Random Forests for land cover classification
Pattern Recognition Letters - Special issue: Pattern recognition in remote sensing (PRRS 2004)
WSEAS Transactions on Computers
WSEAS Transactions on Computers
Hi-index | 0.00 |
Image texture analysis has received a considerable amount of attention over the last few years as it has played an important role in the classification of the remote sensing images. This paper provides an overview of several different approaches to image texture analysis and demonstrates their use on the problem of land cover classification. We used grey level co-occurrence matrix (GLCM) method to assistant the land cover classification and then compared and evaluated all of the result of classifications. In the experimentation, by comparing the classification result of contrast, energy and entropy we find out that the preferable texture features of grey level co-occurrence matrices method was contrast. In this thesis, it used the feature images helping the classification of remote sensing and obtained good result. And it also used C++ programming language to write a programme to compute the number of the feature of texture.