Global-Based Eigenspaces with Mixture of Experts for View-Independent Face Recognition using Different Representations

Abstract

In this paper a model for view-independent face recognition, based on Mixture of Experts, ME is introduced. In conventional ME the problem space is divided into several subspaces for the experts, and the expertsoutputs are combined by a gating network. Basically, the way that the face space is partitioned by ME is important. In our model, experts of ME structure are not biased in any way to prefer one class of faces to another. In the other words the gating network learns a partition of input face space and selects one expert in each of these partitions. We call this method “self-directed partitioning”. In our model, different data preparation algorithm is used, LDA and PCA. The better performance of the LDA method in frontal view for face recognition due to PCA was revealed. Using this advantage of LDA and using both the LDA and the PCA in data preparation, section achieved more overall performance in face recognition due to conventional ME.