Facial Expression Recognition by Multiple Feature Extraction under Highly Corrupted Noisy Environment

Main Article Content

Renu Nagpal
Sumeet Kaur, Pooja Nagpal

Abstract

A person’s face is considered as the mirror of the mind. It is an important biometric feature for personal identification.
Facial expressions and the changes in facial expressions provide important information about effective state of the person, his
temperament and personality, psychopathological diagnostic information, related to stress levels, truthfulness etc. Body language
and facial expressions are the best ways to know the personality of a person and the response of a person in various situations. The
facial expressions tell us about concealed emotions which can be used to verify if the information provided verbally is true. Facial
recognition and expression analysis is rapidly becoming an area of interest in computer science and in the design communities of
human computer interaction. It plays an essential role in communications and in social interactions with other human beings
which deliver rich information about their emotions. Facial expression plays an important role in interpersonal relations.
Automatic recognition of facial expressions can be an important component of natural human-machine interface. Human being
possesses an ability of communication through facial emotions in day to day interaction with others. Recognizing human facial
expression and emotion by computer is an interesting and challenging problem. It provides a key mechanism for understanding
and conveying emotions. This study aims at developing intelligent computers or robots that are mind implemented. This document
demonstrates how multiple features are extracted and emotions are detected from noisy images. Facial expression is the best
channel for emotion recognition and making machine intelligent. An automatic system for the recognition of facial expressions is
based on a representation of the expression, learned from a training set of pre-selected meaningful features. However, in reality
the noises that may embed into an image document will affect the performance of face recognition algorithms. As a first we
investigate the emotionally intelligent computers which can perceive human emotions. In this research paper five emotions
namely angry, fear, happy, sad along with neutral is tested from database in noisy environment of salt and peeper noise. Very high
recognition rate has been achieved for all emotions along with neutral on the training dataset as well as user defined dataset. The
proposed method uses Neural Networks by which emotions are classified.

 

Keywords: biometrics; facial expression; neural network; histogram equalization; multiple features

Downloads

Download data is not yet available.

Article Details

Section
Articles