ABSTRACT-
Augmenting human computer interaction with
automated analysis and synthesis of facial expressions is a
goal towards which much research effort has been devoted
recently.
Facial gesture recognition is one of the important component
of natural human-machine interfaces; it may also be
used in behavioural science , security systems and in
clinical practice. Although humans recognise facial
expressions virtually without effort or delay, reliable
expression recognition by machine is still a challenge.
The face expression recognition problem is challenging
because different individuals display the same expression
differently.
This paper presents an overview of gesture recognition in
real time using the concepts of correlation and Mahalanobis
distance.We consider the six universal emotional categories
namely joy, anger, fear, disgust, sadness and surprise.
Keywords –Gesture recognition; Cross correlation;
Mahalanobis Distance
I-INTRODUCTION
The task of identifying objects and features from image
data is central in many active research fields. In this paper
we address the inherent problem that a single object may
give rise to many possible images, depending on factors
such as the lighting conditions, the pose of the object, and
its location and orientation relative to the camera.
The face is the most extraordinary communicator, capable
of accurately signalling emotion in a bare blink of a
second, capable of concealing emotion equally well [17].
This paper presents an approach to classify different
gestures. A key challenge is achieving optimal
preprocessing, feature extraction and its representation,
and classification, particularly under the conditions of
input data variation.
From the viewpoint of automatic recognition, several
various evaluation distance functions have been proposed
and investigated theoretically. City block distance,
Euclidean distance, weighted Euclidean distance, subspace
method, multiple similarity method, Bayes decision
method and Mahalanobis distance are known typical
distance functions [18]. Recognition of features in real
time video is yet another challenge, due to variable
characteristics such as brightness, contrast etc. which
affect the video sequences or real times to a large extent.
Such are difficult to analyse and work on using the earlier
filter based approaches.
Results show that the Mahalanobis distance is the most
effective of the seven typical evaluation distance
functions. Considering the foregoing result and the
properties of distribution a modified system which
combines correlation and Mahalanobis distance is
proposed to construct a more accurate and faster system.
The remainder of this paper is organized as follows;
Section 2 briefly reviews the basics of Correlation
Techniques and Mahalanobis Distance and also presents
the comparison between other Distance Functions and
Mahalanobis distance approach.
Section 3 gives the details of our experimental
methodology.
BACKGROUD AD RELATED WORK
As indicated by Mehrabian [5] in face-to-face human
communication only 7% of the communicative message is
due to linguistic language, 38% is due to paralanguage,
while 55% of it is transferred by facial expressions.
Ekman and Friesen [10] developed the most
comprehensive system for synthesizing facial expressions
based on what they call Action Units (AU). They defined
the facial action coding system (FACS). FACS consists of
46 action units (AU), which describe basic facial
movements. Traditionally, template matching methods
using Eigen face by Principal Component Analysis (PCA)
and Fischer face by linear discriminant analysis (LDA) are
popular for face recognition and expression classification
[2]. The well-known Mahalanobis Distance classifier is
based on the assumption that the underlying probability
distributions are Gaussian. The neural network classifiers
and polynomial classifiers make no assumptions regarding
underlying distributions. The decision boundaries of the
polynomial classifier can be made to be arbitrarily
nonlinear corresponding to the degree of the polynomial
hence comparable to those of the neural networks

DOWNLOAD FULL REPORT
http://googleurl?sa=t&source=web&cd=2&ve...F1003.1819&ei=FKkBTrbGOIj5rQf6n4SGAw&usg=AFQjCNGH5Nqz2LY3-Aj8uhJaVLoVlYFeYw&sig2=GjSVLwjN0BrIxnXL3BeiMQ