Manifold Discriminant Projection for face Recognition

A novel manifold-based learning method named Manifold Discriminant Projection (MDP) is proposed. MDP not only preserves the sample's local geometric structure, but also makes full uses of class-label information. Specifically, this method firstly uses the neighborhood relationship and class label information to classify the training sample set. For each training sample, there are two classes which are called neighbor class and non-neighbor class; Then, the inter-class scatter and intra-class scatter are defined for each training sample; Finally, the ratio of total inter-class scatter and total intra-class scatter is maximized to make the nearby samples with the same label are more compact, and nearby classes are better separated. Experiment results on ORL and FERET face databases verify the effectiveness of our proposed algorithm.