Autonomous Faces are diverse, semi-rigid, semi-flexible, culturally significant, and

Autonomous face recognition
is the process of locating and identifying faces in a scene using pattern
recognition techniques. While humans recognize faces many times a day with
apparent ease, automating this process has challenged researchers for the past
two decades. What does an automated face recognition system offer us to warrant
the years of research this problem has received? A system that automatically
recognizes faces would be useful for several reasons. From a security perspective,
an automatic face recognition system could enhance current access control
systems by authenticating a user’s identity. Examples of such access control systems
are secure computer systems, bank automatic teller machines, and automatic card
readers. In fact, any organization or system that permits access based on a
person’s identity would find a face recognition system useful. Other security
applications for a face recognition system would be criminal identification and
scanning airports for terrorists. Finally, this system could be adapted for use
in a speech recognition system or a visual communications system 40.

Face detection is a computer
technology that determines the locations and sizes of human faces in digital
images. For example, by scanning the faces of people entering a secure
or restricted area, a face recognition system could be used to control entry.
Similar defense related applications of face recognition can easily be found in
antiterrorism and antinarcotics operations. Face recognition is a relevant subject in pattern recognition, neural
networks, computer graphics, image processing and psychology. Faces are
diverse, semi-rigid, semi-flexible, culturally significant, and part of our
individual entity. There are many approaches to the face-recognition problem.
Some techniques rely on a single face template or a model for detection; others
relay on facial sub-features. A variety of detection techniques are employed
from correlation, neural networks, eigen templates, Bayesian model and flexible
models. Given an arbitrary image faces in the image, the goal of face detection
is to determine whether or not there are any faces in the image and, if
present, return the image location and extent of each face. A typical sequence
of steps in the identification procedure is as follows.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

(1)
Determine a set of independent features to represent a face

(2)
Represent the known faces in terms of their features in a database

(3)
Determine the feature values of the new (unidentified) face

(4)
Use a matching scheme to obtain a “best” fit with the known faces

Detecting faces in a
single image:
The single- image detection can be broadly classified into four categories
which are 1

(i)       Knowledge-based methods,

(ii)     Feature-based methods,

(iii)    Template matching,

(iv)    Appearance-based methods

Knowledge-based
methods: As the number of
expected targets becomes larger and larger, it becomes difficult to for a human
observer to identify an object from images of poor quality. Hence, there is a
need to develop a knowledge-based recognition system. Knowledge based methods are
basically rule based methods and are mainly designed for face localization. In
knowledge based methods, the rules capture the relationships between facial
features. The rules are derived from a researcher’s knowledge of human faces.
For example, a face often appears in an image with two eyes that are symmetric
to each other, a nose and a mouth. The relationship between features can be
represented by their relative distances and positions. Facial features in an
input image are extracted first, and face candidates are identified based on
the derived rules. A verification process is usually applied to reduce false
detection.