Skip to main navigation Skip to search Skip to main content

A soft classification algorithm based on spectral-spatial kernels in hyperspectral images

  • Yanfeng Gu*
  • , Ying Liu
  • , Ye Zhang
  • *Corresponding author for this work
  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper, a soft classification algorithm based on composite kernels, which incorporate both spectral and spatial information, is proposed for hyperspectral image. Compared with hard classification, soft classification provides more information about the probabilities one pixel belongs to each class. To calculate these probabilities, the proposed algorithm uses Support Vector Machine (SVM), and it successfully converts SVM output values into probabilities, while at the same time integrates spatial and spectral information by composite kernels. To validate the proposed algorithm, experiments are conducted on hyperspectral images with 126 and 186 bands, and experimental results show that soft classification using SVM can yield better results compared with Maximum Likelihood Classifier (MLC),and the introduction of spectral-spatial kernels can greatly improve classification accuracies.

Original languageEnglish
Title of host publicationSecond International Conference on Innovative Computing, Information and Control, ICICIC 2007
PublisherIEEE Computer Society
ISBN (Print)0769528821, 9780769528823
DOIs
StatePublished - 2007
Event2nd International Conference on Innovative Computing, Information and Control, ICICIC 2007 - Kumamoto, Japan
Duration: 5 Sep 20077 Sep 2007

Publication series

NameSecond International Conference on Innovative Computing, Information and Control, ICICIC 2007

Conference

Conference2nd International Conference on Innovative Computing, Information and Control, ICICIC 2007
Country/TerritoryJapan
CityKumamoto
Period5/09/077/09/07

Fingerprint

Dive into the research topics of 'A soft classification algorithm based on spectral-spatial kernels in hyperspectral images'. Together they form a unique fingerprint.

Cite this