Multiple data-dependent kernel for classification of hyperspectral images

Kernel-based learning strategies have recently emerged as powerful tools for hyperspectral classification. However, designing optimal kernels is still a challenging issue that needs to be further investigated. In this paper, we propose a multiple data-dependent kernel (MDK) for classification of HSI. Core ideas of the MDK are twofold: (1) optimizing the combination of multiple basic kernels in merit of centered kernel alignment (CKA), which can evaluate the degree of agreement between a kernel and a learning task; (2) optimizing the coefficients of data-dependent kernel (DK) by virtue of Fisher's discriminant analysis (FDA), which can measure the between-class and within-class separability of the data simultaneously. Furthermore, we apply the proposed MDK to two state-of-the-art classifiers, i.e. support vector machine (SVM) and sparse representation classifier (SRC). Experimental results conducted on three benchmark HSIs with different spectral and spatial resolutions validate the feasibility of the proposed methods.