In this paper, we systematically study the effect of poorly registered faces on the training and inferring stages of traditional face recognition algorithms. We then propose a novel multiple-instance based subspace learning scheme for face recognition. In this approach, we iteratively update the subspace training instances according to diverse densities, using class-balanced supervised clustering. We test our multiple instance subspace learning algorithm with Fisherface for the application of face recognition. Experimental results show that the proposed learning algorithm can improve the robustness of current methods with poorly aligned training and testing data.
展开▼
