Multiple classifier combination for land cover classification of remote sensing image

Land cover classification is a common application of remote sensing images. In order to improve the performance of land cover classification, multiple classifier combinations are used to classify CBERS CCD images. Some techniques and classifier combination algorithms are investigated. The classifier ensemble consist of six member classifiers: maximum likelihood classifier (ML), support vector machine (SVM), artificial neural networks (ANN), spectral angle mapper (SAM), minimum distance classifier (MD) and decision tree classifier (DTC) is constructed, and the results of every member classifier are evaluated. The Voting strategy is experimented to combine the member classifier. We finished this in Parallel MATLAB. The results show that multiple classifier combination can improve the performance of image classification.