A three-layer system for image retrieval

Visual patterns are composed of basic features forming well-defined structures and/or statistical distributions. Often, they always present simultaneously in visual images. This makes the problem of description and representation of visual patterns complicated. In this paper we proposed a hierarchical retrieval system, which is based on subimages and combinations of feature histograms, to efficiently combine structure and statistical information for retrieval tasks. We illustrate the results on face database retrieval problem. It is shown that proper selection of subimage and feature vectors can significantly improve the performance with minimized complexity.