Semi-supervised two-dimensional manifold learning based on pair-wise constraints
Wei Xue, Zhengqun Wang, Feng Li, Zhong-xia Zhou · 2014
Considering the huge calculated amount of eigen-decomposition in one-dimensional Linear local tangent space alignment (LLTSA), this paper proposed a Semi-supervised two-dimensional manifold learning based on pair-wise constraints (2D-PCLTSA). 2D-PCLTSA adopts two-dimensional image matrices as the samples to extract image feature information, and uses pair-wise constraints as supervised information. 2D-PCLTSA preserves the feature information in the sample set while taking advantage of the supervised information effectively. Through the experiments on YALE and ORL, 2D-PCLTSA outperforms based on traditional dimensionality reduction algorithms with maximum average recognition rate by 2.85% and 6.25% respectively. Especially, our algorithm could keep well classification performance with a few constraints.