APPLICATION OF SOFTMAX REGRESSION AND ITS VALIDATION FOR SPECTRAL-BASED LAND COVER MAPPING

Abstract

The presented Softmax Regression classifier is a generalization of logistic regression. It is used for multi-class classification, where classes are mutually exclusive. Implemented in a classification framework, it provides a flexible approach to customize a classification process. Traditional classification is focused with classifiers that can only be applied on the same dataset. The Softmax Regression classifier can be created and trained on a reference dataset using spectral and spatial information and then applied to similar data multiple times. We present the general workflow of Softmax Regression classification as part of a case study that is based on attribute images derived from hyperspectral airborne and elevation imagery.