Semi-supervised Spatial Spectral Local Discriminant Analysis for Hyperspectral Image Feature Extraction

Making full use of the spatial spectral features contained in hyperspectral images, a hyperspectral image feature extraction algorithm (S
4
LFDA) for semi-supervised spatial spectral local discriminant analysis is proposed, in view of the spatial consistency of hyperspectral datasets, the pixels are first spatially reconstructed to preserve the neighbour relationship of hyperspectral data, and then the spectral information divergence is introduced to reconstruct the similarity between cells, and in order to make full use of a large number of unlabeled samples to improve the performance of the algorithm, the fuzzy C-means clustering algorithm is used to cluster the samples to obtain pseudo-labels. Then, the normalization term is added to the intra-class divergence matrix and interclass divergence matrix of the local FDA algorithm to maintain the consistency of the cluster structure of the unlabeled samples, and finally the local FDA algorithm is used to maximize the interclass divergence and minimize the intra-class divergence of the labeled samples and solve the best projection vector. The S
4
LFDA algorithm not only maintains the divisibility of the data set in the spectral domain, but also maintains the neighbour relationship of the pixels in the spatial region, rationally uses labeled samples and unlabeled samples, and improves the classification performance of the algorithm. Experiments were carried out in Pavia University and Indian Pines, and the overall classification accuracy reached 95.60 and 94.38, which effectively improved the performance of feature classification compared with other dimensional reduction algorithms.