Automatic Object-Based Hyperspectral Image Classification Using Complex Diffusions and a New Distance Metric

Abstract

This paper proposes an approach for the development of automatic object-based techniques used for hyperspectral image classification. The proposed approach employs an adaptive smoothing step that utilizes an extension of partial differential equations (PDEs) from real domain (RPDE) to complex domain (CPDE). This idea results in generalized PDEs that simultaneously have the properties of both forward and backward diffusions. The genetic algorithm and an innovative fitness function are applied for adaptively tuning the CPDE parameters. The smoothed data are then fed into a Pixon-based object extraction process, which is itself an adaptive process. We also propose a novel distance metric for the Pixon creation step in order to facilitate the use of textural information which exists in the data. The spectral features of the extracted objects are used for a support vector machine classifier.