FACE EXPRESSION RECOGNITION USING AUTOREGRESSIVE MODELS TO TRAIN NEURAL NETWORK CLASSIFIERS

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 modela€ s representation (Burg and Levinson).