Grassmann Discriminant Analysis for Face Recoginition Based on Image Set

Several studies explored the application of Discriminant analysis on Grassmann manifolds to tackle the image sets matching. But these methods suffer from not considering the local structure of the data. In this paper, a new method of face recognition which based on a graph embedding framework and geometric distance perturbation has been proposed. By introducing similarity graphs and maximal linear patch, the geometrical structure between images and image sets can be exploited. Experiments on several face image datasets demonstrate the effective of this method.