Evaluation of classifiers for polarimetric SAR classification

Polarimetric SAR data is been extensively used for the application of land use and land cover classification. Various classifier approaches have been applied to many different polarimetric images employing numerous features. In this paper, we want to provide an evaluation of commonly used supervised classifiers within the field of polarimetric SAR classification considering the effects of different number of training samples. Two polarimetric SAR images are considered representing an easier 4 class and more complex 15 class problem using a small set of eigen-decomposition features and tested with Neural Network, SVM, and Decision Tree classifiers. Results show that already rather small training sets can provide comparable results reducing the need for large labeled training data especially considering more challenging classification tasks. This can be further investigated in the area of semi-supervised learning.