Probabilistic class structure regularized sparse representation graph for semi-supervised hyperspectral image classification

作者：

Highlights：

• An effective method is introduced to estimate the probabilistic class structure

• Sparse representation based edge weighting method is employed in the graph based SSL.

• Probabilistic class structure information is incorporated into the Sparse representation model.

• The proposed graph construction method is superior to several traditional methods.

摘要

Highlights•An effective method is introduced to estimate the probabilistic class structure•Sparse representation based edge weighting method is employed in the graph based SSL.•Probabilistic class structure information is incorporated into the Sparse representation model.•The proposed graph construction method is superior to several traditional methods.

论文关键词：Graph,Probabilistic class structure,Sparse representation (SR),Semi-supervised learning (SSL),Hyperspectral image (HSI) classification

论文评审过程：Received 15 March 2016, Revised 10 August 2016, Accepted 19 September 2016, Available online 21 September 2016, Version of Record 1 October 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.09.011