Region-based CBIR in GIS with local space filling curves to spatial representation

Abstract

In this paper we present a region-based retrieval method for satellite images using motif co-occurrence matrix (MCM) in conjunction with spatial relationships. Each image is decomposed into coherent segments; MCM is computed for each region; the spatial relationship among them are evaluated by using a *-tree representation. The image is represented by an attributed relational graph (ARG) where nodes contain the visual feature (MCM); edges represent spatial relationship. Principal component analysis show the usefulness of MCM as a feature.