The Classification Of Remote Sensing Image Based On Spatial Data Mining And Knowledge Discovery

Surveying land use type of area and getting land use information quantificationally by remote sensing technology at the present time are one of the most important fields. The classification of remote sensing image is the first step for using remote sensing data in land resource analysis and application. Therefore, how to distinguish kinds of images and meet the accuracy to a certainty is a pivotal problem in remote sensing image research, provided with very important significance.This article take a case study on the land use classification of the outskirts of Fuzhou study area in Fujian Province. Classification rules are discovered from the samples through C4.5 algorithm, which integrates spectral, textural and the topography characters. The interpretation was performed by a judgment based on these rules. The traditional supervised as well as logic channel classifications are also performed to check the classification accuracies. The results have suggested that the accuracy of classification based on the C4.5 algorithm is higher than others', which can obtain a lot of reasonable rules most quickly and effectively. So, it was felt that it is a good way to promote the wide application of knowledge-based interpretation of remote sensing images.