You know how it’s really fun sometimes to take pictures and look at pictures of beautiful, delicious, decorative food?
Ya, well Google hates that.
That’s why they’re funding a research project called Im2Calories which will likely spin off an app that measures calories based on images of food; “high res” not required.
In other words, Google just found one more way for Instagram to make us hate ourselves.
Using “sophisticated deep-learning algorithms” to judge the shape and size of a food item, the technology will use visual analysis and pattern recognition based on existing foods – along with an ever-evolving dataset of relative caloric metrics – to chew up an image of your meal (including condiments) and spit out an estimate of the calories it contains.
Given the number of people in North America suffering from weight-related health problems, it’s not difficult to imagine how something like this could come in handy.
Yeah, but do nutrition facts tell you how DELICIOUS something is?
And given the number of people in North America enjoying a regular dose of food porn on their smartphones, it’s not difficult to imagine how something like this could make someone want to egg the Google offices.
The accuracy of the estimates are obviously relevant, but the degree of accuracy isn’t too much of a concern for Kevin Murphy, hereinafter referred to as Buzz Killington, the Google Research Scientist who presented the technology overview at a summit last week in Boston.
“To me it’s obvious that people really want this and this is really useful…I have colleagues in epidemiology and public health, and they really want this stuff…If it only works 30 percent of the time, it’s enough that people will start using it,” said Killington.
Nobody knows when the technology will be available to the public or how much it will cost when it is released. But one thing we do know is that if a plate of food looks sexy enough for us to take its photo and tag it with #foodporn, then giving us a calorie count is definitely #TMI.
