Face Recognition by Combining Neural Network based on Mixture of Experts

This paper proposed a new method for face recognition with principal component analysis in the feature extraction phase, and devised a modified version of Mixture of Experts in which each expert is an MLP, instead of linear networks in order to improve the performance of the expert networks, and consequently the whole network performance; Therewith, we use a Momentum term in training the MLP experts, which speeds up the adjustment of weight greatly. We explore three different Mixture of Experts constructing a neural network. Our proposed model, achieved a correct recognition rate on Yale and ORL datasets. Comparisons with other algorithms demonstrate that our method performs better in terms of higher recognition rate, with smaller number of epochs in human face recognition.