Person recognition using facial video information: A state of the art

摘要: In this article we propose a detailed state of the art on person recognition using facial video information. We classify existing approaches present in scientific literature between those that neglect temporal information, and exploit it even partially. Concerning first category, detail extensions to data of: eigenfaces, fisherfaces, active appearance models (AAMs), radial basis function neural networks (RBFNNs), elastic graph matching (EGM), hierarchical discriminative regression trees (HDRTs) pairwise clustering methods. After that, focus strategies exploiting particular analysing: motion with optical flow, evolution over time hidden Markov (HMMs) or various probabilistic tracking approaches, head Gaussian mixture models.