Semi-supervised discriminant analysis based on UDP regularization

We propose a semi-supervised learning algorithm for discriminant analysis, which uses the geometric structure of both labeled and unlabeled samples and perform a manifold regularization on LDA. The labeled data points provide labeling information and the unlabeled data points provide extra geometric structure information of the data, then we learn a labeling function which is as smooth as possible on the data manifold. Experiments on several face databases show the effectiveness of the algorithm.