International Journal of Computer Trends and Technology- volume3Issue4- 2012
ISSN: 2231-2803 http://www.internationaljournalssrg.org Page 522
Neural Network associated with recognition
of Facial Expressions of Basic Emotions
Rehmat Khan, Rohit Raja
Shri Shankaracharya Engineering College,CSVTU
Bhilai(C.G.), India.
Abstract—The science of image processing, helps t to
recognize the human gesture for general life applications.
For example, observing the gesture of a driver when he/she
is driving and alerting him/her when in sleepy mood will be
quite useful. Human gestures can be identified by observing
the different movements of eyes, mouth, nose and hands.
The face is a rich source of information about human
behavior. The proposed method will recognize the facial
expression from a well captured image. The approach for
Facial Expression Recognition System is based on PCA and
Neural Network. For any Facial Expression Recognition, it
is necessary to extract the features of face that can be
possibly used to detect the expression. For Feature
Extraction the Principal Component Analysis will be used.
After extracting the features the eigenvectors will be
generated this will be further fed into the Neural Network
for Expression Recognition. The paper briefly describes the
schemes for selecting the image and then processing the
image to recognize the expressions.
Index Terms— Eigen faces Eigen Vector, Eigen Value,
Neural Network, Back Propagation, Facial Expression
Recognition System, FERS.
I. INTRODUCTION
FACIAL expression is one of the most powerful,
natural, and immediate means for human beings to communicate
expression of their emotions and intentions. The face can
express emotion sooner than people verbalize or even realize
their feelings. The need for reliable recognition and
identification of facial users is obvious.
Mehrabian[11] pointed out that 7% of human communication
information is communicated by linguistic language (verbal
part), 38% by paralanguage (vocal part) and 55% by facial
expression. Therefore facial expressions are the most important
information for emotions perception in face to face
communication. For classifying facial expressions into different
categories, it is necessary to extract important facial features
which contribute in identifying proper and particular
expressions. Recognition and classification of human facial
expression by computer is an important issue to develop
automatic facial expression recognition system in vision
community. Further facial expressions can be ambiguous. They
have several possible interpretations. Facial expression
recognition should not be confused with human emotion
recognition as is often done in computer vision. Facial
expression recognition deals with classification of facial motion
and facial feature deformation in to abstract classes that are
purely based on visual information.
In this paper, we proposed a computational model of
facial expression recognition, which is fast, reasonably simple,
and accurate. The proposed approaches have advantages over
the other face recognition schemes in its speed and simplicity,
learning capacity and relative insensitivity to small or gradual
changes in the face image.
The method of facial Expression Recognition System
consists of four components: input image, image processing,
component analysis or feature selection and Expression
Recognition. Image processing consists of scaling and image
rendering to prepare the face for expression recognition. The
process of expression recognition involves processing images by
extracting the facial features, and then using an algorithm to
identify the expressions made based on the movements of the
feature made. The working of project can be understood by the
diagram as shown in Fig1. In the Figure there are total 5
modules. The Input image, Image Preprocessing, Feature
Extraction (Using the PCA algorithm), Classification (Using the
Backpropagation Neural Network algorithm) and output.