New Cinema: Dance Like Michael Jackson... Using Your Face

Pretty much everyone's a fan of Michael Jackson's music and pretty much everyone, at some point in their lives, has attempted to dance like him. Those iconic moves are infectious, the only problem is most of us don't have the skill or dedication to pull it off. All we have is our own self-delusion (your ten-year-old self may've convinced your mom you're as good as MJ, but let's be honest: you sucked). But how about if you could dance like Michael Jackson just by using facial expressions? That surprised look you've just pulled, well that could be a small moonwalk.

This is the idea behind a project from our New Cinema hackathon, a collaboration between The Creators Project, Eyebeam, and Framestore that explored bold new ways of cinematic storytelling. This particular project, called Face Dance, involved filmmakers Ariel Schulman and Henry Joost (aka Supermarché) and creative coders Aaron Meyers, Lauren McCarthy, and James George. The group decided to use facial recognition software and motion capture of a Michael Jackson impersonator to create a bank of moves for a program that allows people to control a projected image of the King of Pop by moving the muscles in their face.

Meaning with the help of depth sensing face detection software you can turn smiles, frowns, and blinks into spins, legs kicks, and crotch grabs. Shamoan. "When you watch this dance, it's not just about watching someone do a cool dance," explains George." It's about the knowledge that there's an interaction taking place, that it's being performed in this cool, funny way. And seeing the relationship between somebody's face moving and the dance happening." It all adds up to a novel, inventive, and amusing way to bust some MJ moves.

This is not the first, nor will it be the last time people use facial recognition software to explore the potential applications of the human face and interaction software. Here's a rundown of some previous projects that utilise similar software in impressive and unusual ways.

Arturo Castro, Faces

Building on research from the openFrameworks community,

Castro

created a project that lets users substitute their face for someone else's in real-time using projection and a face tracking add-on for openFrameworks. One minute you're a freaky-looking Brad Pit, the next you're a terrifying Salvador Dali.

Kyle McDonald and Matt Mets, Blind Self Portrait

In

McDonald

and Mets' piece users close their eyes while computer vision tracks their face, which is then interpreted by a machine which then guides the person's hand to create a self-portrait. Creating a collaboration between human and machine for a unique interpretation of the human face.

Jeremy Bailey, The Future Of Television

Using FaceOSC software, which allows users to make music with their face,

Jeremy Bailey

's project imagines a time when television channels are not just shown on dull LCD screens, but instead are projected onto your face. Make a facial movement to change the channel and wear your televisual viewing like a proud mask of glitchy visuals.

Karolina Sobecka, All the Universe is Full of the Lives of Perfect Creatures

Like many of the above works,

Sobecka

's installation utilizes

Jason Saragih

's Facetracker library, but with this piece users' facial expressions are imitated by a virtual animal mask reflected in a mirror which appears directly over their own image, turning you, momentarily, into a snarling or growling beast.

Motion capture facilities and mentorship for Face Dance courtesy of .

@stewart23rd