Searching similar images — Vector quantization with S-tree

Abstract

Searching of similar pictures was in the past based mainly on searching of similar picture names. We try to find an effective method how to search pictures by searching of similar information in the picture (histograms, shapes, blocks,). There already are some methods but still not effective enough. In this paper we describe a method where we combine vector quantization (VQ) and fuzzy S-trees. Work contains testing of our approach and you can see results in a final chapter of this paper. The benefit of this work is not the final solution but we put a key-stone for further research and for optimizations. First tests show up the efficiency and usefulness of our approach, which is under laid by executed tests.