Video-based face recognition using manifold learning by neural networks

This paper proposes a method using manifold learning by neural networks for identifying people while they are talking. In training phase people say the same sentence, we train the NN for learning low-dimensional nonlinear manifolds that are embedded in high-dimensional video space. After training phase we use another video of the same persons while they are saying another sentence for testing. Comparing the recognition results with other methods shows that our method outperforms other methods. Finally we achieve 98.4% of recognition rate.