Spotted at Techland by a dear friend:
If you can’t decide what you want for dinner, Kraft’s new face-scanning technology might be able to help. Kraft and Intel’s new Meal Planning Solution device, which they hope to bring to a supermarket near you, uses analytics determined from your look to see which recipes you would like to make. Goodbye Grandma’s recipe box. You’ve now been replaced by the vast Internet catalogue of Kraft recipes.
In an interview with Mashable, Intel director of retail and digital signage for the embedded and communications group Jose Avalos explained how the Meal Planning Solution worked. Basically the machine can judge age and gender just by scanning your face.Using the shading caused by your natural facial features such as your eyes, which are typically darker than the rest of your face, the device can tell what you look like. It’s about 86 percent accurate in figuring out if the user is a male or female, and slightly better at telling the difference between children and elderly people. Still, it works overwhelmingly well (70 percent) when figuring out if you are a adult or a young adult. Avalos elaborated:
Intel AIM Suite face detection algorithms have statistically learned the pattern of a human face by being trained on an audience database of thousands of pictures of human faces,” he continues. “The demographics of a face can be determined using a similar process to how a face is found, where the patterns being looked at correspond to male or female faces, or certain age brackets (children, young adults, adults, seniors). The algorithms have learned which face features have the strongest weighting for each gender and age bracket. The combination of various facial features such as eye positioning, nose shape, cheek bones, and overall facial structure are among the variables that are taken into consideration during this process.
I still can’t get over the fact that the machine will take one look at me and know what I want to eat. If it predicts I want to make macaroni and cheese (which I make at least once a week), I’m seriously going to be afraid.
One big problem is that scanning your face can’t determine what food you are allergic to or other eating habits that you may have as of yet. Other features have been implemented to further customize the experience. The machine can read your supermarket loyalty cards so it can determine what you buy on a regular basis, which can help point out dietary restrictions like being Kosher or being vegan. Your Kraft iFood Assistant account and KraftRecipies.com browsing activity can be uploaded to the device so it can factor in what recipes you like to look at. The machine can even dispense samples – see the video from Fast Company.
Kraft is still looking for a supermarket chain to partner with, but the first Meal Planning Solution should be installed sometime this year. There’s still some things they want to figure out, like adding social media sharing functions or a rating system so people who have tried the recipes can comment.
So…. what do you think? Since it won’t ever be predicting that I want a carrot or a grapefruit… it’s pretty likely to botch it on my end. And, really… can we also talk about the racial implications of this?
I just… I give up. On life.
Got a Weekend WTF?! to share with the class? Send it on over to firstname.lastname@example.org!
I will stay far away from this machine. It may detect my soulfood weakness and put me on a diet of fried chicken, mac and cheese and sweet potato recipe variations, lol.
It bugs me that they keep referring to people’s gender when what they mean is people’s sex. If a machine could tell gender, now that really would be something.
I’m baffled by the purpose of this machine – even IF it scanned my face and recommended healthy foods……why in the blue blazes would I need or want a machine to tell me such things?
Tokyo has already been experimenting with this type of technology in soft drink vending machines. Here’s a link covering this topic; it might shed a little more light on the subject:
Comments are closed.