BEMD and wavelet denoising based classification for hyperspectral image

Author

He, Zhi ; Jin, Jing ; Zhang, Miao ; Shen, Yi ; Wang, Yan

Author_Institution

Sch. of Astronaut., Harbin Inst. of Technol., Harbin, China

fYear

2011

fDate

10-12 May 2011

Firstpage

1

Lastpage

6

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.

Keywords

image classification; image denoising; support vector machines; BEMD; bi-dimensional empirical mode decomposition; bi-dimensional intrinsic mode function; feature selection technique; hyperspectral image classification; support vector machine; wavelet denoising; Accuracy; Hyperspectral imaging; Noise reduction; Support vector machines; Training; Wavelet transforms; bi-dimensional empirical mode decomposition (BEMD); classification; feature selection; support vector machine (SVM); wavelet denoising;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference (I2MTC), 2011 IEEE

Conference_Location

Binjiang

ISSN

1091-5281

Print_ISBN

978-1-4244-7933-7

Type

conf

DOI

10.1109/IMTC.2011.5944098

Filename

5944098