Sure, we were promised jetpacks and flying cars in the future, but there may be an even more exciting development on the way.
During the recent Deep Learning Summit in Boston, a research paper entitled 'Semantic Image Segmentation Using Deep Learning & Graphical Models' caught the attention of those in attendance, as it promised to change the lives of Instagram users everywhere. No longer will pictures of food simply sit there, looking great after being filtered, there may soon exist a technology that will be able to count the calories in them.
Google researcher Kevin Murphy presented the experimental program, dubbed Im2Calories, which analyses the image and uses Google's incredibly vast library of data to pull out the vital stats on those delicious looking pancakes or super-healthy smoothie. The app looks at the pixels of the image and can then make a pretty good guess not only at what it is, but at how much of it there is and what the rough calorie count would be, info that normally has to be manually inputted.
Speaking to Popular Science, Murphy explained that the technology behind this great little app (which is a long way from getting any kind of public release at the moment) has more far-ranging applications than just counting the calories in your food: "Suppose we did street scene analysis. We don't want to just say there are cars in this intersection. That's boring. We want to do things like localize cars, count the cars, get attributes of the cars, which way are they facing. Then we can do things like traffic scene analysis, predict where the most likely parking spot is. And since this is all learned from data, the technology is the same, you just change the data."
Via GOOD. Main pic via Jason Howie/Flickr
