Face recognition technology is
mostly used in real time applications. Therefore reliability is very important. Face recognition is a task that
humans perform routinely and effortlessly in
our daily lives. Wide availability of powerful and low-cost desktop and
embedded computing systems has created an enormous interest in automatic
processing of digital images in a variety of applications, including biometric
authentication, surveillance, human-computer interaction, and multimedia
management. Research and development in automatic face recognition follows
naturally.
Face recognition technology is now significantly advanced since the time
when the Eigen face method was proposed. In the constrained situations, for example
where lighting, pose, stand-off, facial wear, and facial expression can be
controlled, automated face recognition can surpass human recognition
performance, especially when the database (gallery) contains a large number of
faces.1 However, automatic face recognition still faces many challenges when
face images are acquired under unconstrained environments. In the following
sections, we give a brief overview of the face recognition process, analyze
technical challenges, propose possible solutions, and describe state-of-the-art
performance.
Advantages
It’s impossible for buddy punching to occur, since everyone has to have
their face scanned to clock in.
It’s easy to
add new visitors and track them. Anyone that is not in the system will not be
given access.
It’s no need to having someone system nearby.
Usually they
will work with existing software that you have in place.
It’s very difficult to fool the system and tracking
time, attendance while proving better security
Ear
There are several reasons to use
ear as a biometric authentication system than other biometric authentication
systems. Ear biometric is a passive biometric which means without the
user’s active participation authentication can be done successfully. Ear
does not change during human life as ascertained whereas face changes more
significantly with age than any other part of human body. Cosmetics, facial
hair and hair styling, emotions express different states of mind like sadness,
happiness, fear or surprise.
It is said that color
distribution in ear is more uniform than other parts in human body like face,
iris, retina which means there is less possibility to lose information.
Furthermore, ear images cannot be
disturbed by glasses, beard or make-up.In order to use the ear as a
biometric authentication, we have to prove that each and every person has
unique ears. There is no absolute way of proving that humans have unique ears
but the evidences from certain experiments are help to prove that the nature of
the human ear doesn’t change with the time.Ear is thus considered as a
valuable means for personal identification especially used in criminal
investigation or in surveillance areas different means that can be used for
biometric authentication are images of ear, thermo graphic images of ear and
ear prints that are get by pressing ear against a flat paper.In a device
like smart phone, when the user is in a call, the smartphone can silently take
a photo of the ear and authenticate whether the user is the correct one. This
provides authentication method to the smart phone without user’s knowledge.
Ear recognition mechanism is a
classical pattern recognition system which uses 2D or 3D digital image of the
ear and compares the features with the images that are already in the database.
Eye
When using the eye as one of the biometrics to authenticate
user, two methods are found. One is retinal scan and the other is iris scan.
In retinal scan infrared light
rays are sent to analyze the characteristics of retinal blood vessel patterns.
Blood vessels in the retina absorb infrared rays faster than the surrounding so
that it is easy to analyze characteristics of blood vessels.This method
is rarely used to due to user friendliness and expensiveness. The main drawback
in this method is intrusiveness.
Iris scanning has claimed to be
less intrusive and iris pattern is observed using a photo of the eye taken by
special grey scale camera.Once the iris is identified in the eye, the
software creates a net of curves covering the iris. Based on the darkness
of the points, the software creates the iris code, which characterizes the
iris.
When creating the iris code two
factors are considered. First, the overall iris code darkness of the image is
influenced by the lighting conditions so the darkness threshold used to decide
whether a given point is dark or bright cannot be static, it must be
dynamically computed according to the overall picture darkness. And second, the
size of the iris dynamically changes as the size of the pupil changes. Before
computing the iris code, a proper transformation must be done. In the decision
process the matching software given 2 iris codes computes the Hamming distance
based on the number of different bits.The Hamming distance is a score (within the
range 0 – 1, where 0 means the same iris codes), which is then compared with
the security threshold to make the final decision.
Computing the Hamming distance of
two iris codes is very speed fast (it is in fact only counting the number of
bits in the exclusive OR of the two iris codes). It is said that the iris recognition was the
fastest identification out of all the biometric systems we could work with.
Discrimination rate of false acceptance have never encountered and the false
rejection rate was low. The main
advantage of the iris
scans is the
ability to perform
them from a
distance of up to
three feet and short
time of scan
of only 20
seconds initially, with
subsequent identification
requiring only two
seconds. Glasses and contact
lenses do not interfere with the scanning process and identification.
Even if the accuracy of
the biometric techniques is not perfect yet, there are many mature biometric
systems available now. Proper design and implementation of the biometric system
can indeed increase the overall security, especially the smartcard based
solutions seem to be very promising. Making a secure biometric systems is,
however, not as easy as it might appear. The word biometrics is very often used
as a synonym for the perfect security. This is a misleading view. There are
numerous conditions that must be taken in account when designing a secure
biometric system. First, it is necessary to realize that biometrics are not
secrets. This implies that biometric measurements cannot be used as capability
tokens and it is not secure to generate any cryptographic keys from them.
Second, it is necessary to trust the input device and make the communication
link secure. Third, the input device needs to check the liveners of the person
being measured and the device itself should be verified for example by a
challenge response protocol.
·