Facial Recognition
 Facial recognition is perhaps the most obvious form of identification
because, as humans, we use it everyday to identify each other.
Biometric facial recognition has come a long way since its
inception. Originally, it was highly inaccurate and required
a highly controlled environment. Thanks to product research
and development, facial recognition systems can now reasonably
accurately identify individuals simultaneously within a crowd.
The identification of a person by their facial image can
be done in a number of different ways:
1). 2D Imaging
Facial recognition in visible light typically models key
features from the central portion of a facial image. Using
a wide assortment of cameras, the visible light systems extract
features from the captured image(s) that do not change over
time while avoiding superficial features such as facial expressions
or hair.
Facial recognition analyses the characteristics of a person's
face images input through a digital video camera. It measures
the overall facial structure, including distances between
eyes, nose, mouth, and jaw edges. These measurements are retained
in a database and used as a comparison when a user stands
before the camera.
To prevent a fake face or mould from faking out the system,
many systems now require the user to smile, blink, or otherwise
move in a way that is human before verifying.
Pose, lighting, and expression have historically prevented
2D facial recognition from working well.
2). 3D Modeling
The biometric data obtained is more comprehensive than 2-D
imagery since it contains information along three axes instead
of two. For applications such as facial recognition, having
the highest possible detail is helpful because it provides
additional data for biometric identification.
3.) Infrared thermography
Infrared thermography is a relatively new area of interest
measuring infrared patterns of facial heat emission.
Thermography senses the temperature of an object. Human beings
stand out against the background due to their higher temperature.
It is capable of mapping not only facial features, but also
the pattern of blood vessels within the skin.
Major benefits of facial recognition are that it is non-intrusive,
requires no physical contact, is continuous, and accepted
by most users. Verification or identification can be accomplished
from two feet away or more, and without requiring the user
to wait for long periods of time or do anything more than
look at the camera.
What sets apart facial recognition from other biometrics
is that it can be used for surveillance purposes. For example,
public safety authorities wanting to locate certain individuals
such as wanted criminals, suspected terrorists, and missing
children. Facial recognition may have the potential to help
the authorities with this mission.
Advantages of facial recognition
- Can be used without the end user interacting with the
reader (non-intrusive).
- Very simple education process for the end user (“look
at the mirror”).
- Simple to enroll.
- Generally accepted by the public.
Disadvantages of facial recognition
- A reasonably controlled environment is required.(Lighting,
etc)
- Cost is higher than other forms of biometrics.
- People can avoid being recognised by covering up (e.g.
scarf and sunglasses).
|
