories the meal has.
Some initial hurdles for this crowdsoucring tool were users misidentifying foods from other cultures or were too lazy to select the right foods. But after tweaking the tool to included a structured workflow and some cultural awareness, PateMate has been tested to be just as accurate in providing calorie estimates as as a group of trained nutritionists.
Eric Hysen, who co-developed PlateMate with Jon Noronha, explained that:
Nutrition is such a pervasive issue in our society, from counting calories at the dinner table to burning them on the treadmill. People worry about whether they’re doing the right thing. It seemed like a really good opportunity for crowdsourcing to make difference.