We propose a semi-supervised method of land cover classification for remotely sensed multi spectral data. The method is usefule specially when the number of training data is small and restricted. The method derives the additional training data out of ...
We propose a semi-supervised method of land cover classification for remotely sensed multi spectral data. The method is usefule specially when the number of training data is small and restricted. The method derives the additional training data out of the object image by using the results of two different types of classifiers. We extract the pixels in which the results of two classifiers were coincide with each other and use the mas the additional training data in the classifiction. By the results of experiments, in which we used maximum like lihood method and A da Boost for the two classifiers, we confirmed that the algorithm is effective to improved the accuracy of classification.