How to Hide from Machines: The perilous glamour of life under surveillance | DisMagazine

See on Scoop.itdigital culture

CV Dazzle is a response. It is a form of expressive interference that combines highly stylized makeup and hair styling with face-detection thwarting designs. As camouflage, this facial markup works to protect against automated face detection and recognition systems by altering the contrast and spatial relationship of key facial features. The variations are limitless.

When disrupting face-detection it is advisable to avoid wearing makeup that enhances facial features. For example, emphasizing the darkness around the eyes with eye shadow or eyeliner would make your face more visible to face detection algorithms. Ideally, your face would become the anti-face, or inverse. In the animal kingdom, this inverse effect is known as countershading. A similar effect can be achieved by creating a partial inverse that targets key areas of the face. The CV Dazzle protocols were developed to thwart face detection by OpenCV, which uses the Viola Jones method. The looks shown here were also tested and validated against Facebook’s PhotoTagger, Google’s Picasa, and eblearn.


See on