Locality-preserving sparse representation-based classification in hyperspectral imagery

Authors:
Publisher website
Google Scholar
Abstract
This paper proposes to combine locality-preserving projections (LPP) and sparse representation (SR) for hyperspectral image classification. The LPP is first used to reduce the dimensionality of all the training and testing data by finding the optimal linear approximations to the eigenfunctions of the Laplace Beltrami operator on the manifold, where the high-dimensional data lies. Then, SR codes the projected testing pixels as sparse linear combinations of all the training samples to classify the testing pixels by evaluating which class leads to the minimum approximation error. The integration of LPP and SR represents an innovative contribution to the literature. The proposed approach, called locality-preserving SR-based classification, addresses the imbalance between high dimensionality of hyperspectral data and the limited number of training samples. Experimental results on three real hyperspectral data sets demonstrate that the proposed approach outperforms the original counterpart, i.e., SR-based classification.
Funding Information
  • National Nature Science Foundation of China (41571349)
  • National Natural Science Foundation of China (41571349)
  • National Natural Science Foundation of China (41325004)
  • National Nature Science Foundation of China (41325004)
  • National Natural Science Foundation of China (41325004)
  • Key Research Program of the Chinese Academy of Sciences (KZZD-EW-TZ-18)
  • Chinese Academy of Sciences (KZZD-EW-TZ-18)
  • Chinese Academy of Sciences Key Deployment Project (KZZD-EW-TZ-18)

This publication has 29 references indexed in Scilit: