Land Covers Classification for Remote Sensing Images Based on Spectral and Textural Information

Abstract

In this paper, the classifiers for land/water and natural land/artificial land combined the texture measures with spectral analysis for remote sensing images have been built. The specific recognition has been designed in order to take advantages of both analyses. Moreover, coastal line development analysis, the length or ratio of natural/artificial seacoast, could be calculated automatically. The use of red/infrared spectral analysis refines the boundary of classes; meanwhile the merging of co-occurrence matrix texture analysis and spectral information has improved the accuracy of the three-class labeling.