Satellite cloud image processing and information retrieval system

Abstract

With the development of remote sensing imaging technology, the satellite information includes more abundant data, and the quality of satellite cloud image had achieved great progress. The satellite cloud images contain the valuable information for weather forecasting and early prediction of different atmospheric disturbances such as typhoons, hurricanes etc. The processing of content-based satellite cloud image has become one of the most important tasks for using the satellite cloud image information for continuous research. Content-based satellite cloud image processing and information retrieval is a very important problem in image processing and analysis field. In this research, a Content-Based Image Retrieval (CBIR) system has been developed using color, texture and shape as retrieval features from the satellite image repository. To extract the grey level/color properties of an image, histogram values have been used. Four functions of texture features have used such as (Entropy, Energy, correlation and contrast) and the shape features (area, perimeter and metric) have been extracted using the morphological operations. The images and the extracted feature vectors were stored in the database. Results obtained from the processing demonstrate the usability of proposed system.