Distributed Face Recognition via Consensus on SE(3)
Résumé
We consider the problem of distributed face recognition in a calibrated camera sensor network. We assume that each camera is given a small and possibly different training set of face images taken under varying viewpoint, expression, and illumination conditions. Each camera can estimate the pose and identity of a new face using classical techniques such as Eigenfaces or Tensorfaces combined with a simple classifier. However, the pose estimates obtained by a single camera could be very poor, due to limited computational resources, impoverished training sets, etc., which could lead to poor recognition results. Our key contribution is to propose a distributed face recognition algorithm in which neighboring cameras share their individual estimates of the pose in order to achieve a “consensus” on the face pose. For this purpose, we use a provably convergent distributed consensus algorithm on SE(3) that estimates the global Karcher mean of the face pose in a distributed fashion. Experiments on the Weizmann database show that our algorithm effectively improves the local pose estimates, and achieves the performance of centralized face recognition algorithms using only local processing.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...