Description

Remote sensing image retrieval (RSIR), which aims to efficiently retrieve the images from large collections of remote sensing images, is a fundamental task in remote sensing. Traditional RSIR methods rely on handcrafted low-level visual features to represent the content of remote sensing images. Hence in this process, we proposed a algorithm to retrieve the SAR images based on two major steps like, feature extraction and classification. The stability of the features is well performed to improve the retrieval rate. Then the performance of the retrieval is evaluated by means of the accuracy and error rate.