A binary decision tree classifier implementing logistic regression as a feature selection and classification method and its comparison with maximum likelihood

This study deals with two different approaches to the classification of hyperspectral image data using a multiple stage classifier structured as a binary tree. One approach implements the Gaussian maximum likelihood (GML) decision function at each node of the tree and the second makes use of traditional binary logistic regression (LR). The results obtained by classification of AVIRIS images data are compared with single- stage classifiers.