Avoiding facial recognition detection

For those concerned about the probable misuse of ComputerVision technology in the facial recognition realm, there is a new project underway which can help counteract unwanted matching. That project is known as CV Dazzle. It comes as a response to the rising concerns of privacy that accompany advancements in facial recognition technology.

According to the project’s mastermind, Adam Harvey, “The name is derived from a type of camouflage used during WWI, called Dazzle, which was used to break apart the gestalt-image of warships, making it hard to discern their directionality, size, and orientation. Likewise, the goal of CV Dazzle is to break apart the gestalt of a face, or object, and make it undetectable to computer vision algorithms, in particular face detection.”

In the past, people might have used sunglasses or masks as way of hiding themselves. However, many facial recognition applications are programmed to account for the changes a face undergoes (as viewed from the standpoint of a computer) when an individual puts on sunglasses. Meanwhile, wearing masks in public is often times either illegal, or at the very least, somewhat questionable.

Instead of relying on these types of disguises, CV Dazzle – which began in the Interactive Telecommunications Program at New York University, uses conventional methods like makeup, hairstyle, and clothing choices to partially hide or obscure an individual’s face.

CV Dazzle vs PhotoTagger from Adam Harvey on Vimeo.

Leave a Reply

Post Navigation