Skip to main navigation Skip to search Skip to main content

BEMD and wavelet denoising based classification for hyperspectral image

  • School of Astronautics, Harbin Institute of Technology

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

Abstract

A high-accuracy algorithm based on combination of bi-dimensional empirical mode decomposition (BEMD) and wavelet denoising is presented in this paper, in which BEMD is adapted to decompose optimal bands selected from feature selection technique into many bi-dimensional intrinsic mode functions (BIMFs) and sym4 wavelet is chosen to denoise these BIMFs, so that the denoised BIMFs could be taken as input of support vector machine (SVM). Experimental results indicate that the proposed approach not only has promising accuracy but also significantly reduces complexity and computational time of SVM.

Original languageEnglish
Title of host publication2011 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2011 - Proceedings
Pages311-316
Number of pages6
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2011 - Binjiang, Hangzhou, China
Duration: 10 May 201112 May 2011

Publication series

NameConference Record - IEEE Instrumentation and Measurement Technology Conference
ISSN (Print)1091-5281

Conference

Conference2011 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2011
Country/TerritoryChina
CityBinjiang, Hangzhou
Period10/05/1112/05/11

Keywords

  • bi-dimensional empirical mode decomposition (BEMD)
  • classification
  • feature selection
  • support vector machine (SVM)
  • wavelet denoising

Fingerprint

Dive into the research topics of 'BEMD and wavelet denoising based classification for hyperspectral image'. Together they form a unique fingerprint.

Cite this