BEMD and wavelet denoising based classification for hyperspectral image

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 (BIMF...

Full description

Saved in:
Bibliographic Details
Published in2011 IEEE International Instrumentation and Measurement Technology Conference pp. 1 - 6
Main Authors Zhi He, Jing Jin, Miao Zhang, Yi Shen, Yan Wang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2011
Subjects
Accuracy
bi-dimensional empirical mode decomposition (BEMD)
classification
feature selection
Hyperspectral imaging
Noise reduction
support vector machine (SVM)
Support vector machines
Training
wavelet denoising
Wavelet transforms
Online AccessGet full text
ISBN1424479339
9781424479337
ISSN1091-5281
DOI10.1109/IMTC.2011.5944098

Cover

More Information
Summary: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.
ISBN:1424479339
9781424479337
ISSN:1091-5281
DOI:10.1109/IMTC.2011.5944098