Discriminative low-rank preserving projection for dimensionality reduction

As an effective image clustering tool, low-rank representation (LRR) can capture the intrinsic representation of the observed samples. However, firstly, the good representation does not mean good classification performance. Secondly, no projection matrix is obtained in the training stage, and it cannot deal with the new samples. By incorporating the discriminant analysis and the local neighborhood relationship of the original samples into the low-rank representation, a novel discriminative low-rank preserving projection (DLRPP) algorithm is presented for dimensionality reduction. In DLRPP, the global structure information can be captured by LRR, and the local geometricinformation is simultaneously preserved by the manifold regularization term. The constrained term is induced by the adaptive graph, which is obtained by low-rank representation coefficients. In addition, by introducing discriminant analysis constraint term, DLRPP can learn an optimal projection matrix for data dimensionality reduction. The numerous experiments on six public image datasets prove that the proposed DLRPP can obtain better recognition accuracy compared with the state-of-the-art feature extraction methods.