Supervised Linear Manifold Learning Feature Extraction for Hyperspectral Image Classification

摘要

A supervised neighborhood preserving embedding (SNPE) linear manifold learning feature extraction method for hyperspectral image classification is presented in this paper.A point's k nearest neighbours are found by using new distance which is proposed according to prior class-label information.The new distance makes intra-class more tightly and interclass more seperately.SNPE overcomes the single manifold assumption of NPE.Data sets laid on (or near) multiple manifolds can be processed.Experiments on AVIRIS hyperspectral data sets demonstrate the effectiveness of our method.