Indexing and retrieval in large satellite image databases

We are presenting a global scheme devoted to the management of very large databases of remote sensing images, with a specific attention to high resolution images. We show at first the specificities of indexing satellite images. Then we present the different stages of a global system, mostly based on textural feature detection and SVM classification, for indexing and retrieving parts of satellite images with given properties. We show the role of the semantic information extraction and we propose and experiment three different manners to introduce such a semantic information in the query system and to adapt the data to the user's demand.