摘要：This paper describes a new classification method (DER) based on evidential reasoning towhich a series of modifications are added [1]. DER allows including new evidence for theclassification process and defines a different decision rule. The evidential reasoning algorithmprovides a means to combine evidence from different data sources. It is a supervisedclassification technique that uses a training samples set. This novel method (DER) offers alearning stage to introduce new evidence in case the classifier requires so. Moreover, it usesthe plausibility measure in order to define the decision rule as a way to incorporate data-associated uncertainty. The proposed method is applied in order to classify crops inhyperspectral images of the area of Nebraska (USA). Some results obtained are presented inorder to assess DER precision
