New computer program sees plaid shirt, labels you a hipster

Image via Shutterstock.

Your computer might soon become as judgmental as your high school classmates.

A new computer program being developed at the University of California in San Diego is using an algorithm to determine which social category you fit into, based off of your photos on social media.

Developers made the program by feeding it tons of photo sets, giving them each their own label and specific features to look out for. The program then tries to find these features to predict in a new photo—like plaid shirt and skinny jeans, or black eyeliner and tattoos, as indicative clues.

The program is similar to the facial recognition software Facebook uses, but rather than just focus on the face, it's trained to focus on the entire body to search for specific features. It identifies and categorizes people into eleven different "urban tribes" such as "hipsters," "bikers," "ravers," "surfers," and "goths."

An example of "urban tribe" photos the program was fed.

The program's developer, Computer Science Professor Serge Belongie, told ABC News he was inspired to create the program by a particular type of photo popping up on his Facebook feed.

"It was the group shot where people are eating dinner and someone says, 'Hey! Let's take a photo!'" Belongie said. "There's something about those photos that pop out and says what type of people they are."

The ultimate goal—if the program succeeds—is for websites to create a more personalized visit for users, including "the potential to improve recommendation services, context sensitive advertising and other social analysis applications," the USCD project page states.

Belongie admitted the software is only successful 48 percent of the time; which makes sense because you could wear tortoiseshell glasses, have a patchy bear, drink fair-trade coffee, and still not consider yourself a hipster.

"It's embarrassing to mix up goths with hipsters, but it's kind of reasonable based on the limited vision the computer has," Belongie noted. "Imagine you have a soda straw and you're only looking at the photo through the straw. You're only looking at little patches of the image."