Face Recognition

Published on January 2017 | Categories: Documents | Downloads: 65 | Comments: 0 | Views: 558
of 27
Download PDF   Embed   Report

Comments

Content

Face Recognition

Pushpendra Kumar Pateriya
Assistant Professor

Facial-scan’s strengths
It has the ability to leverage existing image
acquisition equipment.
 It can search against static images such as
driver’s license photographs.
 It is the only biometric able to operate
without user cooperation.
 ...


Facial-scan’s weaknesses
Changes in acquisition environment reduce
matching accuracy.
 Changes in physiological characteristics
reduce matching accuracy.
 It has the potential for privacy abuse due to
noncooperative enrollment
 and identification capabilities.


Components

Face Recognition Through
Software
The software used for facial recognition
recognizes and distinguishes the face from
its background by some of the common
nodal points given below.
* Distance between the eyes
* Nose width
* Depth of the eye sockets
* Cheekbone shape
* Length of jaw-line

How Facial-Scan Technology
Works?







Steps:
Image Acquisition
Image Processing
Distinctive Characteristics Extraction
Template Creation
Template Matching

Steps in the facial recognition
prcess

Normalization/Preprocessing of Image
Normalization: Once the face has been detected
(separated from its background), the face needs to
be normalized. This means that the image must be
standardized in terms of size, pose, illumination,
etc., relative to the images in the gallery or reference
database. To normalize a probe image, the key
facial landmarks must be located accurately. Using
these landmarks, the normalization algorithm can (to
some degree) reorient the image for slight
variations. Such corrections are, however, based on
statistical inferences or approximations which may
not be entirely accurate.

Competing Facial-Scan
Technologies





Eigenface
Feature Analysis
Neural Network
Automatic Face Processing

Eigenfaces


Eigenface, roughly translated as “one’s own
face,” is a technology patented at MIT that
utilizes a database of two-dimensional,
grayscale facial images (Eigenfaces) from
which templates are created during
enrollment and verification.

Eigenface...


Eigenfaces are a set of eigenvectors used
in the computer vision problem of human
face recognition. The approach of using
eigenfaces for recognition was developed
by Sirovich and Kirby (1987) and used by
Matthew Turk and Alex Pentland in face
classification. It is considered the first
successful example of facial recognition
technology.

Eigenfaces...


These eigenvectors are derived from the
covariance matrix of the probability
distribution of the high-dimensional vector
space of possible faces of human beings.

Eigenface...

Feature Analysis

Feature Analysis
The most widely utilized facial recognition
technology.
 This technology is related to Eigenface, but
is more capable of accommodating
changes in appearance or facial aspect
(smiling versus frowning, for example).
 Visionics, a prominent facial recognition
company, uses Local Feature Analysis
(LFA), which can be summarized as a
reduction of facial features to an
“irreducible set of building elements.


Feature Analysis...




Feature analysis derives enrollment and
verification templates from dozens of
features from different regions of the face
and also incorporates the relative location of
these features.
The extracted features are building blocks,
and boththe type of blocks and their
arrangement are used for identification and
verifi-cation.

Facial recognition – spacing of facial features.

Feature Analysis...







The extracted features are building blocks, and both
the type of blocks and their arrangement are used for
identification and verification. It anticipates that the
slight movement of a feature located near one’s mouth
will be accompanied by relatively similar movement of
adjacent features.
Since feature analysis is not a global representation of
the face, it can accommodate angles up to
approximately 25 degrees in the horizontal plane, and
approximately 15 degrees in the vertical plane.
A straight-ahead facial image from a distance of 3 feet
will be the most accurate.

Neural Network
Neural network systems employ algorithms
to determine the similarity of the unique
global features of live versus enrolled or
reference faces, using as much of the facial
image as possible.
 Neural systems are designed to learn which
features are most effective within the body
of users that the system is intended to
serve.


Neural Network...






Features from both the enrollment and the
verification faces vote on whether there is a
match.
An incorrect vote, such as a false match,
prompts the matching algorithm to modify
the weight it gives to certain facial features.
Neural network systems learn which features
are most effective for matching and
pragmatically adjust themselves based on
the methods that have proven most effective.

Neural Network...




Since these technologies are capable of
learning over time, they may be capable of
reducing the time-based performance
problems found in many facial-scan
systems.
An artificial neuron is a mathematical
function conceived as a crude model, or
abstraction of biological neurons. Artificial
neurons are the constitutive units in an
artificial neural network.

Automatic Face Processing
Automatic face processing (AFP) is a more
rudimentary technology, using distances and
distance ratios between easily acquired
features such as eyes, end of nose, and
corners of mouth.
 Though overall not as robust as Eigenfaces,
feature analysis, or neural network, AFP
may be more effective in dimly lit, frontal
image-capture situations.
 It is often used in booking station
applications in which environmental
conditions are more controlled.


Facial-Scan Deployments


Facial-scan is generally deployed in
environments where existing acquisition
technology or facial images are in place,
such as public-sector ID card applications,
surveillance systems, and booking stations.

Facial-Scan Weaknesses

Face recognition is not perfect and struggles to perform under
certain conditions. Ralph Gross, a researcher at the Carnegie
Mellon Robotics Institute, describes one obstacle related to the
viewing angle of the face: "Face recognition has been getting
pretty good at full frontal faces and 20 degrees off, but as soon
as you go towards profile, there've been problems."
Other conditions where face recognition does not work well include
poor lighting, sunglasses, long hair, or other objects partially
covering the subject’s face, and low resolution images.
Another serious disadvantage is that many systems are less
effective if facial expressions vary. Even a big smile can render
the system less effective. For instance: Canada now allows only
neutral facial expressions in passport photos.

Weaknesses...

References














Samir Nanavati, Michael Thieme, Raj Nanavati, “Biometrics:
Identity Verification in a Netwrorked World”, 1st Edition, 2008
Wiley
http://visgraph.cs.ust.hk/biometrics/Papers/Multi_Modal/com-pam
i1993-10-01.pdf
http://doras.dcu.ie/285/1/lncs_3212.pdf
http://www.securityrevue.com/article/2011/01/close-circuit-televis
ion-cameras-survelliance-and-biometric-identification-system/
http://www.surrey.ac.uk/cvssp/research/facial_analysis/
http://www.cse.msu.edu/rgroups/biometrics/Publications/Face/Kla
rePaulinoJain_AnalysisFacialFeaturesIdenticalTwins_IJCB11.pdf
http://electronics.howstuffworks.com/gadgets/high-techgadgets/facial-recognition.htm
http://www.ppt.gc.ca/info/photos.aspx
http://www.informedia.cs.cmu.edu/documents/rowley-ieee.pdf
http://www.circuitstoday.com/working-of-facial-recognition-system

Require Knowledge Set:
http://www.itl.nist.gov/div898/handbook/pmc/s
ection5/pmc541.htm
http://en.wikipedia.org/wiki/Covariance_matrix

Sponsor Documents

Or use your account on DocShare.tips

Hide

Forgot your password?

Or register your new account on DocShare.tips

Hide

Lost your password? Please enter your email address. You will receive a link to create a new password.

Back to log-in

Close