Abstract

Fast nearest neighbor ( ) finding has been extensively studied. While some fast algorithms using metrics rely on the essential properties of metric spaces, the others using non-metric measures fail for large-size templates. However, in some applications with very large size templates, the best performance is achieved by methods based on the dissimilarity measures resulting in a special space where computations cannot be pruned by the algorithms based-on the triangular inequality. For such methods, the existing fast algorithms except condensing algorithms are not applicable. In this paper, a fast hierarchical search algorithm is proposed to find �- s using a non-metric measure in a binary feature space. Experiments with handwritten digit recognition show that the new algorithm reduces on average dissimilarity computations by more than � while losing the accuracy by less than � , with a increase in memory. 1

Citations