How We Spot Friends in the Crowd Before Being Able to See Their Face

Facial recognition is already very much in place in all sorts of ways, from Facebook to surveillance cameras. Perhaps now they’ll add body recognition too

20131010022028416052683_06971760fc_z.jpg
Stephen McLeod Blythe

You’re standing in a crowd, and suddenly you recognize a friend, far off in the distance. But you’re too far away to see her face, so how did you know it was her? It turns out that we’re good at recognizing people from their body language, stance and other physical cues that we can observe long before we see their faces.

The research, published the journal Psychological Science, looked at just how we rely on body language for identification. What they found was that we’re actually just as good at recognizing people from faces as we are from other cues. “Accuracy in identifying the person without the face was identical to that in identifying the whole person,” the researchers write.

This happened even if the subjects weren’t consciously looking for body cues. Participants generally thought they were looking at the faces in the photos they were shown, but eye-tracking equipment revealed that instead they were looking all over.

Lauren Kirchner at Pacific Standard digs into some of the applications of this kind of research:

According to the University of Texas, this study was funded by the Technical Support Working Group of the Department of Defense, and the work of one of its co-authors, P. Jonathon Philips, is partially funded by the FBI. The fact that these agencies are working to find ways to make facial-recognition technology even more accurate than it already is won’t be surprising news, but neither will it be welcome news, to many people.

And facial recognition is already very much in place in all sorts of ways, from Facebook to surveillance cameras. Perhaps now they’ll add body recognition too.

More from Smithsonian.com:

Facial Recognition Software Makes Art from Random Noise
The Privacy Wars: Goggles That Block Facial Recognition Technology

Get the latest stories in your inbox every weekday.