It's nearly impossible to gaze up during the day without spotting sort of cloudy, billowing face staring back at us. But rarely do we get the opportunity to see the faces we so casually trample right beneath our feet. Now, a new program by Onformative is giving us a bird's eye's view of every facial landform on Earth.
Using openFrameworks and Google Maps, Onformative's searching agent, Google Faces, scans satellite image after satellite image with a facial detection algorithm, picking out any potential new geological friends along the way. And it does this at Every. Possible. Zoom level.
Starting at infancy, we're trained to seek out the familiarity of human faces, because it's those same faces hovering over us that (hopefully) also provide safety and comfort. With Google Faces, Onformative hopes to explore this general phenomenon:
Objective investigations and subjective imagination collide to one inseparable process. The tendency to detect meaning in vague visual stimuli is a psychological phenomenon called Pareidolia, and captures the core interest of this project. We were driven by the idea, to explore how the psychological phenomenon of Pareidolia, could be generated by a machine. We wrote an algorithm simulating this tendency, as it continuously searches for face-like shapes while iterating above the landscapes of the earth.
For the application to be able to work independently, the team uses ofxBerkelium, a service wrapper that allows them to capture images from the virtual browser zooming around Google Maps within their own application.
But finding and taking down all these coordinates doesn't come quick—Google Faces will be traveling around the virtual world for the next several months. Of course, not all the resulting finds produce an immediately recognizable face, but just as many more offer visions of an Earth more expressive than you could have ever imagined. So tread lightly—you never know who you're stepping on. [Onformative via Creative Applications Network]