International Journal of Engineering & Technology, 4 (x) (2015) xxx-xxx
www.sciencepubco.com/index.php/IJET
©Science Publishing Corporation
doi:
Research paper
Performance Comparisons of Artificial Neural Network
Algorithms in Facial Expression Recognition
Amira ElsirTayfour
1
*, Altahir Mohammed
2
, Moawia Elfaki Eldow
3
1
PhD Research Scholar, King Khalid University
2
Sudan University of Science & Technology
3
University of Khartoum
*Corresponding author E-mail: amtyfoor@gmail.com
Copyright © 2015 Amira ElsirTayfour et al. This is an open access article distributed under the Creative Commons Attribution License, which permits
unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
This paper presents methods for identifying facial expressions. The objective of this paper is to present a combination of
texture oriented method with dimensional reduction and use for training the Single-Layer Neural Network (SLN), Back
Propagation Algorithm (BPA) and Cerebellar Model Articulation Controller (CMAC) for identifying facial expressions.
The proposed methods are called intelligent methods that can accommodate for the variations in the facial expressions
and hence prove to be better for untrained facial expressions. Conventional methods have limitations that facial
expressions should follow some constraints. To achieve the expression detection accuracy, Gabor wavelet is used in
different angles to extract possible textures of the facial expression. The higher dimensions of the extracted texture
features are further reduced by using Fi sher’s linear discriminant function for increasing the accuracy of the proposed
method. Fisher’s linear discriminant function is used for transforming higher -dimensional feature vector into a two-
dimensional vector for training proposed algorithms. Different facial emotions considered are angry, disgust, happy, sad,
surprise and fear are used. The performance comparisons of the proposed algorithms are presented.
Keywords: Fisher’s Linear Discriminant Function; Wavelet Gabor Filter; Artificial Neural Network.
1. Introduction
Identification of facial expressions has been a main factor used in clinical treatments, security, information finding from
unknown persons and interacting with fellow beings. In many cases, it would be difficult to identify the expression
using the manual method, especially when lots of expressions are available in different images. Hence, an automatic
method is required to be provided that can accommodate the change in expression and accurately identify the
expression.
2. Related work
Standard methods like static and dynamic techniques have been used earlier by researchers in identifying emotions.
Bayesian technique has been used as an important static method. Ravi et al., [5], gave a comparative study and analysis
of ‘Facial Expression Recognition Technology’ along with its progressive growth and developments. Oliveira et al.,[4],
proposed a novel method called two-dimensional discriminant locality preserving projections (2D-DLPP) is proposed
that can best discriminate different pattern classes. Cheng et al, [2], proposed a Gaussian Process model for the facial
expression recognition in the Japanese female facial expression data set and found successful classification of facial
expression.
Klaus and Ursula, [3], report the development of a rapid test of emotion recognition ability, the Emotion Recognition
Index (ERI), consisting of two subtests: one for facial and one for vocal emotion recognition. Ruffman, [6], presents
that recognition of emotion in still photos provides important information about young-old differences and has