Snapping food pics is about to get more useful than ever, thanks to a new artificially intelligent technology developed by researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL). It's called Pic2Recipe, and the algorithm is able to give you a list of ingredients and recipe recommendations for each food shot you take. Can you imagine the chef-like possibilities?
Before you get your hopes up, we're only talking about the technology right now. It's not an app — yet.
To create the cool new system, CSAIL graduate student Nicholas Hynes and his team of researchers compiled data from popular recipe websites into one database called Recipe1M. It can then find common ingredients and suggest similar recipes from their very own database.
I'm no scientist, but this sounds life-changing in a world where food photography is at the forefront of our social media lives. I mean, a restaurant in England is even offering its customers "Instagram kits" to ensure their photos are perfectly lit and ready for the 'gram.
Now, these researchers are saying we could potentially turn our photo libraries into a cookbook? Beautiful.
In an interview with Gizmodo, Hynes explained the complexities of trying to "teach" their system — it sounds like something straight out of Person of Interest — how to recognize different cooking methods (e.g. steaming versus frying).
He also thinks Pic2Recipe will help people become more familiar with what they're eating. He told Gizmodo,
This could potentially help people figure out what's in their food when they don't have explicit nutritional information. For example, if you know what ingredients went into a dish but not the amount, you can take a photo, enter the ingredients, and run the model to find a similar recipe with known quantities, and then use that information to approximate your own meal.
Yep, I need it.
There's no word on when Pic2Recipe will finally be an app. However, as soon as it hits the App Store, I will pay whatever amount necessary.
You can try the demo here.