Hyperspectral Image Classification Using Spectral–Spatial Composite Kernels Discriminant Analysis

Abstract

This paper proposes a framework for hyperspectral images (HSIs) classification with composite kernels discriminant analysis (CKDA). The CKDA uses the spectral and spatial information extracted by Gaussian weighted local mean operator (GWLM) and is suitable to solve few labeled samples classification problem of HSI, which has very important practical significance for the case that training samples are insufficient due to high cost. Experimental results show that the spatial information extracted by GWLM can greatly improve the performance, and demonstrate the superiority of CKDA for HSI classification in the case of few labeled samples. Compared with other state-of-the-art spectralspatial kernel methods, the proposed methods also show very good advantages, especially the parallel kernel method.Index Terms-Composite kernels discriminant analysis (CKDA), Gaussian weighted local mean operator (GWLM), spatial information, spectral information.

Multiscale Weighted Adjacent Superpixel-Based Composite Kernel for Hyperspectral Image Classification

“…For instance, the composite kernel (CK) [31] method (i.e., SVMCK) replaces each target pixel with the mean value of the square neighborhood centered on the target pixel, so as to extract spatial features and thus show good classification performance. On this basis, many multiple kernels learning methods, such as extreme learning machine with CK [32], CK discriminant analysis [33], and subspace multiple kernels learning [34], have also been used to classify HSI, effectively improving the classification accuracy. Unlike CK, the spatial-spectral kernel (SSK) only constructs a kernel function to exploit the spatial and spectral features in feature space.…”

Laplacian Regularized Spatial-Aware Collaborative Graph for Discriminant Analysis of Hyperspectral Imagery

“…Spectral-Spatial information can be used as a preprocessing. For example, Gaussian weighted local mean operator was employed to extract spectral-spatial feature in Composite Kernels Discriminant Analysis (CKDA) [36]. A robust spectral-spatial distance rather than simple spectral distance was adopted in Robust Spatial LLE (RSLLE) [37].…”

A Review on Multiple-Feature-Based Adaptive Sparse Representation (Mfasr) and Other Classification Types

“…This method acts as object recognition. According to this classification method, the various classification techniques such as clonal selection feature extraction [22], semisupervised discriminative locally enhanced alignment [23], Principle Component Analysis (PCA) [24] and kernel discriminative analysis [25]. To enhance the class seperability problems [26], a kernel [27] method has been used in the above mentioned approaches.…”