Regularized RBF Networks for Hyperspectral Data Classification

In this communication, we analyze several regularized types of Radial Basis Function (RBF) Networks for crop classification using hyperspectral images. We compare the regularized RBF neural network with Support Vector Machines (SVM) using the RBF kernel, and AdaBoost Regularized (ABR) algorithm using RBF bases, in terms of accuracy and robustness. Several scenarios of increasing input space dimensionality (128, 6, 3 and 2 number of bands) are tested for six labeled images containing six crop classes. Also, regularization, sparseness, and knowledge extraction are paid attention. Several conclusions are drawn: (1) all models offer similar accuracy but SVM and ABR yield slightly better results than RBFNN; (2) results indicate that ABR are less affected by the curse of dimensionality and has identified efficiently the presence of noisy bands; (3) we find that regularization is a useful method to work with noisy data distributions; and (4) some physical consequences are extracted from the trained models. Finally, this preliminary work lead us to think of kernel-based machines as efficient and robust methods for hyperspectral data classification.