Nice Op-Art column by Adam Harvey in the NY Times about thwarting face-detection algorithms with makeup and hair styling:
Next year the Janus program, an initiative run by the director of national intelligence, will begin to collect photographs of people’s faces from social media websites and public video feeds. Machines will then use powerful algorithms to pair those photos with existing biometric profiles.
The Janus program isn’t alone: Facial-recognition technology is quickly becoming a mainstay of commercial and government surveillance systems. While it can provide benefits in automation and security, it is also a threat to privacy. Sophisticated algorithms can already extract information about your gender, age and even mood from a single image, and then link those physical attributes to commercial or government databases.
This powerful surveillance technology is cheap, ubiquitous and unregulated.
My project, CV Dazzle, explores how fashion can be used as camouflage from face-detection technology, the first step in automated face recognition. The name is derived from a type of World War I naval camouflage called Dazzle, which used cubist-inspired designs to break apart the visual continuity of a battleship and conceal its orientation and size. Likewise, CV Dazzle uses avant-garde hairstyling and makeup designs to break apart the continuity of a face. Since facial-recognition algorithms rely on the identification and spatial relationship of key facial features, like symmetry and tonal contours, one can block detection by creating an “anti-face.”
Have an amazing project to share? Join the SHOW-AND-TELL every Wednesday night at 7:30pm ET on Google+ Hangouts.
Join us every Wednesday night at 8pm ET for Ask an Engineer!
Learn resistor values with Mho’s Resistance or get the best electronics calculator for engineers “Circuit Playground” – Adafruit’s Apps!
Maker Business — Raspberry Pi and CoderDojo Join Forces
Wearables — Gold glow
Electronics — Linear Love
Biohacking — Read Faster Using JETZT or SPEEDREAD
No comments yet.
Sorry, the comment form is closed at this time.