face recognition
The ability to recognize people by their facial characteristics. The most advanced technology is based on the Eigenface algorithm, which maps the characteristics of a person's face into a multidimensional face space. Computers can conduct facial database searches and/or perform live, one-to-one or one-to-many verifications with unprecedented accuracy and split-second processing. Users can be granted secure access to their computer, mobile devices, or for online e-commerce, simply by looking into their Web camera.
The computer can distinguish the same person with different appearances; for example, with or without glasses, change of hair style and seasonal skin color changes. Neural networks were used for earlier face recognition systems, but with Eigenface, the computer cannot be easily fooled by photographs or by someone else with a similar appearance. One of the leading vendors in this area is L-1 Identity Solutions, Stamford, CT (www.l1id.com). See information security and biometrics.
 |
| Face Biometrics |
|---|
| A face is digitized and matched against the face database to determine if the person is authorized to enter a facility or use a system. (Image courtesy of Miros, Inc.) |