Skip to main navigation Skip to search Skip to main content

Dimension reduction for hyperspectral image based on the second generation bandelet transform

  • Xiaoping Du*
  • , Hang Chen
  • , Zhengjun Liu
  • , Ming Liu
  • , Xiangzhen Cheng
  • *Corresponding author for this work

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

Abstract

A dimensionality reduction method is proposed by using the second generation Bandelet transform. The redundant components of the hyperspectral cube are firstly partitioned into several subsets. Subsequently the Bandelet coefficients and the geometries flows of the hyperspectral image are generated by performing second generation Bandelet transform. In the follow step, Principal Components Analysis (PCA) is introduced to simplify the redundant data. Finally, the new reduced hyperspectral cube is reconstructed by taking inverse Bandelet transform. Some numerical simulations are made to test the validity and capability of the proposed dimensionality reduction algorithm.

Original languageEnglish
Title of host publicationInternational Symposium on Photoelectronic Detection and Imaging 2013
Subtitle of host publicationImaging Spectrometer Technologies and Applications
PublisherSPIE
ISBN (Print)9780819497796
DOIs
StatePublished - 2013
Event5th International Symposium on Photoelectronic Detection and Imaging, ISPDI 2013 - Beijing, China
Duration: 25 Jun 201327 Jun 2013

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8910
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference5th International Symposium on Photoelectronic Detection and Imaging, ISPDI 2013
Country/TerritoryChina
CityBeijing
Period25/06/1327/06/13

Keywords

  • Bandelet transform
  • Dimensionality reduction
  • Hyperspectral
  • Mutipscale

Fingerprint

Dive into the research topics of 'Dimension reduction for hyperspectral image based on the second generation bandelet transform'. Together they form a unique fingerprint.

Cite this