Unseen Portraits
ARTISTIC INVESTIGATION OF FACE-TRACKING ALGORITHMS, 2015
Philipp Schmitt & Stephan Bogner (DE)
Computer vision relies on algorithms to make sense of the world. Unseen Portraits investigates what face recognition algorithms consider to be a human face. How much do you have to deform someone’s features to make them invisible to a machine?
Portrait photos of visitors are distorted on a screen. A surveillance camera films the distortion and uses facial recognition software to scan the camera footage for faces while the image becomes more and more obscured.
The moment the photo becomes too warped and the face can't be recognised by the algorithm anymore, the software takes a screenshot. The visitor is now invisible to computer vision.
Despite its subject matter, Unseen Portraits isn't a conceptual investigation of the algorithms used. Rather, the project uses computer vision software as an artistic tool, creating images reminiscent of Francis Bacon's self-portraits from the 1970s. It isn’t so much a mechanism to hide from the software as it is a way to capture the software’s flaws in a work of art.
BIO
Stephan Bogner and Philipp Schmitt are German designers (and sometimes artists), currently studying Interaction Design at the University of Design in Schwäbisch Gmünd, Germany. They are curious about new ways of using upcoming and established technologies. Stephan and Philipp are friends who enjoy working as a team to tackle topics such as machine vision or robotics. Their work has been featured on CreativeApplications, WIRED, Fast Company and at Bundes.Festival.Film.Technologies at the HKU.