Paper Info
Title
Application And Evaluation Of Wavelet-Based Denoising Method In Hyperspectral Imagery Data
Abstract
The imaging hyper-spectrometer is highly susceptible to the presence of noise and its noise removal is regularly necessary before any derivative analysis. A wavelet-based(WT) method is developed to remove noise of hyperspectral imagery data, and commonly used denoising methods such as Savitzky-Golay method(SG), moving average method(MA), and median filter method(MF) are compared with it. Smoothing index(SI) and comprehensive evaluation indicator(eta) are designed to evaluate the performance of the four denoising methods quantitatively. The study is based on hyperspectral data of wheat leaves, collected by Pushbroom Imaging Spectrometer (PIS) and ASD Fieldspec-FR2500 (ASD) in the key growth periods. According to SI and eta, the denoising performance of the four methods shows that WT>SG=MA>MF and WT>MA>MF>SG, respectively. The comparison results reveal that WT works much better than the others with the SI value 0.28 and eta value 5.74E-05. So the wavelet-based method proposed in this paper is an optimal choice to filter the noise, in terms of balancing the contradiction between the smoothing and feature reservation ability.
Year
DOI
Venue
2011
10.1007/978-3-642-27278-3_47
COMPUTER AND COMPUTING TECHNOLOGIES IN AGRICULTURE V, PT II
Keywords
Field
DocType
imaging hyper-spectrometer, noise, filtering, wavelet analysis, quantitative evaluation
Noise reduction,Computer vision,Imaging spectrometer,Median filter,Pattern recognition,Filter (signal processing),Hyperspectral imaging,Smoothing,Artificial intelligence,Moving average,Mathematics,Wavelet
Conference
Volume
Issue
ISSN
369
PART 2
1868-4238
Citations 
PageRank 
References 
2
0.46
2
Authors
7
Name
Order
Citations
PageRank
Hao Yang1287.63
Dongyan Zhang265.81
Wenjiang Huang317951.84
Zhongling Gao430.82
Xiaodong Yang55817.09
Li Cun-jun6138.27
Cunjun Li7124.61