This form of biometry is fairly straightforward. It basically tries to match various facial characteristics such as distance between eyes, width of nose, cheekbones, jaw line and chin characteristics to arrive at an identity match. Using the captured image, the biometric software makes certain calculations to arrive at the right angle for matching the photograph to the stored sample template.
It then plots a series of points and measures the distance between them to arrive at a sample-this sample is then used to match against photographs stored in the database.
Facial recognition is mostly used by crime fighting and security units as checks against shady characters and known felons. The use of this form of biometry has found limited success in practical applications due to various factors such as facial features being covered by hair or hats, the reflection from spectacles, angle of captured image and poor lighting.
However, progress continues to be made in this area and future implementations look promising.
More Tags :