Facial recognition

Facial recognition technology identifies people by analyzing features of the face not easily altered &mdash; the upper outlines of the eye sockets, the areas around the cheekbones, and the sides of the mouth. The technology is typically used to compare a live facial scan to a stored template, but it can also be used in comparing static images such as digitized passport photographs. Facial recognition can be used in both verification and identification systems. In addition, because facial images can be captured from video cameras, facial recognition is the only biometric that can be used for surveillance purposes.

The two primary algorithms used in facial recognition systems are based on the eigenface method and local feature analysis (LFA). The eigenface method looks at the face as a whole and represents a person’s face as a set of templates that require 1,300 bytes. LFA breaks down the face into feature &mdash; specific fields, such as the eyes, nose, mouth, and cheeks, creating an 84 byte template.