A presenter at Black Hat 2011 put forward their research on using Facebook as a facial recognition database. Not only do people upload a lot of pictures of themselves and their friends, they also tag them with the names of the people in the pictures. This means that there is a large sample of data to be used, with the same face available from multiple angles, lighting conditions and backgrounds. The findings; nearly perfect recognition and re-identification of people in the database with a photo taken from a smartphone in under 3 seconds. Thank Techware Labs for the chill that just headed down your spine.
"Every month Facebook users upload 2.5 Billion photos. With each upload users may identify and tag not only themselves, but everyone in the photo. What if we could use this massive attendance sheet of the world in a larger way. Say with facial recognition and location information? Today Alessandro Acquisti presented his research and attempts at doing just that."
Here is some more Tech News from around the web:
- Inside Turntable.fm: saving music radio from itself @ Ars Technica
- Google allows C and C++ code to run in Chrome web browser @ The Inquirer
- Lost in Limbo @ The Tech Report
- Smartphone images can hijack BlackBerry servers @ The Register
- Asus RT-N56U Black Diamond Router @ X-bit Labs
- One Week left to Win Steelseries 5h v2 MOH and Siberia v2 iPod @ XSReviews