Feature extraction of hyperspectral images with image fusion and recursive filtering

Xudong Kang, Shutao Li, Jon Atli Benediktsson

Research output: Contribution to journalArticlepeer-review

201 Citations (Scopus)

Abstract

Feature extraction is known to be an effective way in both reducing computational complexity and increasing accuracy of hyperspectral image classification. In this paper, a simple yet quite powerful feature extraction method based on image fusion and recursive filtering (IFRF) is proposed. First, the hyperspectral image is partitioned into multiple subsets of adjacent hyperspectral bands. Then, the bands in each subset are fused together by averaging, which is one of the simplest image fusion methods. Finally, the fused bands are processed with transform domain recursive filtering to get the resulting features for classification. Experiments are performed on different hyperspectral images, with the support vector machines (SVMs) serving as the classifier. By using the proposed method, the accuracy of the SVM classifier can be improved significantly. Furthermore, compared with other hyperspectral classification methods, the proposed IFRF method shows outstanding performance in terms of classification accuracy and computational efficiency.

Original languageEnglish
Article number6600779
Pages (from-to)3742-3752
Number of pages11
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume52
Issue number6
DOIs
Publication statusPublished - Jun 2014

Other keywords

  • Feature extraction
  • hyperspectral image
  • image classification
  • image fusion (IF)
  • recursive filtering

Fingerprint

Dive into the research topics of 'Feature extraction of hyperspectral images with image fusion and recursive filtering'. Together they form a unique fingerprint.

Cite this