An RCE-based associative memory with application to human face recognition

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-based associative memory. We study the capacity of this memory model on the practical problem of human face recognition. In this case, capacity is described by two measures: the ability of the system to correctly identify known individuals, and the ability of the system to reject individuals who are not in the database. Experimental results are given which show how the performance of the system varies as the size of the database increases: up to 1000 individuals.