Abstract
|
Article Information:
Challenging of Facial Expressions Classification Systems: Survey, Critical Considerations and Direction of Future Work
Amir Jamshidnezhad and M.D. Jan Nordin
Corresponding Author: Amir Jamshidnezhad
Submitted: December 30, 2011
Accepted: January 13, 2012
Published: May 01, 2012 |
Abstract:
|
The main purpose of this study is analysis of the parameters and the affects of those on the
performance of the facial expressions classification systems. In recent years understanding of emotions is a
basic requirement in the development of Human Computer Interaction (HCI) systems. Therefore, an HCI is
highly depended on accurate understanding of facial expression. Classification module is the main part of facial
expressions recognition system. Numerous classification techniques were proposed in the previous researches
to use in the facial expressions recognition systems. In order to evaluate the performance of the classification
system we should consider the parameters which influence the classification results. Therefore, in this article,
the most recent classification techniques for the purpose of facial expressions recognition as well as features
extraction were surveyed and the parameters which affect the accuracy of results were considered and
discussed. Based on this article, the features type, number of extracted features, database and image type are
the main parameters that influence the accuracy rate of classification models. Furthermore, as the direction of
the future work of this research, a Genetic-Fuzzy classification model was proposed for facial expressions
recognition to fulfill the classification requirements.
Key words: Classification, facial expressions recognition, features extraction, fuzzy logic, genetic algorithm, ,
|
Abstract
|
PDF
|
HTML |
|
Cite this Reference:
Amir Jamshidnezhad and M.D. Jan Nordin, . Challenging of Facial Expressions Classification Systems: Survey, Critical Considerations and Direction of Future Work. Research Journal of Applied Sciences, Engineering and Technology, (09): 1155-1165.
|
|
|
|
![](http://www.maxwellsci.com/images/RJASET-maxw.jpg) |
ISSN (Online): 2040-7467
ISSN (Print): 2040-7459 |
![Submit Manuscript](../images/sub.jpg) |
Information |
|
|
|
Sales & Services |
|
|
|