Face clustering using semi-supervised Neighborhood Preserving Embedding with pairwise constraints
Na Wang, Xia Li · 2009
Following the intuition that the image variation of faces can be effectively modeled by low dimensional linear spaces, we propose a semi-supervised subspace learning method for face clustering using side-information in the form of must-link pairwise constraints which specify whether a pair of data instances belongs to the same class. A subspace called S-NPEface is found by using a Semi-supervised Neighborhood Preserving Embedding algorithm (S-NPE). The subspace attempts not only to preserve the local geometric structure of the face manifold, but also to satisfy the pairwise constraints refined by the user. Experimental results on two standard face databases demonstrate the effectiveness of our proposed algorithm.