A Multi-Resolution Content-Based Retrieval Approach for Geographic Images

Current retrieval methods in geographic image databases use only pixel-by-pixel spectral information. Texture is an important property of geographical images that can improve retrieval eeectiveness and eeciency. In this paper, we present a content-based retrieval approach that utilizes the texture features of geographical images. Various texture features are extracted using wavelet transforms. Based on the texture features, we design a hierarchical approach to cluster geographical images for eeective and eecient retrieval, measuring distances between feature vectors in the feature space. Using wavelet-based multi-resolution decomposition, two diierent sets of texture features are formulated for clustering. For each feature set, diierent distance measurement techniques are designed and experimented for clustering images in a database. The experimental results demonstrate that the retrieval eeciency and eeectiveness improve when our clustering approach is used.