Design and Implementation of Content-based Remote Sensing Image Retrieval System

摘要

Remote sensing images are important geo-spatial data resource and contain a wealth of information. This paper studies the content-based remote sensing images retrieval technology based on spectral, texture and shape features. The system adopts the inertia ratio and mean based on the spectral histogram to extract the spectral feature, takes the Gray-Level CoOccurrence Matrix (GLCM) algorithm to extract the texture feature, and uses the torque characteristics based on contour shape to extract the shape feature. The Euclidean distance method is taken for similarity measuring. The related experiments proved the effectiveness of each method.