Hierarchical orthogonal matching pursuit for face recognition

This paper tries to exploit the joint group intrinsics in face recognition problem by using sparse representation with multiple features. We claim that different feature vectors of one test face image share the same sparsity pattern at the higher group level, but not necessarily at the lower (inside the group) level. This means that they share the same active groups, but not necessarily the same active set. To this end, a hierarchical orthogonal matching pursuit algorithm is developed. The basic idea of this approach is straightforward: At each iteration step, we first select the best group which is shared by different features, then we select the best atoms (within this group) for each feature. This algorithm is very efficient and shows good performance in standard face recognition dataset.