Comparison between two prototype representation schemes for a nearest neighbor classifier

The paper is about the problem of finding good prototypes for a condensed nearest neighbor classifier in a recognition system. A comparison study is done between two prototype representation schemes. The prototype search is done by a genetic algorithm which is able to generate novel prototypes (i.e. prototypes which are not among the training samples). It is shown that the generalized representation scheme is more powerful, giving significantly larger normalized interclass distances. It is also shown that both representation schemes with genetic algorithm give significantly better prototypes than a direct prototype selection algorithm, which can select only among the training samples.