Multiple kernel fuzzy discriminant analysis for hyperspectral imaging classification

The classical fuzzy discriminant analysis with kernel methods (KFDA) is an effective method of solving nonlinearity pattern analysis problem. In some complicated cases, the kernel machine constituted by a single kernel function is not able to meet some practical application requirements, such as heterogeneous information or unnormalised data, non-flat distribution of samples, etc. By searching for an appropriate linear combination of base kernel functions or matrices, multiple kernel learning (MKL) is able to improve the performance in some extent. So it is a necessary choice to introduce multiple kernel learning into KFDA in order to get better results. In this study, multiple kernel fuzzy discriminant analysis (MKFDA) is proposed. Our method obtains the projection matrix from fuzzy discriminant analysis with multiple kernel, and then feature extraction and classification are made based on the projection matrix. The experiment on the AVIRIS image was performed, and the results showed that the performance of fuzzy discriminant analysis with multiple kernels is better than that of fuzzy discriminant with single kernel for the Hyperspectral images' feature extraction and classification.