Retrieval of remote sensing image based on combining spatial relation with texture feature

With increasing huge amount of remote sensing data collected from various airborne and satellite sensors, how to find the interested image has been one of the key problems in the management of multi-source remote sensing image database. In this paper, a new retrieval approach based on combining spatial relation with two different texture features is applied in the similarity retrieval of multi-source remote sensing image database which consists of different resolution, different waveband, different platform, and different temporal remote sensing images. The similarity retrieval contains six consecutive stages: preprocessing the images, feature extraction, intra-feature normalization, similarity measure, inter-feature normalization, and experimental evaluation. It was indicated by experimental results that the proposed method has powerful practical merits than the traditional methods such as gray level co-occurrence matrix method and the tree-structured wavelet transform or wavelet packets method. © 2008 by Binary Information Press.