Traditional linear Fukunaga-Koontz Transform (FKT) [1] is a powerful discriminative subspaces building approach. Previous work has successfully extended FKT to be able to deal wit...
We describe an analog-VLSI neural network for face recognition based on subspace methods. The system uses a dimensionality-reduction network whose coefficients can be either progr...
Gonzalo Carvajal, Waldo Valenzuela, Miguel Figuero...
In this paper we construct an associative memory model based on the restricted Coulomb energy (RCE) network. We propose a simple architecture and training algorithm for this RCE-b...
Xiaoyan Mu, Mehmet Artiklar, Paul Watta, Mohamad H...
This paper describes an active-camera real-time system for tracking, shape description, and classi"cation of the human face and mouth expressions using only a PC or equivalen...
Abstract. A new exemplar-based probabilistic approach for face recognition in video sequences is presented. The approach has two stages: First, Exemplars, which are selected repres...