Facebook is getting ever better at recognizing you in your (or your friends') pictures—but there's a lot to identifying who you are from a two dimensional image.

The company uses a system called DeepFace, which is about 97-percent as accurate as a human eye at recognizing faces. It's pretty scary, not something you'd necessarily want just for the sake of tagging photos. The system has a bunch of data that it analyzes, and some of that information was made public in 2013 when Facebook let users download this proprietary data; an option the company took away shortly after. Media artist and teacher Brian House took his downloaded data, along with another student's, and put it on display for a project they call “Eternal Portraits.” 

From House:

Facebook uses face recognition software to identify its users in photos. This works via a ‘template’ of your facial features that is created from your profile images. These features — the distance between your eyes, the symmetry of your mouth — generally do not change over time. Unlike a photograph, which captures some ephemeral expression of who you are at a particular moment, a face recognition template forever remains your portrait. It is all possible photos, taken and untaken, by which you, or someone else, might document your life.

Check out more here

[via Brian House]