Spectral-spatial feature extraction using orthogonal linear discriminant analysis for classification of hyperspectral data

Hyperspectral image classification is among the most frequent topics of research in recent publications. This paper proposes a new supervised linear feature extraction method for classification of hyperspectral images using orthogonal linear discriminant analysis in both spatial and spectral domains. In fact, an orthogonal filter set and a spectral data transformation are designed simultaneously by maximizing the class separability. The important characteristic of the presented approach is that the proposed filter set is supervised and considers the class separability when extracting the features, thus it is more appropriate for feature extraction compared with other filters such as Gabor. In order to compare the proposed method with some existing methods, the extracted spatial-spectral features are fed into a support vector machine classifier. Some experiments on the widely used hyperspectral images, namely Indian Pines, Pavia University, and Salinas data sets, reveal that the proposed approach leads to state-of-the-art performance when compared to other recent approaches.