Semi-supervised Laplacianfaces from Pairwise Constraints for Face Recognition

Subspace methods have been successfully applied to face recognition tasks. It is well-studied in both unsupervised learning and supervised learning, such as Eigenface and Fisherface. In practice, besides abundant unlabeled examples, domain knowledge in the form of pairwise constraints is commonly available, which specifies whether a pair of instances belong to the same class or different classes. In this study, we propose a face recognition method based on semi-supervised locality preserving learning together with pairwise constraints and unlabeled data, called Semi-supervised Laplacianface (S-Laplacianface). It tries to preserve the local geometric structure of the face manifold as Laplacianface, also requires the subspace to satisfy the pairwise constraints defined by the user. Experimental results on two face databases demonstrate the effectiveness of proposed algorithm.