articleIEEE Transactions on Geoscience and Remote SensingNov 4, 2016Closed access

Hyperspectral Image Classification Using Deep Pixel-Pair Features

Beijing University of Chemical Technology · Mississippi State University

Indexed incrossref

Abstract

The deep convolutional neural network (CNN) is of great interest recently. It can provide excellent performance in hyperspectral image classification when the number of training samples is sufficiently large. In this paper, a novel pixel-pair method is proposed to significantly increase such a number, ensuring that the advantage of CNN can be actually offered. For a testing pixel, pixel-pairs, constructed by combining the center pixel and each of the surrounding pixels, are classified by the trained CNN, and the final label is then determined by a voting strategy. The proposed method utilizing deep CNN to learn pixel-pair features is expected to have more discriminative power. Experimental results based on…

Citation impact

803
total citations
FWCI
76.63
Percentile
100%
References
32
Citations per year

Authors

4

Topics & keywords

Keywords
  • Pixel
  • Hyperspectral imaging
  • Artificial intelligence
  • Computer science
  • Discriminative model
  • Pattern recognition (psychology)
  • Convolutional neural network
  • Deep learning
UN Sustainable Development Goals
  • Reduced inequalities
No related works found for this paper.

Funding