Face Recognition Base on Uncorrelated Linear Extension of Graph Embedding

An uncorrelated linear extension of graph embedding which provides a unified framework for computing all kinds of uncorrelated linear dimensionality reduction algorithms is proposed. Compared with original linear dimensionality reduction methods, the proposed methods are better in terms of reducing or eliminating the statistically correlation between features and improving recognition rate. The experimental results on ORL and Yale face database show that the proposed uncorrelated linear extension of graph embedding methods are better than original methods in terms of recognition rate. Besides, the relation between uncorrelated linear extension of graph embedding and original linear extension of graph embedding is revealed.