Search

Abstract: In this paper, we propose an effective supervised dimensionality reduction technique, namely discriminant sparsity neighborhood preserving embedding (DSNPE), for face recognition. DSNPE constructs graph and corresponding edge weights simultaneously through sparse representation (SR). DSNPE explicitly takes into account the within-neighboring information and between-neighboring information. Further, by taking the advantage of the maximum margin criterion (MMC), the discriminating power of DSNPE is further boosted. Experiments on the ORL, Yale, AR and FERET face databases show the effectiveness of the proposed DSNPE. [Copyright &y& Elsevier]

Abstract: The complete linear discriminant analysis (CLDA) algorithm has been successfully employed for face recognition. The CLDA method can make full use of the discriminant information of the training samples. However, CLDA suffers from the scalability problem. In this paper, we propose an incremental CLDA (ICLDA) to overcome this limitation. We first propose a new implementation of CLDA in which two steps of QR decomposition, rather than singular value decomposition (SVD), are used to get the orthonormal bases of the range and null spaces of the within-class scatter matrix. Then, by using efficient QR-updating technique, we propose the ICLDA method which can accurately incrementally update the discriminant vectors of CLDA instead of recomputing the CLDA again. Experiments on PIE and FERET face databases show the efficiency of our proposed CLDA algorithms over the original implementation of CLDA. [Copyright &y& Elsevier]