Hyperspectral Image Classification with Rotation Random Forest Via KPCA

Junshi Xia*, Nicola Falco, Jon Atli Benediktsson, Peijun Du, Jocelyn Chanussot

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

56 Citations (Scopus)


Random Forest (RF) is a widely used classifier to show a good performance of hyperspectral data classification. However, such performance could be improved by increasing the diversity that characterizes the ensemble architecture. In this paper, we propose a novel ensemble approach, namely rotation random forest via kernel principal component analysis (RoRF-KPCA). In particular, the original feature space is first randomly split into several subsets, and KPCA is performed on each subset to extract high order statistics. The obtained feature sets are merged and used as input to an RF classifier. Finally, the results achieved at each step are fused by a majority vote. Experimental analysis is conducted using real hyperspectral remote sensing images to evaluate the performance of the proposed method in comparison with RF, rotation forest, support vector machines, and RoRF-PCA. The obtained results demonstrate the effectiveness of the proposed method.

Original languageEnglish
Article number7805181
Pages (from-to)1601-1609
Number of pages9
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Issue number4
Publication statusPublished - Apr 2017

Bibliographical note

Publisher Copyright:
© 2008-2012 IEEE.

Other keywords

  • Classification
  • hyperspectral image
  • kernel principal component analysis (KPCA)
  • rotation random forest (RoRF)


Dive into the research topics of 'Hyperspectral Image Classification with Rotation Random Forest Via KPCA'. Together they form a unique fingerprint.

Cite this