Cornell undergraduates Brian Harding and Cat Jubinski built a portable face recognition system for their capstone ECE 4760 project:
Our design consists of an Atmel ATmega644 8-bit microcontroller, a C3088 camera module with an OmniVision OV6620 CMOS image sensor, Atmel’s AT45DB321D Serial Dataflash, a Varitronix MDLS16264 LCD module for output, a 9-volt battery, and a small wooden structure for chin support.
The system is hooked up to a computer to train the pattern-recognition algorithm, but from then on it can enroll new users, delete old users, and recognize up to 20 enrolled users as a standalone system. Their very detailed report claims “an 88% successful login rate with no false positives” and includes testing data, schematics, source code, a priced parts list, and some ideas for improvement in the next prototype. [Thanks, Max!]
10 thoughts on “$30 Face Recognition System”
Comments are closed.
cant this be defeated by just putting a photo of the user in front of the camera?
Thanks Sean!
Will it recognize a photo of the user?
Or rather, will it successfully recognize a photo of a user? If the application isn’t for security, this is a huge success.If it’s security you’re after, you might want to spend more than $30.
mix it with kinect to get 3d data.