Composite Kernel Classification using Spectral-Spatial Features and Abundance Information of Hyperspectral Image

This paper presents a composite kernel classification approach by exploiting both the spectral-spatial information and abundance information of hyperspectral image. The classifier adopted in this work is the multinomial logistic regression, and the spatial information is modeled from extended multi-attribute profiles(EMAPs). The class-based endmember extraction and sparse unmixing method was used to obtain the abundance information. The state-of-the art performance of the proposed approach is illustrated with real hyperspectral data sets collected by the NASA Jet Propulsion Laboratory's Airborne Visible Infrared Imaging Spectrometer (AVIRIS) over the Indian Pines region, Indiana.