Abstract

Neural network classifying method is used in this work to perform facial expression recognition. The processed
expressions were the six most pertinent facial expressions and the neutral one. This operation was
implemented in three steps. First, a neural network, trained using Zernike moments, was applied to the set of
the well known Yale and JAFFE database images to perform face detection. In the second step, Auto
Regressive modeling (AR) using 2D- Burg and Levinson filters was used for facial parameterization. At the last step, neural networks, trained on a set of the AR models, were applied to the rest of the images models to test method\'s performances and to compare the efficiency of the model’s representation (Burg and Levinson).

Information

Item Type:	Journal
Divisions:	» Faculty of Science and Technology
ePrint ID:	36
Date Deposited:	2014-10-30
Further Information:	Google Scholar
URI:	https://www.univ-soukahras.dz/en/publication/article/36

BibTex