Facial Identity and Expression Recognition by using Active Appearance Model with Efficient Second Order Minimization and Neural Networks

This paper proposes a technique for real-time recognition of facial Identity and expression which uses the active appearance model (AAM) with efficient second order minimization algorithm and neural network, especially the multilayer perceptron. The efficient second order minimization allows AAM to have the ability of correct convergence with a little loss of frame rate. And the correctly extracted facial shape with AAM prevents the recognition of facial identity and expression from undergoing a large error. In addition, high dimensional feature vectors of facial identity and expression, which consist of facial shape and texture, can be dealt by the multilayer perceptron with a very high recognition rate of over 98%.