Learning prototypes and distances (LPD). A prototype reduction technique based on nearest neighbor error minimization

A prototype reduction algorithm is proposed which simultaneous train both a reduced set of prototypes and a suitable local metric for these prototypes. Starting with an initial selection of a small number of prototypes, it iteratively adjusts both the position (features) of these prototypes and the corresponding local-metric weights. The resulting prototypes/metric combination minimizes a suitable estimation of the classification error probability. Good performance of this algorithm is assessed through experiments with a number of benchmark data sets and through a real two-class classification task which consists of detecting human faces in unrestricted-background pictures.