A color indexing scheme using two-Level clustering processing for effective and efficient image retrieval
Ji Zhang, Wei Wang, Sheng Zhang · University of Southern Queensland ePrints (University of Southern Queensland) · 2005
[Abstract]: In this paper, we present a clustering-based color indexing scheme for effective amd efficient image retrieval, which is essentially an exploration on the application of clustering technique to image retrieval. In our approach, the color features are clustered automatically using a color clustering algorithm twice (called two-level clustering processing) and two color feature summarizations are obtained, e.g. Local Color Centriods (LCCs) and Global Color Centroids (GCCs). Based upon LCCs and GCCs, a three-level R-tree is bulit for indexing database images and performing effecitve and efficient image retrieval. The experiments show that this indexing scheme is effective and efficient in performing image retrieval.