Image Euclidean distance-based manifold dimensionality reduction algorithm for hyperspectral imagery

Abstract

Two nonlinear dimensionality reduction methods were proposed based on image Euclidean distance. Considering the physical characters of hyperspectral imagery,the methods introduced image Euclidean distance into traditional manifold dimensionality reduction. Compared w ith other methods,our methods have several advantages. The introduction of image Euclidean distance not only considers hyperspectral image's spatial relationship,but also preserves the local feature of datasets w ell. Thus the proposed methods can discard efficiently the redundant information from both the spectral and spatial dimensions. The experiment results demonstrated that the proposed methods have higher classification accuracy than other methods w hen applied to hyperspectral image classification.