Improving Hyperspectral Image Classification by Fusing Spectra and Absorption Features

Many features can be extracted to classify hyperspectral imagery. Classification relying on a single feature set may lose some useful information due to the intrinsic limitation of each feature extraction model. To improve classification accuracy, we propose an information fusion approach, in which both the global and the local aspects of hyperspectral data are taken into account and are combined by a decision-level fusion method. The global features are hyperspectral reflectance curves representing the holistic response to the incident light, and the local features are absorption characteristics reflected by materials' individual constituents. The decision-level fusion is carried out by analyzing the entropy of the classification output from the global feature set and modifying this output via the results of a multilabel classification using the local feature set. Simulations of classification performance on 16 classes of vegetation from the AVIRIS 92AV3C and Salinas data set show the effectiveness of the method, which increases the classification accuracy compared to a popular support vector machine-based method and a production-rule-based decision fusion method.